发表机构
National University of Singapore; School of Computing, National University of Singapore; University of Oxford; Institute of Computing and Intelligence, Harbin Institute of Technology (Shenzhen)（新加坡国立大学; 新加坡国立大学计算机学院; 牛津大学; 哈尔滨工业大学（深圳）计算与智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对情感计算中认知导向情感追踪的研究空白，提出TRACE框架与TRACE-Bench基准，进而开发TRACER推理方法，在五项情感相关任务上实现优于基线模型的性能。
AI 中文摘要
情感计算已从分类情感识别发展到基于大型多模态模型的开放式情感分析，但情感科学将情感描述为一种由评估、调节和社会解释塑造的展开过程，这一过程在计算层面仍未得到充分探索。我们提出TRACE，一个面向认知的框架，它通过三个相互关联的阶段（条件、情感、结果）来形式化情感事件，将可观察线索与内部立场、情感表达调节等认知因素相结合。基于该形式化方法，TRACE-Bench在真实社会场景中通过五个任务评估多模态模型，涵盖基础情感识别、调节解码、原因推理、结果推理和全链重建，共包含646个视频对应的3746个结构化问答对。匹配的人机对比显示存在显著性能差距，且情感专用模型通常落后于通用多模态大语言模型（MLLMs）。模型输出存在反复出现的失败情况，包括将展示的行为视为真实情感，以及在长链生成过程中编造无依据的事件。我们进一步提出TRACER，一种基于认知的结构化推理方法，它将每个推理与来自事实观察、认知评估和已确立的上游结论的显式前提相结合，形成可追踪的中间结论和目标结论图。TRACER在全部五个任务上的表现均优于所有评估的模型基线。项目页面：this https URL
英文摘要
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: https://cogaffc.github.io/TRACE
CommentsSubmitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Project page: https://cogaffc.github.io/TRACE
