Olaf Hellwich
Photo: SCIoI
Olaf Hellwich contributes to the autonomous acquisition of prior knowledge from visual experience and the application of the priors learned from that experience. He posseses expertise in feature extraction, learning of object models from features, 3D object reconstruction, and most recently deep learning.
Projects
Olaf Hellwich is member of:
• Project 01: Object-level scene descriptions and attention in visual search
• Project 08: Knowledge-augmented face perception
• Project 25: Mice learning in social interaction
• Project 29: Hierarchical modularized vision system for perception-action loops
• Project 31: Social responsiveness and its effects on learning in human-human and human-robot interaction
• Project 40: Big mouse data
• Project 46: Mouse lock box 2
• Project 57: Internal and External Visual Information Sampling Using Eye-Movements and Overt Attention in Dynamic Scenes
• Project 08: Knowledge-augmented face perception
• Project 25: Mice learning in social interaction
• Project 29: Hierarchical modularized vision system for perception-action loops
• Project 31: Social responsiveness and its effects on learning in human-human and human-robot interaction
• Project 40: Big mouse data
• Project 46: Mouse lock box 2
• Project 57: Internal and External Visual Information Sampling Using Eye-Movements and Overt Attention in Dynamic Scenes
Publications +
6984777
Hellwich
1
apa
50
date
desc
year
19872
https://www.scienceofintelligence.de/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22BH6IBKQ6%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Petkovi%5Cu0107%20et%20al.%22%2C%22parsedDate%22%3A%222026-06-18%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BPetkovi%26%23x107%3B%2C%20U.%2C%20Frenkel%2C%20J.%2C%20Lazarides%2C%20R.%2C%20%26amp%3B%20Hellwich%2C%20O.%20%282026%29.%20Modeling%20Student%20Engagement%20in%20the%20Wild%3A%20Analysis%20from%20Classroom%20Video.%20%26lt%3Bi%26gt%3BProceedings%20of%20the%2021st%20International%20Conference%20on%20Computer%20Vision%20Theory%20and%20Applications%26lt%3B%5C%2Fi%26gt%3B%2C%20439%26%23x2013%3B446.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.5220%5C%2F0014468800004084%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.5220%5C%2F0014468800004084%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Modeling%20Student%20Engagement%20in%20the%20Wild%3A%20Analysis%20from%20Classroom%20Video%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Uro%5Cu0161%22%2C%22lastName%22%3A%22Petkovi%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jonas%22%2C%22lastName%22%3A%22Frenkel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rebecca%22%2C%22lastName%22%3A%22Lazarides%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%5D%2C%22abstractNote%22%3A%22Digital%20Library%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%2021st%20International%20Conference%20on%20Computer%20Vision%20Theory%20and%20Applications%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222026-06-18%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.5220%5C%2F0014468800004084%22%2C%22ISBN%22%3A%22978-989-758-804-4%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A04%3A36Z%22%7D%7D%2C%7B%22key%22%3A%226EWSDF53%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Reiske%20et%20al.%22%2C%22parsedDate%22%3A%222026-06-15%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BReiske%2C%20P.%2C%20Boon%2C%20M.%20N.%2C%20Andresen%2C%20N.%2C%20Traverso%2C%20S.%2C%20Daniels%2C%20M.%2C%20Hohlbaum%2C%20K.%2C%20Lewejohann%2C%20L.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Sprekeler%2C%20H.%20%282026%29.%20Mouse%20Lockbox%20Dataset%3A%20Behavior%20Recognition%20for%20Mice%20Solving%20Lockboxes.%20%26lt%3Bi%26gt%3BInternational%20Journal%20of%20Computer%20Vision%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B134%26lt%3B%5C%2Fi%26gt%3B%287%29%2C%20318.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs11263-026-02908-x%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs11263-026-02908-x%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Mouse%20Lockbox%20Dataset%3A%20Behavior%20Recognition%20for%20Mice%20Solving%20Lockboxes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrik%22%2C%22lastName%22%3A%22Reiske%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marcus%20N.%22%2C%22lastName%22%3A%22Boon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sole%22%2C%22lastName%22%3A%22Traverso%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marieatou%22%2C%22lastName%22%3A%22Daniels%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22Sprekeler%22%7D%5D%2C%22abstractNote%22%3A%22Machine%20learning%20and%20computer%20vision%20methods%20have%20a%20major%20impact%20on%20the%20study%20of%20natural%20animal%20behavior%2C%20as%20they%20enable%20the%20%28semi-%29%20automatic%20analysis%20of%20vast%20amounts%20of%20video%20data.%20Such%20large-scale%20analysis%20is%20essential%20not%20only%20to%20mere%20behavioral%20research%20but%20its%20applicability%20spans%20across%20a%20large%20range%20of%20disciplines.%20Mice%20are%20the%20standard%20mammalian%20model%20system%20in%20most%20behavioral%20research%20fields%2C%20but%20the%20datasets%20available%20today%20to%20refine%20such%20methods%20focus%20either%20on%20isolated%20or%20social%20behaviors.%20In%20contrast%2C%20datasets%20in%20which%20animals%20interact%20with%20a%20physical%20apparatus%2C%20which%20is%20highly%20relevant%20across%20disciplines%20that%20study%20learning%2C%20are%20as%20of%20yet%20unavailable.%20In%20this%20work%2C%20we%20present%20a%20video%20dataset%20of%20individual%20mice%20solving%20%28multi-step%29%20mechanical%20puzzles%2C%20so-called%20lockboxes.%20The%20more%20than%20110%5Cu00a0hours%20of%20total%20playtime%20show%20their%20behavior%20recorded%20from%20three%20different%20perspectives.%20As%20a%20benchmark%20for%20frame-level%20action%20classification%20methods%2C%20we%20provide%20human-annotated%20labels%20for%20all%20videos%20of%20two%20different%20mice%2C%20equaling%2013%25%20of%20our%20dataset.%20Our%20action%20labels%20provide%20two%20levels%20of%20complexity%2C%20requiring%20the%20classification%20of%20both%20what%20the%20mouse%20is%20doing%20as%20well%20as%20which%20object%20is%20targeted.%20Additionally%2C%20as%20an%20initial%20comparison%20against%20the%20human-annotated%20labels%2C%20we%20used%20two%20different%20keypoint%5Cu00a0%28pose%29%20tracking-based%20action%20classification%20frameworks%20as%20well%20as%20an%20autoencoder-based%20framework%2C%20which%20illustrates%20the%20challenges%20of%20automated%20labeling%20of%20fine-grained%20behaviors%2C%20such%20as%20the%20manipulation%20of%20objects.%20We%20hope%20that%20our%20work%20will%20help%20accelerate%20the%20advancement%20of%20automated%20action%20and%20behavior%20classification%20in%20a%20task-driven%20environment.%20Our%20dataset%2C%20including%20videos%20and%20human-annotated%20labels%2C%20is%20publicly%20available%20at%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.14279%5C%2Fdepositonce-23850.%22%2C%22date%22%3A%222026-06-15%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2Fs11263-026-02908-x%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs11263-026-02908-x%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221573-1405%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22MZQLD39E%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Qu%20et%20al.%22%2C%22parsedDate%22%3A%222026-03%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BQu%2C%20R.%2C%20Hall%2C%20O.%2C%20Bideau%2C%20P.%20K.%2C%20Ouerfelli-Ethier%2C%20J.%2C%20Rolfs%2C%20M.%2C%20Obermayer%2C%20K.%2C%20%26amp%3B%20Hellwich%2C%20O.%20%282026%29.%20Salience-SGG%3A%20Enhancing%20Unbiased%20Scene%20Graph%20Generation%20with%20Iterative%20Salience%20Estimation.%20%26lt%3Bi%26gt%3B2026%20IEEE%5C%2FCVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%20%28WACV%29%26lt%3B%5C%2Fi%26gt%3B%2C%201032%26%23x2013%3B1042.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FWACV61042.2026.00107%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FWACV61042.2026.00107%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Salience-SGG%3A%20Enhancing%20Unbiased%20Scene%20Graph%20Generation%20with%20Iterative%20Salience%20Estimation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Runfeng%22%2C%22lastName%22%3A%22Qu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ole%22%2C%22lastName%22%3A%22Hall%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%20K%22%2C%22lastName%22%3A%22Bideau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julie%22%2C%22lastName%22%3A%22Ouerfelli-Ethier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Rolfs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Obermayer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%5D%2C%22abstractNote%22%3A%22Scene%20Graph%20Generation%20%28SGG%29%20suffers%20from%20a%20long-tailed%20distribution%2C%20where%20a%20few%20predicate%20classes%20dominate%20while%20many%20others%20are%20underrepresented%2C%20leading%20to%20biased%20models%20that%20underperform%20on%20rare%20relations.%20Unbiased-SGG%20methods%20address%20this%20by%20implementing%20debiasing%20strategies%2C%20but%20often%20at%20the%20cost%20of%20spatial%20understanding%5Cu2014resulting%20in%20over-reliance%20on%20semantic%20priors.%20We%20introduce%20Salience-SGG%2C%20a%20novel%20framework%20featuring%20an%20Iterative%20Salience%20Decoder%20%28ISD%29%20that%20emphasizes%20triplets%20with%20salient%20spatial%20structures.%20To%20support%20this%2C%20we%20propose%20semantic-agnostic%20salience%20labels%20guiding%20ISD.%20Evaluations%20on%20Visual%20Genome%2C%20Open%20Images%20V6%2C%20and%20GQA-200%20show%20that%20Salience-SGG%20achieves%20state-of-the-art%20performance%20and%20improves%20existing%20Unbiased-SGG%20methods%20in%20their%20spatial%20understanding%20as%20demonstrated%20by%20the%20Pairwise%20Localization%20Average%20Precision.%20Code%20is%20available%20at%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Frunfeng-q%5C%2FSalience-SGG.%22%2C%22proceedingsTitle%22%3A%222026%20IEEE%5C%2FCVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%20%28WACV%29%22%2C%22conferenceName%22%3A%222026%20IEEE%5C%2FCVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%20%28WACV%29%22%2C%22date%22%3A%222026-03%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FWACV61042.2026.00107%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fabstract%5C%2Fdocument%5C%2F11492111%22%2C%22ISSN%22%3A%222642-9381%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A05%3A09Z%22%7D%7D%2C%7B%22key%22%3A%22B42IVRCN%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Andresen%20et%20al.