Preprint
Sep 2026
CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying
CAM stores the entities and relations extracted from video clips in a knowledge graph that captures the high-level semantics of each entity or relation and summarizes the local subgraph of the target entity or relation once the subgraph reaches a predefined size.
Yi-Zhou Tian, Zi-Zhe Chen, Shi-Yuan Deng et al.
· 0 citations