CogEmo:多模态情绪认知评估推理框架
Get the story
2026年10月9日,arXiv Human-Computer Interaction 频道发布论文《从表层到深度:多模态情绪理解中的认知评价推理》,提出从感知到认知评价的多模态情绪理解范式,旨在超越可观察情感线索的表层关联并缓解 Clever Hans 效应。研究团队配套发布三项成果:指令微调数据集 CogEmo-40K、紧凑稀疏多模态大模型 CogEmo-MoE,以及评测基准 CogEmo-Bench。该基准引入 Appraisal Evidence Quality Score(AEQS),覆盖六个评价维度,用于评估认知评价推理质量。目前未见后续验证或第三方复现报道。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
- arXiv · Human-Computer Interaction从表层到深度:多模态情绪理解中的认知评价推理
论文提出从感知到认知评价的多模态情绪理解范式,以超越可观察情感线索的表层关联并缓解 Clever Hans 效应。配套发布 CogEmo-40K 指令微调数据集、紧凑稀疏 MLLM CogEmo-MoE 与评测基准 CogEmo-Bench,后者引入 Appraisal Evidence Quality Score(AEQS)覆盖六个评价维度。
Heat trend
Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.