%22%2C%22parsedDate%22%3A%222026-02-18%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BAndresen%2C%20N.%2C%20W%26%23xF6%3Bllhaf%2C%20M.%2C%20Wilzopolski%2C%20J.%2C%20Lang%2C%20A.%2C%20Wolter%2C%20A.%2C%20Howe-Wittek%2C%20L.%2C%20Bekemeier%2C%20C.%2C%20Pawlak%2C%20L.-I.%2C%20Beyer%2C%20S.%2C%20Cynis%2C%20H.%2C%20Hietel%2C%20E.%2C%20Rieckmann%2C%20V.%2C%20Rieckmann%2C%20M.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20Lewejohann%2C%20L.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Hohlbaum%2C%20K.%20%282026%29.%20%26lt%3Bi%26gt%3BAutomatic%20pain%20face%20analysis%20in%20mice%3A%20Applied%20to%20a%20varied%20dataset%20with%20non-standardized%20conditions%26lt%3B%5C%2Fi%26gt%3B.%20bioRxiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.64898%5C%2F2026.02.16.706098%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.64898%5C%2F2026.02.16.706098%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Automatic%20pain%20face%20analysis%20in%20mice%3A%20Applied%20to%20a%20varied%20dataset%20with%20non-standardized%20conditions%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Manuel%22%2C%22lastName%22%3A%22W%5Cu00f6llhaf%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jenny%22%2C%22lastName%22%3A%22Wilzopolski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annemarie%22%2C%22lastName%22%3A%22Lang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Angelique%22%2C%22lastName%22%3A%22Wolter%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%22%2C%22lastName%22%3A%22Howe-Wittek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Clara%22%2C%22lastName%22%3A%22Bekemeier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Leonie-Iva%22%2C%22lastName%22%3A%22Pawlak%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sarah%22%2C%22lastName%22%3A%22Beyer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Holger%22%2C%22lastName%22%3A%22Cynis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Edith%22%2C%22lastName%22%3A%22Hietel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vera%22%2C%22lastName%22%3A%22Rieckmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Max%22%2C%22lastName%22%3A%22Rieckmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%5D%2C%22abstractNote%22%3A%22Biomedical%20research%20relies%20on%20scientifically%20validated%20tools%20to%20assess%20pain%2C%20suffering%2C%20and%20distress%20in%20laboratory%20animals%20to%20ensure%20their%20well-being.%20In%20mice%2C%20the%20most%20frequently%20used%20laboratory%20animals%2C%20the%20Mouse%20Grimace%20Scale%20%28MGS%29%20provides%20a%20reliable%20tool%20for%20the%20assessment%20of%20facial%20expression%20changes%20caused%20by%20impaired%20well-being.%20However%2C%20no%20automated%20tool%20can%20yet%20reliably%20assess%20all%20features%20of%20the%20MGS%20across%20different%20mouse%20strains%20under%20varying%20experimental%20or%20housing%20conditions%20in%20real-time%2C%20as%20the%20variability%20present%20in%20recorded%20image%20datasets%20poses%20substantial%20challenges%20for%20computer%20vision%20models.%20Despite%20this%20technical%20difficulty%2C%20variability%20across%20subsets%20in%20terms%20of%20mouse%20strain%2C%20treatments%2C%20laboratory%2C%20and%20image%20acquisition%20setup%20is%20essential%20for%20paving%20the%20way%20toward%20MGS%20assessment%20under%20non-standardized%20conditions%20in%20the%20home%20cage%20rather%20than%20standardized%20cage-side%20recording%20setups.%20Against%20this%20background%2C%20a%20large%20and%20diverse%20dataset%20containing%20five%20subsets%20is%20introduced%20and%20a%20deep%20learning%20model%20was%20trained%20to%20predict%20the%20average%20MGS%20scores%20ranging%20between%200%20and%202.%20It%20achieved%20a%20root%20mean%20squared%20error%20%28RMSE%29%20of%200.26%20when%20trained%20on%20all%20subsets%20of%20the%20dataset%2C%20outperforming%20the%20average%20human%20rater%20in%20terms%20of%20error%20magnitude.%20The%20correlation%20between%20human%20raters%20and%20automated%20MGS%20scores%20was%20very%20high%20%28Pearson%5Cu2019s%20r%3D0.85%29.%20In%20the%20cross-dataset%20evaluation%2C%20one%20subset%20was%20excluded%20from%20training%20and%20used%20for%20testing%20the%20model.%20This%20approach%20yielded%20higher%20errors%20compared%20to%20models%20trained%20and%20tested%20on%20the%20same%20subsets.%20A%20model%20restricted%20to%20the%20feature%20of%20orbital%20tightening%20showed%20lower%20performance%20than%20one%20trained%20on%20all%20facial%20features%20of%20the%20MGS.%20Overall%2C%20the%20most%20reliable%20model%20for%20predicting%20average%20MGS%20scores%20for%20a%20novel%20dataset%20is%20the%20one%20trained%20on%20the%20combined%20subsets.%20Performance%20may%20be%20further%20enhanced%20by%20fine-tuning%20the%20model%20using%20human-generated%20MGS%20scores%20for%20a%20portion%20of%20the%20novel%20subset.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22bioRxiv%22%2C%22archiveID%22%3A%22%22%2C%22date%22%3A%222026-02-18%22%2C%22DOI%22%3A%2210.64898%5C%2F2026.02.16.706098%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.biorxiv.org%5C%2Fcontent%5C%2F10.64898%5C%2F2026.02.16.706098v1%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A05%3A28Z%22%7D%7D%2C%7B%22key%22%3A%22GYPMKVUT%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Boon%20et%20al.%22%2C%22parsedDate%22%3A%222026%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBoon%2C%20M.%20N.%2C%20Andresen%2C%20N.%2C%20Traverso%2C%20S.%2C%20Meier%2C%20S.%2C%20Schuessler%2C%20F.%2C%20Hellwich%2C%20O.%2C%20Lewejohann%2C%20L.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20Hohlbaum%2C%20K.%2C%20%26amp%3B%20Sprekeler%2C%20H.%20%282026%29.%20%26lt%3Bi%26gt%3BMechanical%20problem%20solving%20in%20mice%26lt%3B%5C%2Fi%26gt%3B%20%5BPoster%5D.%20Computational%20and%20Systems%20Neuroscience%20%28COSYNE%29%202026.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Mechanical%20problem%20solving%20in%20mice%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Marcus%20N.%22%2C%22lastName%22%3A%22Boon%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Sole%22%2C%22lastName%22%3A%22Traverso%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Sophia%22%2C%22lastName%22%3A%22Meier%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Friedrich%22%2C%22lastName%22%3A%22Schuessler%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22Sprekeler%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222026%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T10%3A44%3A39Z%22%7D%7D%2C%7B%22key%22%3A%22Z54LB52K%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Petkovi%5Cu0107%20et%20al.%22%2C%22parsedDate%22%3A%222025-12-01%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BPetkovi%26%23x107%3B%2C%20U.%2C%20Frenkel%2C%20J.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Lazarides%2C%20R.%20%282025%29.%20Modeling%20Teacher%20Nonverbal%20Immediacy%3A%20Refinement%20and%20Analysis.%20%26lt%3Bi%26gt%3BAdaptive%20Behavior%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B33%26lt%3B%5C%2Fi%26gt%3B%285%26%23x2013%3B6%29%2C%20347%26%23x2013%3B363.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F10597123251374920%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F10597123251374920%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Modeling%20Teacher%20Nonverbal%20Immediacy%3A%20Refinement%20and%20Analysis%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Uro%5Cu0161%22%2C%22lastName%22%3A%22Petkovi%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jonas%22%2C%22lastName%22%3A%22Frenkel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rebecca%22%2C%22lastName%22%3A%22Lazarides%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20presents%20a%20refined%20computational%20approach%20for%20assessing%20teacher%20nonverbal%20immediacy%20%28NVI%29%20from%20classroom%20video%20recordings.%20Building%20on%20a%20previously%20published%20baseline%20model%2C%20we%20re-examined%20the%20original%20ten-feature%20representation%20to%20evaluate%20whether%20focused%2C%20theory-driven%20refinements%20could%20improve%20model%20performance%20without%20altering%20the%20preprocessing%20pipeline.%20The%20revised%20feature%20set%20includes%20distance%20variability%2C%20face%20visibility%2C%20and%20a%20merged%20negative%20affect%20channel%2C%20alongside%20existing%20measures%20of%20gesture%20intensity%2C%20perceived%20proximity%2C%20and%20facial%20expressions.%20Models%20were%20trained%20and%20validated%20on%20a%20dataset%20of%20403%20annotated%2030-second%20video%20segments%20from%20German%20secondary%20school%20classrooms.%20We%20evaluated%20four%20classical%20regressors%5Cu2014linear%20regression%2C%20support%20vector%20regression%2C%20random%20forest%2C%20and%20extra%20trees%5Cu2014alongside%20the%20original%20multilayer%20perceptron%20%28MLP%29.%20The%20refined%20MLP%20improved%20the%20correlation%20with%20human%20ratings%20from%200.44%20to%200.49%20and%20showed%20the%20most%20consistent%20prediction%20errors%20across%20teachers.%20Feature%20sensitivity%20analysis%20confirmed%20that%20the%20model%5Cu2019s%20predictions%20aligned%20with%20theoretical%20expectations%3A%20greater%20proximity%2C%20facial%20visibility%2C%20and%20expressive%20gestures%20were%20associated%20with%20higher%20immediacy.%20These%20results%20highlight%20the%20value%20of%20integrating%20behavioral%20theory%20into%20model%20design%20and%20support%20the%20use%20of%20automated%20tools%20for%20scalable%2C%20interpretable%20analysis%20of%20nonverbal%20communication%20in%20classroom%20settings.%22%2C%22date%22%3A%222025-12-01%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1177%5C%2F10597123251374920%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F10597123251374920%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221059-7123%22%2C%22language%22%3A%22EN%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22EXWDR2GP%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Maier%20et%20al.%22%2C%22parsedDate%22%3A%222025-04-02%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BMaier%2C%20M.%2C%20Leonhardt%2C%20A.%2C%20Blume%2C%20F.%2C%20Bideau%2C%20P.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Abdel%20Rahman%2C%20R.%20%282025%29.%20Neural%20dynamics%20of%20mental%20state%20attribution%20to%20social%20robot%20faces.%20%26lt%3Bi%26gt%3BSocial%20Cognitive%20and%20Affective%20Neuroscience%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B20%26lt%3B%5C%2Fi%26gt%3B%281%29%2C%20nsaf027.