Can Vision-Language Models Analyze Human-Centered Video? Mapping Model Capabilities and Human-AI Collaborative Workflows
This work systematically analyzes all 1,702 CHI 2026 full papers and identifies 125 that annotate videos, and derives a five-dimensional taxonomy spanning analytic purpose, viewpoint, phenomenon, reasoning requirement, and annotation authority to map the capabilities and limitations of a general-purpose VLM.
Xi-Yuan Shen, Jiuyang Lyu, Seokhyun Hwang et al.
· 0 citations