{"ID":6536402,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T08:33:44.272455028Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10238","arxiv_id":"2607.10238","title":"Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset","abstract":"Video emotion analysis is typically framed as a static classification problem, treating each clip as an independent labeled unit. However, such a formulation overlooks a key psychological fact: emotions change as a result of cumulative reactions to consecutive causal events. To bridge this gap, we introduce Dynamic Affective Reasoning, the first large-scale benchmark for viewer-centric affect transitions and causal reasoning over consecutive video events. DAR contains 15,087 videos and 36,908 event-aligned affective segments annotated with 27 emotion categories. Unlike existing video-based emotion datasets, DAR presents a new viewer-centric perspective on fine-grained emotional expressions and transitions, and provides dense, temporally grounded, and causally explicit reasoning chains. Based on DAR, we formally define three challenging tasks: affective segmentation, fine-grained emotion classification, and affective reasoning. Complementing this benchmark, we propose DAR-R1, a two-stage framework that combines supervised fine-tuning with Group Relative Policy Optimization. Experiments across 10+ MLLMs show that DAR-R1 sets a new state-of-the-art for dynamic affective reasoning, in terms of both emotional localization and affective reasoning. Project page: https://github.com/Zhang-Zhiyan/DAR.","short_abstract":"Video emotion analysis is typically framed as a static classification problem, treating each clip as an independent labeled unit. However, such a formulation overlooks a key psychological fact: emotions change as a result of cumulative reactions to consecutive causal events. To bridge this gap, we introduce Dynamic Aff...","url_abs":"https://arxiv.org/abs/2607.10238","url_pdf":"https://arxiv.org/pdf/2607.10238v1","authors":"[\"Zhiyan Zhang\",\"Peipei Song\",\"Jinpeng Hu\",\"Jingyang Jia\",\"Xun Yang\",\"Xiaojun Chang\"]","published":"2026-07-11T09:58:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":614164,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T01:21:01.169441415Z","DeletedAt":null,"paper_id":6536402,"paper_url":"https://arxiv.org/abs/2607.10238","paper_title":"Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset","repo_url":"https://github.com/Zhang-Zhiyan/DAR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}