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fscan%5C%2Fnsaf027%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fscan%5C%2Fnsaf027%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Neural%20dynamics%20of%20mental%20state%20attribution%20to%20social%20robot%20faces%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Maier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexander%22%2C%22lastName%22%3A%22Leonhardt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Blume%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Bideau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rasha%22%2C%22lastName%22%3A%22Abdel%20Rahman%22%7D%5D%2C%22abstractNote%22%3A%22Abstract%5Cn%20%20%20%20%20%20%20%20%20%20%20%20The%20interplay%20of%20mind%20attribution%20and%20emotional%20responses%20is%20considered%20crucial%20in%20shaping%20human%20trust%20and%20acceptance%20of%20social%20robots.%20Understanding%20this%20interplay%20can%20help%20us%20create%20the%20right%20conditions%20for%20successful%20human%5Cu2013robot%20social%20interaction%20in%20alignment%20with%20societal%20goals.%20Our%20study%20shows%20that%20affective%20information%20about%20robots%20describing%20positive%2C%20negative%2C%20or%20neutral%20behaviour%20leads%20participants%20%28N%5Cu2009%3D%5Cu200990%29%20to%20attribute%20mental%20states%20to%20robot%20faces%2C%20modulating%20impressions%20of%20trustworthiness%2C%20facial%20expression%2C%20and%20intentionality.%20Electroencephalography%20recordings%20from%2030%20participants%20revealed%20that%20affective%20information%20influenced%20specific%20processing%20stages%20in%20the%20brain%20associated%20with%20early%20face%20perception%20%28N170%20component%29%20and%20more%20elaborate%20stimulus%20evaluation%20%28late%20positive%20potential%29.%20However%2C%20a%20modulation%20of%20fast%20emotional%20brain%20responses%2C%20typically%20found%20for%20human%20faces%20%28early%20posterior%20negativity%29%2C%20was%20not%20observed.%20These%20findings%20suggest%20that%20neural%20processing%20of%20robot%20faces%20alternates%20between%20being%20perceived%20as%20mindless%20machines%20and%20intentional%20agents%3A%20people%20rapidly%20attribute%20mental%20states%20during%20perception%2C%20literally%20seeing%20good%20or%20bad%20intentions%20in%20robot%20faces%2C%20but%20are%20emotionally%20less%20affected%20than%20when%20facing%20humans.%20These%20nuanced%20insights%20into%20the%20fundamental%20psychological%20and%20neural%20processes%20underlying%20mind%20attribution%20can%20enhance%20our%20understanding%20of%20human%5Cu2013robot%20social%20interactions%20and%20inform%20policies%20surrounding%20the%20moral%20responsibility%20of%20artificial%20agents.%22%2C%22date%22%3A%222025-04-02%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1093%5C%2Fscan%5C%2Fnsaf027%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Facademic.oup.com%5C%2Fscan%5C%2Farticle%5C%2Fdoi%5C%2F10.1093%5C%2Fscan%5C%2Fnsaf027%5C%2F8069429%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221749-5016%2C%201749-5024%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A58%3A33Z%22%7D%7D%2C%7B%22key%22%3A%22I47S7QBP%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Blume%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBlume%2C%20F.%2C%20Qu%2C%20R.%2C%20Bideau%2C%20P.%2C%20Maier%2C%20M.%2C%20Rahman%2C%20R.%20A.%2C%20%26amp%3B%20Hellwich%2C%20O.%20%282025%29.%20How%20Do%20You%20Perceive%20My%20Face%3F%20Recognizing%20Facial%20Expressions%20in%26%23xA0%3BMulti-modal%20Context%20by%26%23xA0%3BModeling%20Mental%20Representations.%20In%20D.%20Cremers%2C%20Z.%20L%26%23xE4%3Bhner%2C%20M.%20Moeller%2C%20M.%20Nie%26%23xDF%3Bner%2C%20B.%20Ommer%2C%20%26amp%3B%20R.%20Triebel%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BPattern%20Recognition%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%2020%26%23x2013%3B36%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-85187-2_2%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-85187-2_2%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22How%20Do%20You%20Perceive%20My%20Face%3F%20Recognizing%20Facial%20Expressions%20in%5Cu00a0Multi-modal%20Context%20by%5Cu00a0Modeling%20Mental%20Representations%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Blume%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Runfeng%22%2C%22lastName%22%3A%22Qu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Bideau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Maier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rasha%20Abdel%22%2C%22lastName%22%3A%22Rahman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Cremers%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Zorah%22%2C%22lastName%22%3A%22L%5Cu00e4hner%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Moeller%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Matthias%22%2C%22lastName%22%3A%22Nie%5Cu00dfner%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Bj%5Cu00f6rn%22%2C%22lastName%22%3A%22Ommer%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Rudolph%22%2C%22lastName%22%3A%22Triebel%22%7D%5D%2C%22abstractNote%22%3A%22Facial%20expression%20perception%20in%20humans%20inherently%20relies%20on%20prior%20knowledge%20and%20contextual%20cues%2C%20contributing%20to%20efficient%20and%20flexible%20processing.%20For%20instance%2C%20multi-modal%20emotional%20context%20%28such%20as%20voice%20color%2C%20affective%20text%2C%20body%20pose%2C%20etc.%29%20can%20prompt%20people%20to%20perceive%20emotional%20expressions%20in%20objectively%20neutral%20faces.%20Drawing%20inspiration%20from%20this%2C%20we%20introduce%20a%20novel%20approach%20for%20facial%20expression%20classification%20that%20goes%20beyond%20simple%20classification%20tasks.%20Our%20model%20accurately%20classifies%20a%20perceived%20face%20and%20synthesizes%20the%20corresponding%20mental%20representation%20perceived%20by%20a%20human%20when%20observing%20a%20face%20in%20context.%20With%20this%2C%20our%20model%20offers%20visual%20insights%20into%20its%20internal%20decision-making%20process.%20We%20achieve%20this%20by%20learning%20two%20independent%20representations%20of%20content%20and%20context%20using%20a%20VAE-GAN%20architecture.%20Subsequently%2C%20we%20propose%20a%20novel%20attention%20mechanism%20for%20context-dependent%20feature%20adaptation.%20The%20adapted%20representation%20is%20used%20for%20classification%20and%20to%20generate%20a%20context-augmented%20expression.%20We%20evaluate%20synthesized%20expressions%20in%20a%20human%20study%2C%20showing%20that%20our%20model%20effectively%20produces%20approximations%20of%20human%20mental%20representations.%20We%20achieve%20State-of-the-Art%20classification%20accuracies%20of%2081.01%25%20on%20the%20RAVDESS%20dataset%20and%2079.34%25%20on%20the%20MEAD%20dataset.%20We%20make%20our%20code%20publicly%20available.%22%2C%22proceedingsTitle%22%3A%22Pattern%20Recognition%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-85187-2_2%22%2C%22ISBN%22%3A%22978-3-031-85187-2%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22LTG2U5B6%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Lazarides%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLazarides%2C%20R.%2C%20Frenkel%2C%20J.%2C%20Daumiller%2C%20M.%2C%20Dresel%2C%20M.%2C%20Petkovi%26%23x107%3B%2C%20U.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20G%26%23xF6%3Bllner%2C%20R.%20%282025%29.%20Disentangling%20teacher%20and%20lesson%20variance%20and%20their%20relations%20to%20supportive%20learning%20environments%3A%20A%20machine%20learning%20assessment%20of%20teacher%20nonverbal%20behavior.%20%26lt%3Bi%26gt%3BJournal%20of%20Educational%20Psychology%26lt%3B%5C%2Fi%26gt%3B.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1037%5C%2Fedu0000999%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1037%5C%2Fedu0000999%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Disentangling%20teacher%20and%20lesson%20variance%20and%20their%20relations%20to%20supportive%20learning%20environments%3A%20A%20machine%20learning%20assessment%20of%20teacher%20nonverbal%20behavior%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rebecca%22%2C%22lastName%22%3A%22Lazarides%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jonas%22%2C%22lastName%22%3A%22Frenkel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Daumiller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22Dresel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Uro%5Cu0161%22%2C%22lastName%22%3A%22Petkovi%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Richard%22%2C%22lastName%22%3A%22G%5Cu00f6llner%22%7D%5D%2C%22abstractNote%22%3A%22Teachers%5Cu2019%20nonverbal%20behaviors%20are%20critical%20for%20motivating%20students%20and%20fostering%20learning.%20However%2C%20there%20is%20a%20lack%20of%20research%20considering%20the%20situatedness%20of%20nonverbal%20teaching%20behaviors.%20Further%2C%20the%20question%20remains%20as%20to%20how%20nonverbal%20behaviors%20interrelate%20with%20dimensions%20of%20supportive%20teaching.%20We%20utilized%20a%20machine%20learning%20approach%20to%20assess%20teachers%5Cu2019%20nonverbal%20immediacy%20%28NVI%29%20from%20classroom%20video%20data%20and%20investigated%20its%20variability%20across%20learning%20situations%2C%20lessons%2C%20and%20teachers.%20Additionally%2C%20we%20examined%20the%20relations%20between%20teachers%5Cu2019%20NVI%20and%20observer-rated%20social%5Cu2013emotional%20support%20at%20the%20level%20of%20the%20teacher%2C%20the%20lesson%2C%20and%20the%20learning%20situation.%20We%20also%20investigated%20relations%20between%20NVI%20and%20student%5Cu2013teacher%20relationships%20and%20autonomy%20support%20focused%20on%20the%20lessons%20of%20the%20specific%20teaching%20unit%20as%20reported%20by%20the%20teacher%20and%20the%20students%20after%20the%20lessons.%20Data%20stemmed%20from%20the%20German%20Teaching%20and%20Learning%20International%20Survey%20%28TALIS%29%20video%20study%20%28Klieme%20et%20al.%2C%202023%29%2C%20which%20was%20implemented%20as%20a%20national%20sub-study%20of%20the%20international%20TALIS%20video%20study.%20The%20sample%20of%20the%20German%20TALIS%20video%20study%20included%2050%20teachers%20%2846%25%20women%3B%20Mage%20%3D%2043%20years%29%20and%20their%201%2C140%20students%20%2853%25%20girls%3B%20Mage%20%3D%2015%20years%29.%20Machine%20learning-assessed%20NVI%20showed%2022.5%25%20between-teacher%20and%205.6%25%20between-lesson%20variance%2C%20with%20%5Cu223c71.7%25%20at%20the%20situational%20level.%20Externally%20observed%20socioemotional%20support%20showed%20higher%20variance%20between%20teachers%20%2839.9%25%29%20and%20lessons%20%2825.5%25%29%2C%20but%20lower%20variance%20at%20the%20situational%20level%20%28%5Cu223c34.5%25%29.