AI Paper Atlas

Research map / Video / Video-language understanding

VideoMamba: State Space Model for Efficient Video Understanding

Kunchang Li, Xinhao Li, Yi Wang, Yinan He, Yali Wang, Limin Wang, Yu Qiao

ECCV 2024 · Video › Video-language understanding · approach: Long video understanding · 511 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add self-distillation from a pretrained smaller VideoMamba teacher when training the larger model (ablation)VideoMamba-B/M · ImageNet-1Ktop-1 accuracyImproved
add early stopping of self-distillation teacher guidance (ablation)VideoMamba · ImageNet-1Ktop-1 accuracyNo clear effect
increase input resolution for ImageNet (224 to 576)VideoMamba-M · ImageNet-1Ktop-1 accuracy: 82.8 -> 84.0Improved
use attention masking instead of tube masking in masked pretraining (ablation)VideoMamba-M · SthSth V2top-1 accuracy: 66.3 -> 68.5Improved
align only the last layer instead of the last 6x2 layers (ablation)VideoMamba-M masked pretraining · SthSth V2top-1 accuracy: 67.7 -> 68.5Improved
use 80% mask ratio instead of 50% or 90% (ablation)VideoMamba-M masked pretraining · SthSth V2top-1 accuracy: 68.1 -> 68.5 (vs 50%)Improved
increase droppath from 0.1 to 0.4 in masked pretraining (ablation)VideoMamba-M · SthSth V2top-1 accuracy: 68.0 -> 68.5Improved
use spatial-first scan instead of temporal-first scan (ablation)VideoMamba-Ti · video classificationtop-1 accuracyImproved
increase input resolution for video tasks (ablation)VideoMamba-Ti · K400 and SthSth V2top-1 accuracyMixed
increase number of input frames (ablation)VideoMamba-Ti · K400 vs SthSth V2top-1 accuracyMixed
increase frames from 32 to 64 for VideoMamba-M (masked pretraining) on Breakfast (ablation)VideoMamba-M · Breakfasttop-1 accuracy: 97.9 -> 96.9Hurt

Later papers that compared with this method

7 later accepted papers report VideoMamba as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy