Video-DCI2 min read
Video-DCI: How Far Are VLM Agents from Human Viewers in Direct Video Corpus Interaction?
Humans answer complex visual questions by inspecting short moments, updating what they know, and redirecting attention toward missing evidence. Existing video benchmarks, however, often provide the relevant video, evaluate only final answers or isolated localization, or permit textual shortcuts,…
By Garry Yang, Yuqiao Liu, Hao Lin, Luohao Pan, Xinru Chen, Wanqi Ren, Zhikang Xu, Yizhan Huang, Huaixiao Tou, James ChengarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 10, 2026.
Comments
Sign in to join the discussion.