%20Results%20from%20three-level%20modeling%20revealed%20that%20teachers%5Cu2019%20NVI%20differed%20substantially%20between%20teachers%20and%20lessons.%20Teachers%5Cu2019%20NVI%20was%20significantly%20positively%20associated%20with%20observer-rated%20socioemotional%20support%20across%20all%20levels%20of%20analysis.%20At%20the%20teacher%20level%2C%20teachers%5Cu2019%20NVI%20was%20significantly%20and%20positively%20related%20to%20autonomy%20support.%20Our%20findings%20indicate%20that%20nonverbal%20behaviors%20of%20the%20teacher%20assessed%20using%20computational%20modeling%20are%20substantially%20related%20to%20a%20supportive%20classroom%20climate.%20%28PsycInfo%20Database%20Record%20%28c%29%202026%20APA%2C%20all%20rights%20reserved%29%22%2C%22date%22%3A%222025%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1037%5C%2Fedu0000999%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221939-2176%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22T243JJ7N%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Lazarides%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLazarides%2C%20R.%2C%20Frenkel%2C%20J.%2C%20Petkovi%26%23x107%3B%2C%20U.%2C%20G%26%23xF6%3Bllner%2C%20R.%2C%20%26amp%3B%20Hellwich%2C%20O.%20%282025%29.%20%26%23x2018%3BNo%20words%26%23x2019%3B%26%23x2014%3BMachine-learning%20classified%20nonverbal%20immediacy%20and%20its%20role%20in%20connecting%20teacher%20self-efficacy%20with%20perceived%20teaching%20and%20student%20interest.%20%26lt%3Bi%26gt%3BBritish%20Journal%20of%20Educational%20Psychology%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B95%26lt%3B%5C%2Fi%26gt%3B%28S1%29%2C%20S15%26%23x2013%3BS31.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1111%5C%2Fbjep.12732%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1111%5C%2Fbjep.12732%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22%5Cu2018No%20words%5Cu2019%5Cu2014Machine-learning%20classified%20nonverbal%20immediacy%20and%20its%20role%20in%20connecting%20teacher%20self-efficacy%20with%20perceived%20teaching%20and%20student%20interest%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rebecca%22%2C%22lastName%22%3A%22Lazarides%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jonas%22%2C%22lastName%22%3A%22Frenkel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Uro%5Cu0161%22%2C%22lastName%22%3A%22Petkovi%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Richard%22%2C%22lastName%22%3A%22G%5Cu00f6llner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%5D%2C%22abstractNote%22%3A%22Background%20Much%20is%20known%20about%20the%20positive%20effects%20of%20teachers%26%23039%3B%20self-efficacy%20on%20instruction%20and%20student%20outcomes%2C%20but%20the%20processes%20underlying%20these%20relations%20are%20unknown.%20Aims%20We%20aimed%20to%20examine%20the%20effects%20of%20teacher%20self-efficacy%20for%20student%20engagement%20%28TSESE%29%20before%20a%20lesson%20on%20teachers%26%23039%3B%20nonverbal%20immediacy%20%28NVI%29%20and%20their%20enthusiastic%20teaching.%20Furthermore%2C%20we%20examined%20how%20NVI%20and%20enthusiastic%20teaching%20affected%20students%26%23039%3B%20interest%20after%20the%20lesson%2C%20controlling%20for%20prior%20interest.%20Sample%20We%20used%20data%20from%20the%20German%20TALIS%20video%20study%20in%20the%20context%20of%20the%20international%20TALIS%20study.%20The%20study%20included%2050%20teachers%20%2846%25%20women%29%20and%20their%201140%20students%20%2853%25%20girls%3B%20ageM%20%3D%2015%20years%29.%20Methods%20We%20developed%20a%20computational%20model%20to%20assess%20teachers%26%23039%3B%20NVI%20on%20classroom%20video%20data.%20Using%20a%20multimodal%20longitudinal%20approach%2C%20we%20tested%20sequential%20processes%20with%20multilevel%20path%20models.%20Results%20TSESE%20before%20the%20lesson%20%28Time%201%29%20was%20positively%20and%20significantly%20related%20to%20teachers%26%23039%3B%20NVI%20during%20the%20lesson%20%28Time%202%29.%20Teachers%26%23039%3B%20NVI%20%28Time%202%29%20was%20positively%20related%20to%20class-level%20enthusiastic%20teaching%20behaviours%2C%20reported%20after%20the%20lesson%20%28Time%203%29.%20Student-reported%20enthusiastic%20teaching%20behaviours%20%28Time%203%29%20were%20significantly%20and%20positively%20associated%20with%20students%26%23039%3B%20interest%20%28Time%203%29%20when%20controlling%20for%20students%26%23039%3B%20prior%20interest%20%28Time%201%29.%20Students%26%23039%3B%20interest%20after%20the%20lesson%20%28Time%203%29%20was%20significantly%20and%20positively%20related%20to%20students%26%23039%3B%20interest%206%20weeks%20later%20%28Time%204%29.%20Conclusions%20Nonverbal%20behaviours%20of%20the%20teacher%20are%20central%20to%20classroom%20instruction%20by%20promoting%20students%26%23039%3B%20perceptions%20of%20the%20teachers%26%23039%3B%20enthusiastic%20teaching%20behaviours.%22%2C%22date%22%3A%222025%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1111%5C%2Fbjep.12732%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2Fabs%5C%2F10.1111%5C%2Fbjep.12732%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222044-8279%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A03%3A35Z%22%7D%7D%2C%7B%22key%22%3A%22TGQP4XZ4%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Petkovi%5Cu0107%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BPetkovi%26%23x107%3B%2C%20U.%2C%20Frenkel%2C%20J.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Lazarides%2C%20R.%20%282025%29.%20Nonverbal%20Immediacy%20Analysis%20in%26%23xA0%3BEducation%3A%20A%20Multimodal%20Computational%20Model.%20In%20O.%20Brock%20%26amp%3B%20J.%20Krichmar%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BFrom%20Animals%20to%20Animats%2017%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%20326%26%23x2013%3B338%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-71533-4_26%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-71533-4_26%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Nonverbal%20Immediacy%20Analysis%20in%5Cu00a0Education%3A%20A%20Multimodal%20Computational%20Model%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Uro%5Cu0161%22%2C%22lastName%22%3A%22Petkovi%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jonas%22%2C%22lastName%22%3A%22Frenkel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rebecca%22%2C%22lastName%22%3A%22Lazarides%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Brock%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Jeffrey%22%2C%22lastName%22%3A%22Krichmar%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20introduces%20a%20novel%20computational%20approach%20for%20analyzing%20nonverbal%20social%20behavior%20in%20educational%20settings.%20Integrating%20multimodal%20behavioral%20cues%2C%20including%20facial%20expressions%2C%20gesture%20intensity%2C%20and%20spatial%20dynamics%2C%20the%20model%20assesses%20the%20nonverbal%20immediacy%20%28NVI%29%20of%20teachers%20from%20RGB%20classroom%20videos.%20A%20dataset%20of%20400%2030-s%20video%20segments%20from%20German%20classrooms%20was%20constructed%20for%20model%20training%20and%20validation.%20The%20gesture%20intensity%20regressor%20achieved%20a%20correlation%20of%200.84%2C%20the%20perceived%20distance%20regressor%200.55%2C%20and%20the%20NVI%20model%200.44%20with%20median%20human%20ratings.%20The%20model%20demonstrates%20the%20potential%20to%20provide%20a%20valuable%20support%20in%20nonverbal%20behavior%20assessment%2C%20approximating%20the%20accuracy%20of%20individual%20human%20raters.%20Validated%20against%20both%20questionnaire%20data%20and%20trained%20observer%20ratings%2C%20our%20models%20show%20moderate%20to%20strong%20correlations%20with%20relevant%20educational%20outcomes%2C%20indicating%20their%20efficacy%20in%20reflecting%20effective%20teaching%20behaviors.%20This%20research%20advances%20the%20objective%20assessment%20of%20nonverbal%20communication%20behaviors%2C%20opening%20new%20pathways%20for%20educational%20research.%22%2C%22proceedingsTitle%22%3A%22From%20Animals%20to%20Animats%2017%22%2C%22conferenceName%22%3A%22SAB%202024%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-71533-4_26%22%2C%22ISBN%22%3A%22978-3-031-71533-4%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A01%3A34Z%22%7D%7D%2C%7B%22key%22%3A%22LVXQ3QLA%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hall%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHall%2C%20O.%2C%20Qu%2C%20R.%2C%20Ouerfelli-Ethier%2C%20J.%2C%20Hellwich%2C%20O.%2C%20Obermayer%2C%20K.%2C%20%26amp%3B%20Rolfs%2C%20M.%20%282025%29.%20%26lt%3Bi%26gt%3BModelling%20visual%20attention%20in%20dynamic%20scenes%20under%20partially%20competing%20task%20demands.%26lt%3B%5C%2Fi%26gt%3B%20%5BPoster%5D.%20Systems%20Vision%20Science%20Symposium.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Modelling%20visual%20attention%20in%20dynamic%20scenes%20under%20partially%20competing%20task%20demands.%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22O.%22%2C%22lastName%22%3A%22Hall%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22R.%22%2C%22lastName%22%3A%22Qu%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22J.%22%2C%22lastName%22%3A%22Ouerfelli-Ethier%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22O.%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22K.%22%2C%22lastName%22%3A%22Obermayer%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22M.%22%2C%22lastName%22%3A%22Rolfs%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T10%3A44%3A39Z%22%7D%7D%2C%7B%22key%22%3A%22UMYYUD5Y%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Reiske%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BReiske%2C%20P.%2C%20Boon%2C%20M.%20N.%2C%20Andresen%2C%20N.%2C%20Traverso%2C%20S.%2C%20Hohlbaum%2C%20K.%2C%20Lewejohann%2C%20L.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Sprekeler%2C%20H.%20%282025%29.%20%26lt%3Bi%26gt%3BMouse%20Lockbox%20Dataset%3A%20Behavior%20Recognition%20for%20Mice%20Solving%20Lockboxes%26lt%3B%5C%2Fi%26gt%3B.%20CV4Animals%20Workshop%20at%20IEEE%5C%2FCVF%20Computer%20Vision%20and%20Pattern%20Recognition%20Conference%20%28CVPR%29.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Mouse%20Lockbox%20Dataset%3A%20Behavior%20Recognition%20for%20Mice%20Solving%20Lockboxes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrik%22%2C%22lastName%22%3A%22Reiske%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marcus%20N.