Papers
arxiv:2402.05861

Memory Consolidation Enables Long-Context Video Understanding

Published on Feb 8
· Submitted by akhaliq on Feb 9
Authors:
,
,
,
,

Abstract

Most transformer-based video encoders are limited to short temporal contexts due to their quadratic complexity. While various attempts have been made to extend this context, this has often come at the cost of both conceptual and computational complexity. We propose to instead re-purpose existing pre-trained video transformers by simply fine-tuning them to attend to memories derived non-parametrically from past activations. By leveraging redundancy reduction, our memory-consolidated vision transformer (MC-ViT) effortlessly extends its context far into the past and exhibits excellent scaling behavior when learning from longer videos. In doing so, MC-ViT sets a new state-of-the-art in long-context video understanding on EgoSchema, Perception Test, and Diving48, outperforming methods that benefit from orders of magnitude more parameters.

Community

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2402.05861 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2402.05861 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2402.05861 in a Space README.md to link it from this page.

Collections including this paper 2