[
    {
        "id": "osp-15109",
        "type": "article-journal",
        "title": "Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes",
        "author": [
            {
                "family": "Li",
                "given": "Hao"
            },
            {
                "family": "Zhang",
                "given": "Jinye"
            },
            {
                "family": "Li",
                "given": "Bobo"
            },
            {
                "family": "Lee",
                "given": "Mong-Li"
            },
            {
                "family": "Hsu",
                "given": "Wynne"
            },
            {
                "family": "Wang",
                "given": "Zheng"
            },
            {
                "family": "Fei",
                "given": "Hao"
            },
            {
                "family": "Zhang",
                "given": "Min"
            }
        ],
        "URL": "https://omanscience.com/en/articles/cognition-oriented-emotion-tracing-from-causes-to-consequences-in-real-world-social-scenes",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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: https://cogaffc.github.io/TRACE"
    }
]