%22%2C%22lastName%22%3A%22Boon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Soledad%22%2C%22lastName%22%3A%22Traverso%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22Sprekeler%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%22%22%2C%22conferenceName%22%3A%22CV4Animals%20Workshop%20at%20IEEE%5C%2FCVF%20Computer%20Vision%20and%20Pattern%20Recognition%20Conference%20%28CVPR%29%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T10%3A44%3A39Z%22%7D%7D%2C%7B%22key%22%3A%229HCXXJXZ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hohlbaum%20et%20al.%22%2C%22parsedDate%22%3A%222024-08-28%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHohlbaum%2C%20K.%2C%20Andresen%2C%20N.%2C%20Mieske%2C%20P.%2C%20Kahnau%2C%20P.%2C%20Lang%2C%20B.%2C%20Diederich%2C%20K.%2C%20Palme%2C%20R.%2C%20Mundhenk%2C%20L.%2C%20Sprekeler%2C%20H.%2C%20Hellwich%2C%20O.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20%26amp%3B%20Lewejohann%2C%20L.%20%282024%29.%20Lockbox%20enrichment%20facilitates%20manipulative%20and%20cognitive%20activities%20for%20mice.%20%26lt%3Bi%26gt%3BOpen%20Research%20Europe%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B4%26lt%3B%5C%2Fi%26gt%3B%2C%20108.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.12688%5C%2Fopenreseurope.17624.2%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.12688%5C%2Fopenreseurope.17624.2%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Lockbox%20enrichment%20facilitates%20manipulative%20and%20cognitive%20activities%20for%20mice%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%22%2C%22lastName%22%3A%22Mieske%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Kahnau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Benjamin%22%2C%22lastName%22%3A%22Lang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kai%22%2C%22lastName%22%3A%22Diederich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rupert%22%2C%22lastName%22%3A%22Palme%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Mundhenk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22Sprekeler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%5D%2C%22abstractNote%22%3A%22Background%20Due%20to%20the%20lack%20of%20complexity%20and%20variety%20of%20stimuli%2C%20conventional%20housing%20conditions%20of%20laboratory%20mice%20do%20not%20allow%20these%20animals%20to%20fully%20express%20their%20behavioral%20repertoire%2C%20including%20manipulative%20and%20cognitive%20activities.%20Therefore%2C%20we%20designed%20mechanical%20puzzles%2C%20so-called%20lockboxes%2C%20for%20mice%20that%20can%20be%20provided%20in%20their%20home%20cages.%20We%20investigated%20the%20impact%20of%20the%20lockbox%20enrichment%20on%20their%20phenotype%20and%20affective%20state%20when%20compared%20to%20conventional%20housing%20%28CH%29%20and%20super-environmental%20enrichment%20%28SEE%29.%20Methods%20Young%20adult%20female%20C57BL%5C%2F6JCrl%20mice%20were%20examined%20before%20and%20after%202-month%20exposure%20to%20the%20different%20types%20of%20enrichment%20in%20a%20phenotyping%20test%20battery%2C%20including%20tests%20for%20trait%20and%20state%20anxiety-related%20behavior%2C%20calorimetric%20measurements%2C%20body%20weight%20measurements%2C%20the%20analysis%20of%20stress%20hormone%20metabolite%20concentrations%2C%20and%20sequential%20problem-solving%20abilities%20with%20a%20novel%20lockbox.%20At%20the%20end%20of%20the%20study%2C%20adrenal%20gland%20weights%20were%20determined%20and%20pathohistological%20evaluation%20was%20performed.%20For%20all%20continuous%20variables%2C%20the%20relative%20variability%20was%20calculated.%20Results%20While%20the%20different%20types%20of%20enrichment%20affected%20trait%20anxiety-related%20behavior%2C%20neither%20state%20anxiety-related%20behavior%20nor%20physiological%20variables%20%28i.e.%2C%20bodyweight%2C%20resting%20metabolic%20rate%2C%20stress%20hormone%20metabolite%20concentrations%2C%20adrenal%20gland%20weights%29%20were%20influenced.%20LE%20improved%20sequential%20problem-solving%20%28i.e.%2C%20solving%20novel%20lockboxes%29%20when%20compared%20to%20SEE.%20Regardless%20of%20the%20housing%20condition%2C%20the%20relative%20variability%20increased%20in%20most%20variables%20over%20time%2C%20although%20the%20coefficient%20of%20variation%20decreased%20for%20some%20variables%2C%20especially%20in%20animals%20with%20access%20to%20LE.%20There%20was%20no%20evidence%20of%20toxicopathological%20effects%20associated%20with%20the%20material%20from%20which%20the%20lockboxes%20were%20made.%20Conclusions%20All%20lockboxes%20are%20available%20as%20open-source%20tool.%20LE%20revealed%20beneficial%20effects%20on%20the%20affective%20state%20of%20laboratory%20mice%20and%20their%20performance%20in%20solving%20novel%20lockboxes.%20Neither%20relevant%20phenotype%20of%20the%20mice%20nor%20reproducibility%20of%20the%20data%20were%20compromised%20by%20LE%2C%20similar%20to%20SEE.%20The%20lockboxes%20may%20also%20be%20used%20as%20novel%20approach%20for%20assessing%20cognition%20in%20mice.%22%2C%22date%22%3A%222024-8-28%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.12688%5C%2Fopenreseurope.17624.2%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fopen-research-europe.ec.europa.eu%5C%2Farticles%5C%2F4-108%5C%2Fv2%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222732-5121%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A58%3A06Z%22%7D%7D%2C%7B%22key%22%3A%22BPRZ4YZZ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Boon%20et%20al.%22%2C%22parsedDate%22%3A%222024-07-30%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBoon%2C%20M.%20N.%2C%20Andresen%2C%20N.%2C%20Traverso%2C%20S.%2C%20Meier%2C%20S.%2C%20Schuessler%2C%20F.%2C%20Hellwich%2C%20O.%2C%20Lewejohann%2C%20L.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20Sprekeler%2C%20H.%2C%20%26amp%3B%20Hohlbaum%2C%20K.%20%282024%29.%20%26lt%3Bi%26gt%3BMechanical%20problem%20solving%20in%20mice%26lt%3B%5C%2Fi%26gt%3B.%20bioRxiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1101%5C%2F2024.07.29.605658%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1101%5C%2F2024.07.29.605658%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Mechanical%20problem%20solving%20in%20mice%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marcus%20Nicolaas%22%2C%22lastName%22%3A%22Boon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Soledad%22%2C%22lastName%22%3A%22Traverso%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sophia%22%2C%22lastName%22%3A%22Meier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedrich%22%2C%22lastName%22%3A%22Schuessler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22Sprekeler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%5D%2C%22abstractNote%22%3A%22Behavioral%20learning%20is%20a%20complex%20phenomenon%20that%20involves%20cognitive%2C%20perceptual%2C%20motor%2C%20and%20emotional%20contributions.%20Yet%2C%20most%20animal%20studies%20focus%20on%20reductionist%20tasks%20that%20aim%20to%20isolate%20one%20of%20these%20aspects.%20%5CnHere%2C%20we%20use%20a%20lockbox%20%5Cu2014%20a%20complex%2C%20multi-step%20mechanical%20puzzle%20%20%5Cu2014%20to%20study%20learning%20dynamics%20in%20freely%20behaving%20mice.%20The%20mice%20engaged%20spontaneously%20with%20the%20task%20and%20learned%20to%20solve%20it%20within%20just%20a%20few%20trials.%20To%20dissect%20different%20contributions%20to%20this%20rapid%20form%20of%20learning%2C%20we%20combined%20deep%20learning-based%20behavioral%20tracking%20in%20a%20multi-camera%20setup%20with%20probabilistic%20inference%20and%20computational%20modeling.%20%5CnWe%20find%20that%20the%20learning%20progress%20of%20the%20mice%20was%20initially%20dominated%20by%20the%20acquisition%20of%20motor%20skills%2C%20i.e.%2C%20the%20increased%20ability%20to%20manipulate%20the%20individual%20mechanisms%2C%20while%20a%20cognitive%20strategy%20for%20the%20task%20sequence%20emerged%20only%20later.%20The%20lockbox%20paradigm%20may%20hence%20offer%20a%20promising%20framework%20for%20studying%20the%20interaction%20between%20low-level%20motor%20learning%20and%20high-level%20decision-making%20strategies%20in%20a%20single%2C%20ethologically%20relevant%20task.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22bioRxiv%22%2C%22archiveID%22%3A%22%22%2C%22date%22%3A%222024-07-30%22%2C%22DOI%22%3A%2210.1101%5C%2F2024.07.29.605658%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fbiorxiv.org%5C%2Flookup%5C%2Fdoi%5C%2F10.1101%5C%2F2024.07.29.605658%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A59%3A00Z%22%7D%7D%2C%7B%22key%22%3A%22QKAHMER8%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Halawa%20et%20al.%22%2C%22parsedDate%22%3A%222024-06%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHalawa%2C%20M.%2C%20Blume%2C%20F.%2C%20Bideau%2C%20P.%2C%20Maier%2C%20M.%2C%20Rahman%2C%20R.%20A.%2C%20%26amp%3B%20Hellwich%2C%20O.%20%282024%29.%20Multi-Task%20Multi-Modal%20Self-Supervised%20Learning%20for%20Facial%20Expression%20Recognition.%20%26lt%3Bi%26gt%3B2024%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%26lt%3B%5C%2Fi%26gt%3B%2C%204604%26%23x2013%3B4614.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPRW63382.2024.00463%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPRW63382.2024.00463%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Multi-Task%20Multi-Modal%20Self-Supervised%20Learning%20for%20Facial%20Expression%20Recognition%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marah%22%2C%22lastName%22%3A%22Halawa%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Blume%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Bideau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Maier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rasha%20Abdel%22%2C%22lastName%22%3A%22Rahman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%5D%2C%22abstractNote%22%3A%22Human%20communication%20is%20multi-modal%3B%20e.g.%2C%20face-to-face%20interaction%20involves%20auditory%20signals%20%28speech%29%20and%20visual%20signals%20%28face%20movements%20and%20hand%20gestures%29.%20Hence%2C%20it%20is%20essential%20to%20exploit%20multiple%20modalities%20when%20designing%20machine%20learning-based%20facial%20expression%20recognition%20systems.%20In%20addition%2C%20given%20the%20ever-growing%20quantities%20of%20video%20data%20that%20capture%20human%20facial%20expressions%2C%20such%20systems%20should%20utilize%20raw%20unlabeled%20videos%20without%20requiring%20expensive%20annotations.%20Therefore%2C%20in%20this%20work%2C%20we%20employ%20a%20multitask%20multi-modal%20self-supervised%20learning%20method%20for%20facial%20expression%20recognition%20from%20in-the-wild%20video%20data.