AI Paper Atlas

Research map / Video / Action recognition

Recurring the Transformer for Video Action Recognition

Jiewen Yang, Xingbo Dong, Liujun Liu, Chao Zhang, Jiajun Shen, Dahai Yu

CVPR 2022 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 131 citations (OpenAlex)

This paper tried a common change: Add residual connections

Add a hidden-state residual connection · Jester-V1 · Accuracy (%): 88.7 -> 91.3 Improved

What 546 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

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
Use recurrent frame-by-frame processing with an attention gate that carries temporal features in a hidden stateRViT · Kinetics-400Top-1 accuracy (%): 81.3 -> 81.5Improved
Use recurrent frame-by-frame processing with an attention gate that carries temporal features in a hidden stateRViT · Something-Something-V2Top-1 accuracy (%): 67.7 -> 67.9Improved
Use recurrent frame-by-frame processing with an attention gate that carries temporal features in a hidden stateRViT · JesterTop-1 accuracy (%): 90.75 -> 92.31Improved
Use recurrent frame-by-frame processing with an attention gate that carries temporal features in a hidden stateRViT · CharadesmAP (%): 63.2 -> 66.1Improved
Add both spatial Ts and temporal Tt tokens for classification (ablation)RViT · Jester valAccuracy (%): 79.94 -> 92.31Improved
Add both spatial Ts and temporal Tt tokens for classification (ablation)RViT · Jester valAccuracy (%): 88.16 -> 92.31Improved
Use linear attention instead of softmax attention (ablation)RViT◦ with residual connection · Jester-V1Accuracy (%): 87.9 -> 91.3Improved
Add a hidden-state residual connection (ablation)RViT◦ with linear attention · