arXiv cs.AI· Hao Li, Jinye Zhang, Bobo Li, Mong-Li Lee, Wynne Hsu, Zheng Wang, Hao Fei, Min Zhang·· 9 天前AI 评分20
TRACE：面向认知的真实社交场景情绪因果链追踪框架与 TRACE-Bench 基准
Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes
AI 导读
研究者提出认知导向框架 TRACE，将情感事件形式化为 Condition、Affect、Effect 三个关联阶段，并构建 TRACE-Bench，用 646 个视频上的 3,746 条结构化问答覆盖情感识别、调节解码、原因推理、结果推理与全链重建五项任务。
正文 · 原文
Abstract:Affective computing has progressed from categorical emotion recognition to open-ended affective analysis with large multimodal models. Yet affective science describes emotion as an unfolding process shaped by appraisal, regulation, and social interpretation, which remains underexplored computationally. We propose TRACE, a cognition-oriented framework that formalizes an affective episode through three interrelated stages: Condition, Affect, and Effect, integrating observable cues with cognitive factors such as internal stance and regulation of emotional display. Based on this formulation, TRACE-Bench evaluates multimodal models in real-world social scenes through five tasks spanning grounded affect recognition, regulation decoding, cause reasoning, effect reasoning, and full-chain reconstruction, with 3,746 structured question-answer pairs over 646 videos. A matched human-model comparison reveals a substantial performance gap, while affect-specialized models also generally lag behind general-purpose MLLMs. Model outputs show recurring failures, including treating displayed behavior as genuine feeling and fabricating unsupported events during long-chain generation. We further propose TRACER, a cognition-grounded structured reasoning method that couples each inference with explicit premises from factual observations, cognitive appraisals, and established upstream conclusions, forming a traceable graph of intermediate and target conclusions. TRACER outperforms all evaluated model baselines on each of the five tasks. Project page: this https URL
| Comments: | Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Project page: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11410 [cs.AI] |
| (or arXiv:2610.11410v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11410 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Li Hao [view email]
[v1]
Thu, 8 Oct 2026 07:40:44 UTC (3,478 KB)
来源：arXiv cs.AI · arxiv.org