%20Our%20model%20combines%20three%20self-supervised%20objective%20functions%3A%20First%2C%20a%20multi-modal%20contrastive%20loss%2C%20that%20pulls%20diverse%20data%20modalities%20of%20the%20same%20video%20together%20in%20the%20representation%20space.%20Second%2C%20a%20multi-modal%20clustering%20loss%20that%20preserves%20the%20semantic%20structure%20of%20input%20data%20in%20the%20representation%20space.%20Finally%2C%20a%20multi-modal%20data%20reconstruction%20loss.%20We%20conduct%20a%20comprehensive%20study%20on%20this%20multimodal%20multi-task%20self-supervised%20learning%20method%20on%20three%20facial%20expression%20recognition%20benchmarks.%20To%20that%20end%2C%20we%20examine%20the%20performance%20of%20learning%20through%20different%20combinations%20of%20self-supervised%20tasks%20on%20the%20facial%20expression%20recognition%20downstream%20task.%20Our%20model%20ConCluGen%20outperforms%20several%20multi-modal%20self-supervised%20and%20fully%20supervised%20baselines%20on%20the%20CMU-MOSEI%20dataset.%20Our%20results%20generally%20show%20that%20multi-modal%20self-supervision%20tasks%20offer%20large%20performance%20gains%20for%20challenging%20tasks%20such%20as%20facial%20expression%20recognition%2C%20while%20also%20reducing%20the%20amount%20of%20manual%20annotations%20required.%20We%20release%20our%20pre-trained%20models%20as%20well%20as%20source%20code%20publicly1.%22%2C%22proceedingsTitle%22%3A%222024%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%22%2C%22conferenceName%22%3A%222024%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%22%2C%22date%22%3A%222024-06%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FCVPRW63382.2024.00463%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10678641%22%2C%22ISSN%22%3A%222160-7516%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A01%3A10Z%22%7D%7D%2C%7B%22key%22%3A%2256Q9R9TQ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Boon%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBoon%2C%20M.%20N.%2C%20Andresen%2C%20N.%2C%20Traverso%2C%20S.%2C%20Meier%2C%20S.%2C%20Hellwich%2C%20O.%2C%20Lewejohann%2C%20L.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20Sprekeler%2C%20H.%2C%20%26amp%3B%20Hohlbaum%2C%20K.%20%282024%29.%20%26lt%3Bi%26gt%3BMouse%20lockbox%3A%20A%20sequential%20mechanical%20decision-making%20task%20to%20investigate%20complex%20mouse%20behavior%26lt%3B%5C%2Fi%26gt%3B%20%5BPoster%5D.%20International%20Congress%20for%20Neuroethology%20%28ICN%29.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Mouse%20lockbox%3A%20A%20sequential%20mechanical%20decision-making%20task%20to%20investigate%20complex%20mouse%20behavior%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Marcus%20N.%22%2C%22lastName%22%3A%22Boon%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Soledad%22%2C%22lastName%22%3A%22Traverso%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Sophia%22%2C%22lastName%22%3A%22Meier%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22Sprekeler%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222024%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T10%3A44%3A40Z%22%7D%7D%2C%7B%22key%22%3A%22IMCFIM9J%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hall%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHall%2C%20O.%2C%20Qu%2C%20R.%2C%20Ouerfelli-Ethier%2C%20J.%2C%20Roth%2C%20N.%2C%20Hellwich%2C%20O.%2C%20Obermayer%2C%20K.%2C%20%26amp%3B%20Rolfs%2C%20M.%20%282024%29.%20%26lt%3Bi%26gt%3BSaccadic%20decision-making%20in%20dynamic%20scenes%20under%20competing%20task%20demands%26lt%3B%5C%2Fi%26gt%3B%20%5BPoster%5D.%20European%20Group%20of%20Process%20Tracing%20Studies%20%28EGPROC%29.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Saccadic%20decision-making%20in%20dynamic%20scenes%20under%20competing%20task%20demands%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Ole%22%2C%22lastName%22%3A%22Hall%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Runfeng%22%2C%22lastName%22%3A%22Qu%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Julie%22%2C%22lastName%22%3A%22Ouerfelli-Ethier%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Nicolas%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Obermayer%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Rolfs%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222024%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T10%3A44%3A39Z%22%7D%7D%2C%7B%22key%22%3A%22W6Z5RK3X%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Roth%20et%20al.%22%2C%22parsedDate%22%3A%222023-10-26%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRoth%2C%20N.%2C%20Rolfs%2C%20M.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Obermayer%2C%20K.%20%282023%29.%20Objects%20guide%20human%20gaze%20behavior%20in%20dynamic%20real-world%20scenes.%20%26lt%3Bi%26gt%3BPLOS%20Computational%20Biology%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B19%26lt%3B%5C%2Fi%26gt%3B%2810%29%2C%20e1011512.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1371%5C%2Fjournal.pcbi.1011512%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1371%5C%2Fjournal.pcbi.1011512%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Objects%20guide%20human%20gaze%20behavior%20in%20dynamic%20real-world%20scenes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicolas%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Rolfs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Obermayer%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Tim%20Christian%22%2C%22lastName%22%3A%22Kietzmann%22%7D%5D%2C%22abstractNote%22%3A%22The%20complexity%20of%20natural%20scenes%20makes%20it%20challenging%20to%20experimentally%20study%20the%20mechanisms%20behind%20human%20gaze%20behavior%20when%20viewing%20dynamic%20environments.%20Historically%2C%20eye%20movements%20were%20believed%20to%20be%20driven%20primarily%20by%20space-based%20attention%20towards%20locations%20with%20salient%20features.%20Increasing%20evidence%20suggests%2C%20however%2C%20that%20visual%20attention%20does%20not%20select%20locations%20with%20high%20saliency%20but%20operates%20on%20attentional%20units%20given%20by%20the%20objects%20in%20the%20scene.%20We%20present%20a%20new%20computational%20framework%20to%20investigate%20the%20importance%20of%20objects%20for%20attentional%20guidance.%20This%20framework%20is%20designed%20to%20simulate%20realistic%20scanpaths%20for%20dynamic%20real-world%20scenes%2C%20including%20saccade%20timing%20and%20smooth%20pursuit%20behavior.%20Individual%20model%20components%20are%20based%20on%20psychophysically%20uncovered%20mechanisms%20of%20visual%20attention%20and%20saccadic%20decision-making.%20All%20mechanisms%20are%20implemented%20in%20a%20modular%20fashion%20with%20a%20small%20number%20of%20well-interpretable%20parameters.%20To%20systematically%20analyze%20the%20importance%20of%20objects%20in%20guiding%20gaze%20behavior%2C%20we%20implemented%20five%20different%20models%20within%20this%20framework%3A%20two%20purely%20spatial%20models%2C%20where%20one%20is%20based%20on%20low-level%20saliency%20and%20one%20on%20high-level%20saliency%2C%20two%20object-based%20models%2C%20with%20one%20incorporating%20low-level%20saliency%20for%20each%20object%20and%20the%20other%20one%20not%20using%20any%20saliency%20information%2C%20and%20a%20mixed%20model%20with%20object-based%20attention%20and%20selection%20but%20space-based%20inhibition%20of%20return.%20We%20optimized%20each%20model%5Cu2019s%20parameters%20to%20reproduce%20the%20saccade%20amplitude%20and%20fixation%20duration%20distributions%20of%20human%20scanpaths%20using%20evolutionary%20algorithms.%20We%20compared%20model%20performance%20with%20respect%20to%20spatial%20and%20temporal%20fixation%20behavior%2C%20including%20the%20proportion%20of%20fixations%20exploring%20the%20background%2C%20as%20well%20as%20detecting%2C%20inspecting%2C%20and%20returning%20to%20objects.%20A%20model%20with%20object-based%20attention%20and%20inhibition%2C%20which%20uses%20saliency%20information%20to%20prioritize%20between%20objects%20for%20saccadic%20selection%2C%20leads%20to%20scanpath%20statistics%20with%20the%20highest%20similarity%20to%20the%20human%20data.%20This%20demonstrates%20that%20scanpath%20models%20benefit%20from%20object-based%20attention%20and%20selection%2C%20suggesting%20that%20object-level%20attentional%20units%20play%20an%20important%20role%20in%20guiding%20attentional%20processing.%22%2C%22date%22%3A%222023-10-26%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1371%5C%2Fjournal.pcbi.1011512%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdx.plos.org%5C%2F10.1371%5C%2Fjournal.pcbi.1011512%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221553-7358%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A55%3A48Z%22%7D%7D%2C%7B%22key%22%3A%22L3JLBDS2%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Boon%20et%20al.%22%2C%22parsedDate%22%3A%222023-09%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBoon%2C%20M.%20N.%2C%20Andresen%2C%20N.%2C%20Meier%2C%20S.%2C%20Hellwich%2C%20O.%2C%20Lewejohann%2C%20L.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20Sprekeler%2C%20H.%2C%20%26amp%3B%20Hohlbaum%2C%20K.%20%282023%2C%20September%29.%20%26lt%3Bi%26gt%3BMouse%20lock%20box%3A%20a%20sequential%20mechanical%20decision-making%20task%20to%20investigate%20complex%20mouse%20behavior%26lt%3B%5C%2Fi%26gt%3B%20%5BPoster%5D.%20Bernstein%20Conference.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.12751%5C%2FNNCN.BC2023.056%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.12751%5C%2FNNCN.BC2023.056%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Mouse%20lock%20box%3A%20a%20sequential%20mechanical%20decision-making%20task%20to%20investigate%20complex%20mouse%20behavior%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Marcus%20N.%22%2C%22lastName%22%3A%22Boon%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Sophia%22%2C%22lastName%22%3A%22Meier%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22Sprekeler%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%2C%7B%22creatorType%22%3A%22contributor%22%2C%22firstName%22%3A%22German%20Neuroinformatics%22%2C%22lastName%22%3A%22Node%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222023-09%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%2210.12751%5C%2FNNCN.BC2023.056%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fabstracts.g-node.org%5C%2Fabstracts%5C%2Ff3b4d47f-e82b-46db-9df9-5872475f9c98%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-16T15%3A43%3A04Z%22%7D%7D%2C%7B%22key%22%3A%22Z5LU4L62%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Dolokov%20et%20al.%22%2C%22parsedDate%22%3A%222023%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BDolokov%2C%20A.