Skip to yearly menu bar Skip to main content


MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Enxin Song · Wenhao Chai · Guanhong Wang · Haoyang Zhou · Feiyang Wu · Yucheng Zhang · Tian Ye · Haozhe Chi · Xun Guo · Yanting Zhang · Yan Lu · Jenq-Neng Hwang · Gaoang Wang

Arch 4A-E Poster #350
[ ]
Thu 20 Jun 5 p.m. PDT — 6:30 p.m. PDT


Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these challenges. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video and 14K manual annotations for validation of the effectiveness of our method.

Live content is unavailable. Log in and register to view live content