Benchmarking Visual State Tracking in Multimodal Video Understanding 事件

Benchmarking Visual State Tracking in Multimodal Video Understanding arXiv:2606.03920v1 Announce Type: new Abstract: Understanding a video requires more than recognizing isolated moments, as humans continuously track entities, states, and events over time. This capacity for visual state tracking is fundamental to video understanding, yet remains underexplored in current evaluations of Multimodal Large Language Models (MLLMs). We introduce Visual STAte Tracking benchmark (VSTAT), a video-based b