%2C%20Andresen%2C%20N.%2C%20Hohlbaum%2C%20K.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20Lewejohann%2C%20L.%2C%20%26amp%3B%20Hellwich%2C%20O.%20%282023%29.%20Upper%20Bound%20Tracker%3A%20A%20Multi-Animal%20Tracking%20Solution%20for%20Closed%20Laboratory%20Settings%3A%20%26lt%3Bi%26gt%3BProceedings%20of%20the%2018th%20International%20Joint%20Conference%20on%20Computer%20Vision%2C%20Imaging%20and%20Computer%20Graphics%20Theory%20and%20Applications%26lt%3B%5C%2Fi%26gt%3B%2C%20945%26%23x2013%3B952.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.5220%5C%2F0011609500003417%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.5220%5C%2F0011609500003417%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Upper%20Bound%20Tracker%3A%20A%20Multi-Animal%20Tracking%20Solution%20for%20Closed%20Laboratory%20Settings%3A%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexander%22%2C%22lastName%22%3A%22Dolokov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%2018th%20International%20Joint%20Conference%20on%20Computer%20Vision%2C%20Imaging%20and%20Computer%20Graphics%20Theory%20and%20Applications%22%2C%22conferenceName%22%3A%2218th%20International%20Conference%20on%20Computer%20Vision%20Theory%20and%20Applications%22%2C%22date%22%3A%222023%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.5220%5C%2F0011609500003417%22%2C%22ISBN%22%3A%22978-989-758-634-7%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.scitepress.org%5C%2FDigitalLibrary%5C%2FLink.aspx%3Fdoi%3D10.5220%5C%2F0011609500003417%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A52%3A25Z%22%7D%7D%2C%7B%22key%22%3A%22MQW2YAL9%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Maier%20et%20al.%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BMaier%2C%20M.%2C%20Blume%2C%20F.%2C%20Bideau%2C%20P.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Abdel%20Rahman%2C%20R.%20%282022%29.%20Knowledge-augmented%20face%20perception%3A%20Prospects%20for%20the%20Bayesian%20brain-framework%20to%20align%20AI%20and%20human%20vision.%20%26lt%3Bi%26gt%3BConsciousness%20and%20Cognition%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B101%26lt%3B%5C%2Fi%26gt%3B%2C%20103301.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.concog.2022.103301%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.concog.2022.103301%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Knowledge-augmented%20face%20perception%3A%20Prospects%20for%20the%20Bayesian%20brain-framework%20to%20align%20AI%20and%20human%20vision%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Maier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Blume%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Bideau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rasha%22%2C%22lastName%22%3A%22Abdel%20Rahman%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%2205%5C%2F2022%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.concog.2022.103301%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Flinkinghub.elsevier.com%5C%2Fretrieve%5C%2Fpii%5C%2FS1053810022000332%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%2210538100%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A27Z%22%7D%7D%2C%7B%22key%22%3A%22DCZ2RZ22%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Halawa%20et%20al.%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHalawa%2C%20M.%2C%20Hellwich%2C%20O.%2C%20%26amp%3B%20Bideau%2C%20P.%20%282022%29.%20Action-Based%20Contrastive%20Learning%20for%20Trajectory%20Prediction.%20In%20S.%20Avidan%2C%20G.%20Brostow%2C%20M.%20Ciss%26%23xE9%3B%2C%20G.%20M.%20Farinella%2C%20%26amp%3B%20T.%20Hassner%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BComputer%20Vision%20%26%23x2013%3B%20ECCV%202022%26lt%3B%5C%2Fi%26gt%3B%20%28Vol.%2013699%2C%20pp.%20143%26%23x2013%3B159%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-19842-7_9%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-19842-7_9%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Action-Based%20Contrastive%20Learning%20for%20Trajectory%20Prediction%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marah%22%2C%22lastName%22%3A%22Halawa%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Bideau%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Shai%22%2C%22lastName%22%3A%22Avidan%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Gabriel%22%2C%22lastName%22%3A%22Brostow%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Moustapha%22%2C%22lastName%22%3A%22Ciss%5Cu00e9%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Giovanni%20Maria%22%2C%22lastName%22%3A%22Farinella%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Tal%22%2C%22lastName%22%3A%22Hassner%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%22Computer%20Vision%20%5Cu2013%20ECCV%202022%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222022%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-19842-7_9%22%2C%22ISBN%22%3A%22978-3-031-19841-0%20978-3-031-19842-7%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Flink.springer.com%5C%2F10.1007%5C%2F978-3-031-19842-7_9%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A50%3A40Z%22%7D%7D%2C%7B%22key%22%3A%22EYWZDLFS%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Roth%20et%20al.%22%2C%22parsedDate%22%3A%222021%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRoth%2C%20N.%2C%20Bideau%2C%20P.%2C%20Hellwich%2C%20O.%2C%20Rolfs%2C%20M.%2C%20%26amp%3B%20Obermayer%2C%20K.%20%282021%29.%20%26lt%3Bi%26gt%3BA%20modular%20framework%20for%20object-based%20saccadic%20decisions%20in%20dynamic%20scenes%26lt%3B%5C%2Fi%26gt%3B.%20EPIC%20workshop%20at%20CVPR.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FARXIV.2106.06073%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FARXIV.2106.06073%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22A%20modular%20framework%20for%20object-based%20saccadic%20decisions%20in%20dynamic%20scenes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicolas%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Bideau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Rolfs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Obermayer%22%7D%5D%2C%22abstractNote%22%3A%22Visually%20exploring%20the%20world%20around%20us%20is%20not%20a%20passive%20process.%20Instead%2C%20we%20actively%20explore%20the%20world%20and%20acquire%20visual%20information%20over%20time.%20Here%2C%20we%20present%20a%20new%20model%20for%20simulating%20human%20eye-movement%20behavior%20in%20dynamic%20real-world%20scenes.%20We%20model%20this%20active%20scene%20exploration%20as%20a%20sequential%20decision%20making%20process.%20We%20adapt%20the%20popular%20drift-diffusion%20model%20%28DDM%29%20for%20perceptual%20decision%20making%20and%20extend%20it%20towards%20multiple%20options%2C%20defined%20by%20objects%20present%20in%20the%20scene.%20For%20each%20possible%20choice%2C%20the%20model%20integrates%20evidence%20over%20time%20and%20a%20decision%20%28saccadic%20eye%20movement%29%20is%20triggered%20as%20soon%20as%20evidence%20crosses%20a%20decision%20threshold.%20Drawing%20this%20explicit%20connection%20between%20decision%20making%20and%20object-based%20scene%20perception%20is%20highly%20relevant%20in%20the%20context%20of%20active%20viewing%2C%20where%20decisions%20are%20made%20continuously%20while%20interacting%20with%20an%20external%20environment.%20We%20validate%20our%20model%20with%20a%20carefully%20designed%20ablation%20study%20and%20explore%20influences%20of%20our%20model%20parameters.%20A%20comparison%20on%20the%20VidCom%20dataset%20supports%20the%20plausibility%20of%20the%20proposed%20approach.%22%2C%22proceedingsTitle%22%3A%22%22%2C%22conferenceName%22%3A%22EPIC%20workshop%20at%20CVPR%22%2C%22date%22%3A%222021%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.48550%5C%2FARXIV.2106.06073%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2106.06073%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-05-26T14%3A46%3A01Z%22%7D%7D%2C%7B%22key%22%3A%22DZ8PQZ9M%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Roth%20et%20al.%22%2C%22parsedDate%22%3A%222021%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRoth%2C%20N.%2C%20Bideau%2C%20P.%2C%20Hellwich%2C%20O.%2C%20Rolfs%2C%20M.%2C%20%26amp%3B%20Obermayer%2C%20K.%20%282021%29.%20%26lt%3Bi%26gt%3BModeling%20the%20influence%20of%20objects%20on%20saccadic%20decisions%20in%20dynamic%20real-world%20scenes%26lt%3B%5C%2Fi%26gt%3B.%2043rd%20European%20Conference%20on%20Visual%20Perception%20%28ECVP%29.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Modeling%20the%20influence%20of%20objects%20on%20saccadic%20decisions%20in%20dynamic%20real-world%20scenes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Nicolas%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Bideau%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Rolfs%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Obermayer%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222021%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-05-26T15%3A11%3A12Z%22%7D%7D%2C%7B%22key%22%3A%22S34RQTVW%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Andresen%20et%20al.%22%2C%22parsedDate%22%3A%222020-04-15%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BAndresen%2C%20N.%2C%20W%26%23xF6%3Bllhaf%2C%20M.%2C%20Hohlbaum%2C%20K.%2C%20Lewejohann%2C%20L.%2C%20Hellwich%2C%20O.%2C%20Th%26%23xF6%3Bne-Reineke%2C%20C.%2C%20%26amp%3B%20Belik%2C%20V.%20%282020%29.%20Towards%20a%20fully%20automated%20surveillance%20of%20well-being%20status%20in%20laboratory%20mice%20using%20deep%20learning%3A%20Starting%20with%20facial%20expression%20analysis.%20%26lt%3Bi%26gt%3BPLOS%20ONE%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B15%26lt%3B%5C%2Fi%26gt%3B%284%29%2C%20e0228059.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1371%5C%2Fjournal.pone.0228059%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1371%5C%2Fjournal.pone.0228059%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Towards%20a%20fully%20automated%20surveillance%20of%20well-being%20status%20in%20laboratory%20mice%20using%20deep%20learning%3A%20Starting%20with%20facial%20expression%20analysis%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Niek%22%2C%22lastName%22%3A%22Andresen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Manuel%22%2C%22lastName%22%3A%22W%5Cu00f6llhaf%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22Hohlbaum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christa%22%2C%22lastName%22%3A%22Th%5Cu00f6ne-Reineke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vitaly%22%2C%22lastName%22%3A%22Belik%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Chang-Qing%22%2C%22lastName%22%3A%22Gao%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222020-4-15%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1371%5C%2Fjournal.pone.0228059%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdx.plos.org%5C%2F10.1371%5C%2Fjournal.pone.0228059%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221932-6203%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A47%3A07Z%22%7D%7D%2C%7B%22key%22%3A%224YNQ2UHV%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Halawa%20et%20al.