Preprint
Sep 2026
MEMO: Multi-Level Entity-Aware Memory for Streaming Video Understanding
This work argues that streaming video memory should explicitly encode structured and semantically meaningful representations, particularly at the entity level, and proposes MEMO, a novel framework that models streaming video through multi-level, entity-aware structured memory.
Yin-Ying Li, Yu-Qian Fu, Yu-Lin Dai et al.
· 1 citation