GRASP：学习多个人非语言互动中的社会推理
GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions
AI总结：
GRASP通过连接高层社会问答与细粒度目光和指代手势事件，提升多个人非语言互动的社会推理能力，包含290万对问题-答案对，提出Social Grounding Reward提升模型性能。
摘要：
理解社会互动需要推理微妙的非语言线索，但当前多模态大语言模型（MLLMs）在多个人视频中常无法识别谁与谁互动。我们引入GRASP，一个大规模社会推理数据集，将高层社会问答与细粒度目光和指代手势事件连接起来。GRASP包含290K个问题-答案对，覆盖46K小时视频，按16类分类涵盖目光、手势及联合目光-手势推理，同时包含GRASP-Bench用于评估。不同于以往仅关注孤立线索或高层社会问答的资源，GRASP通过身份一致的目光轨迹、指代手势及其联合组成构建社会事件。此外，我们提出Social Grounding Reward（SGR），一种利用这些社会事件鼓励模型推理每个互动参与者的学习信号。实验显示，SGR在GRASP-Bench上提升性能，同时在相关社会视频问答基准上保持零样本性能。
英文摘要：
Understanding social interactions requires reasoning over subtle non-verbal cues, yet current multimodal large language models (MLLMs) often fail to identify who interacts with whom in multi-person videos. We introduce GRASP, a large-scale social reasoning dataset that connects high-level social QA with fine-grained gaze and deictic gesture events. GRASP contains 290K question--answer pairs over 46K videos totaling 749 hours, organized by a 16-category taxonomy spanning gaze, gesture, and joint gaze--gesture reasoning, together with GRASP-Bench for evaluation. Unlike prior resources that focus on either isolated cues or high-level social QA, GRASP builds questions from identity-consistent gaze trajectories, deictic gestures, and their joint compositions into social events. Moreover, we propose Social Grounding Reward (SGR), a learning signal that uses these social events to encourage models to reason about the participants involved in each interaction. Experiments show that SGR improves performance on GRASP-Bench while maintaining zero-shot performance on related social video QA benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
