SafeGesture: Evaluating Fine-Grained Hand Gesture Understanding in Vision-Language Models through Scenario-Conditioned Safety Interpretation
SafeGesture:通过场景条件安全解释评估视觉语言模型的细粒度手势理解能力
机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) ; Urban Information Lab, The University of Texas at Austin(德克萨斯大学奥斯汀分校城市信息实验室)
专题命中 评测与基准 :language model(title,abstract)
AI总结 本文提出SafeGesture基准,评估5款视觉语言模型的细粒度手势安全理解能力,发现模型存在感知与推理脱节,瓶颈为场景条件安全推理而非手势识别。
Comments 14 pages, 22 tables, 2 figures. Code and benchmark resources available at https://github.com/The-Responsible-AI-Initiative/SafeGesture