conftrace_

token mark

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

region-level understanding (1) video region comprehension (1) token-level attention (1) referring expression comprehension (1) multimodal large language model (1) video understanding (1) visual question answering (1)

Papers

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks CVPR 2025