动态情感推理基准测试：一个以观众为中心的视频情感数据集

中文摘要 AI 辅助

视频情感分析通常被视为静态分类问题，将每个片段视为独立的标记单元。但这种方式忽略了一个关键心理事实：情感会因对连续因果事件的累积反应而变化。为弥补这一差距，我们引入了动态情感推理，这是首个针对以观众为中心的情感转变和连续视频事件因果推理的大规模基准测试。DAR包含15,087个视频和36,908个事件对齐的情感片段，标注了27种情感类别。与现有基于视频的情感数据集不同，DAR从以观众为中心的视角呈现了细粒度情感表达和转变，并提供了密集、基于时间且因果明确的推理链。基于DAR，我们正式定义了三项具有挑战性的任务：情感分割、细粒度情感分类和情感推理。作为这个基准测试的补充，我们提出了DAR - R1，这是一个将监督微调与组相对策略优化相结合的两阶段框架。在10多个MLLMs上的实验表明，DAR - R1在情感定位和情感推理方面都为动态情感推理设定了新的最先进水平。

英文摘要

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.

发表机构

• University of Science and Technology of China（中国科学技术大学）
• Hefei University of Technology（合肥工业大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

25 pages, 6 figures. Accepted to ECCV 2026