%22%2C%22parsedDate%22%3A%222020%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHalawa%2C%20M.%2C%20W%26%23xF6%3Bllhaf%2C%20M.%2C%20Vellasques%2C%20E.%2C%20Sanz%2C%20U.%20S.%2C%20%26amp%3B%20Hellwich%2C%20O.%20%282020%29.%20%26lt%3Bi%26gt%3BLearning%20Disentangled%20Expression%20Representations%20from%20Facial%20Images%26lt%3B%5C%2Fi%26gt%3B.%20WiCV%20at%20ECCV2020.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2008.07001%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2008.07001%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Learning%20Disentangled%20Expression%20Representations%20from%20Facial%20Images%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Marah%22%2C%22lastName%22%3A%22Halawa%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Manuel%22%2C%22lastName%22%3A%22W%5Cu00f6llhaf%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Eduardo%22%2C%22lastName%22%3A%22Vellasques%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Urko%20S%5Cu00e1nchez%22%2C%22lastName%22%3A%22Sanz%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Olaf%22%2C%22lastName%22%3A%22Hellwich%22%7D%5D%2C%22abstractNote%22%3A%22Face%20images%20are%20subject%20to%20many%20different%20factors%20of%20variation%2C%20especially%20in%20unconstrained%20in-the-wild%20scenarios.%20For%20most%20tasks%20involving%20such%20images%2C%20e.g.%20expression%20recognition%20from%20video%20streams%2C%20having%20enough%20labeled%20data%20is%20prohibitively%20expensive.%20One%20common%20strategy%20to%20tackle%20such%20a%20problem%20is%20to%20learn%20disentangled%20representations%20for%20the%20different%20factors%20of%20variation%20of%20the%20observed%20data%20using%20adversarial%20learning.%20In%20this%20paper%2C%20we%20use%20a%20formulation%20of%20the%20adversarial%20loss%20to%20learn%20disentangled%20representations%20for%20face%20images.%20The%20used%20model%20facilitates%20learning%20on%20single-task%20datasets%20and%20improves%20the%20state-of-the-art%20in%20expression%20recognition%20with%20an%20accuracy%20of60.53%25on%20the%20AffectNetdataset%2C%20without%20using%20any%20additional%20data.%22%2C%22date%22%3A%222020%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2008.07001%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A50%3A31Z%22%7D%7D%5D%7D
Petković, U., Frenkel, J., Lazarides, R., & Hellwich, O. (2026). Modeling Student Engagement in the Wild: Analysis from Classroom Video. Proceedings of the 21st International Conference on Computer Vision Theory and Applications, 439–446. https://doi.org/10.5220/0014468800004084
Reiske, P., Boon, M. N., Andresen, N., Traverso, S., Daniels, M., Hohlbaum, K., Lewejohann, L., Thöne-Reineke, C., Hellwich, O., & Sprekeler, H. (2026). Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes. International Journal of Computer Vision, 134(7), 318. https://doi.org/10.1007/s11263-026-02908-x
Qu, R., Hall, O., Bideau, P. K., Ouerfelli-Ethier, J., Rolfs, M., Obermayer, K., & Hellwich, O. (2026). Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation. 2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 1032–1042. https://doi.org/10.1109/WACV61042.2026.00107
Andresen, N., Wöllhaf, M., Wilzopolski, J., Lang, A., Wolter, A., Howe-Wittek, L., Bekemeier, C., Pawlak, L.-I., Beyer, S., Cynis, H., Hietel, E., Rieckmann, V., Rieckmann, M., Thöne-Reineke, C., Lewejohann, L., Hellwich, O., & Hohlbaum, K. (2026). Automatic pain face analysis in mice: Applied to a varied dataset with non-standardized conditions. bioRxiv. https://doi.org/10.64898/2026.02.16.706098
Boon, M. N., Andresen, N., Traverso, S., Meier, S., Schuessler, F., Hellwich, O., Lewejohann, L., Thöne-Reineke, C., Hohlbaum, K., & Sprekeler, H. (2026). Mechanical problem solving in mice [Poster]. Computational and Systems Neuroscience (COSYNE) 2026.
Petković, U., Frenkel, J., Hellwich, O., & Lazarides, R. (2025). Modeling Teacher Nonverbal Immediacy: Refinement and Analysis. Adaptive Behavior, 33(5–6), 347–363. https://doi.org/10.1177/10597123251374920
Maier, M., Leonhardt, A., Blume, F., Bideau, P., Hellwich, O., & Abdel Rahman, R. (2025). Neural dynamics of mental state attribution to social robot faces. Social Cognitive and Affective Neuroscience, 20(1), nsaf027. https://doi.org/10.1093/scan/nsaf027
Blume, F., Qu, R., Bideau, P., Maier, M., Rahman, R. A., & Hellwich, O. (2025). How Do You Perceive My Face? Recognizing Facial Expressions in Multi-modal Context by Modeling Mental Representations. In D. Cremers, Z. Lähner, M. Moeller, M. Nießner, B. Ommer, & R. Triebel (Eds.), Pattern Recognition (pp. 20–36). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-85187-2_2
Lazarides, R., Frenkel, J., Daumiller, M., Dresel, M., Petković, U., Hellwich, O., & Göllner, R. (2025). Disentangling teacher and lesson variance and their relations to supportive learning environments: A machine learning assessment of teacher nonverbal behavior. Journal of Educational Psychology. https://doi.org/10.1037/edu0000999
Lazarides, R., Frenkel, J., Petković, U., Göllner, R., & Hellwich, O. (2025). ‘No words’—Machine-learning classified nonverbal immediacy and its role in connecting teacher self-efficacy with perceived teaching and student interest. British Journal of Educational Psychology, 95(S1), S15–S31. https://doi.org/10.1111/bjep.12732
Petković, U., Frenkel, J., Hellwich, O., & Lazarides, R. (2025). Nonverbal Immediacy Analysis in Education: A Multimodal Computational Model. In O. Brock & J. Krichmar (Eds.), From Animals to Animats 17 (pp. 326–338). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-71533-4_26
Hall, O., Qu, R., Ouerfelli-Ethier, J., Hellwich, O., Obermayer, K., & Rolfs, M. (2025). Modelling visual attention in dynamic scenes under partially competing task demands. [Poster]. Systems Vision Science Symposium.
Reiske, P., Boon, M. N., Andresen, N., Traverso, S., Hohlbaum, K., Lewejohann, L., Thöne-Reineke, C., Hellwich, O., & Sprekeler, H. (2025). Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes. CV4Animals Workshop at IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR).
Hohlbaum, K., Andresen, N., Mieske, P., Kahnau, P., Lang, B., Diederich, K., Palme, R., Mundhenk, L., Sprekeler, H., Hellwich, O., Thöne-Reineke, C., & Lewejohann, L. (2024). Lockbox enrichment facilitates manipulative and cognitive activities for mice. Open Research Europe, 4, 108. https://doi.org/10.12688/openreseurope.17624.2
Boon, M. N., Andresen, N., Traverso, S., Meier, S., Schuessler, F., Hellwich, O., Lewejohann, L., Thöne-Reineke, C., Sprekeler, H., & Hohlbaum, K. (2024). Mechanical problem solving in mice. bioRxiv. https://doi.org/10.1101/2024.07.29.605658
Halawa, M., Blume, F., Bideau, P., Maier, M., Rahman, R. A., & Hellwich, O. (2024). Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 4604–4614. https://doi.org/10.1109/CVPRW63382.2024.00463
Boon, M. N., Andresen, N., Traverso, S., Meier, S., Hellwich, O., Lewejohann, L., Thöne-Reineke, C., Sprekeler, H., & Hohlbaum, K. (2024). Mouse lockbox: A sequential mechanical decision-making task to investigate complex mouse behavior [Poster]. International Congress for Neuroethology (ICN).
Hall, O., Qu, R., Ouerfelli-Ethier, J., Roth, N., Hellwich, O., Obermayer, K., & Rolfs, M. (2024). Saccadic decision-making in dynamic scenes under competing task demands [Poster]. European Group of Process Tracing Studies (EGPROC).
Roth, N., Rolfs, M., Hellwich, O., & Obermayer, K. (2023). Objects guide human gaze behavior in dynamic real-world scenes. PLOS Computational Biology, 19(10), e1011512. https://doi.org/10.1371/journal.pcbi.1011512
Boon, M. N., Andresen, N., Meier, S., Hellwich, O., Lewejohann, L., Thöne-Reineke, C., Sprekeler, H., & Hohlbaum, K. (2023, September). Mouse lock box: a sequential mechanical decision-making task to investigate complex mouse behavior [Poster]. Bernstein Conference. https://doi.org/10.12751/NNCN.BC2023.056
Dolokov, A., Andresen, N., Hohlbaum, K., Thöne-Reineke, C., Lewejohann, L., & Hellwich, O. (2023). Upper Bound Tracker: A Multi-Animal Tracking Solution for Closed Laboratory Settings: Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 945–952. https://doi.org/10.5220/0011609500003417
Maier, M., Blume, F., Bideau, P., Hellwich, O., & Abdel Rahman, R. (2022). Knowledge-augmented face perception: Prospects for the Bayesian brain-framework to align AI and human vision. Consciousness and Cognition, 101, 103301. https://doi.org/10.1016/j.concog.2022.103301
Halawa, M., Hellwich, O., & Bideau, P. (2022). Action-Based Contrastive Learning for Trajectory Prediction. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Eds.), Computer Vision – ECCV 2022 (Vol. 13699, pp. 143–159). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-19842-7_9
Roth, N., Bideau, P., Hellwich, O., Rolfs, M., & Obermayer, K. (2021). A modular framework for object-based saccadic decisions in dynamic scenes. EPIC workshop at CVPR. https://doi.org/10.48550/ARXIV.2106.06073
Roth, N., Bideau, P., Hellwich, O., Rolfs, M., & Obermayer, K. (2021). Modeling the influence of objects on saccadic decisions in dynamic real-world scenes. 43rd European Conference on Visual Perception (ECVP).
Andresen, N., Wöllhaf, M., Hohlbaum, K., Lewejohann, L., Hellwich, O., Thöne-Reineke, C., & Belik, V. (2020). Towards a fully automated surveillance of well-being status in laboratory mice using deep learning: Starting with facial expression analysis. PLOS ONE, 15(4), e0228059. https://doi.org/10.1371/journal.pone.0228059
Halawa, M., Wöllhaf, M., Vellasques, E., Sanz, U. S., & Hellwich, O. (2020). Learning Disentangled Expression Representations from Facial Images. WiCV at ECCV2020. https://arxiv.org/abs/2008.07001
Best Poster Award (VISAPP 2023)
PI Lecture -
POSTPONED – Olaf Hellwich (Science of Intelligence)
SSBCracK Defence, Science & Technology News – August 2025 - New Dataset Captures Mice Solving Lockbox Puzzles in Complex Behavioral Study
Phys.org – August 2025 - Mice lockbox puzzle-solving captured in multi-camera video datasets
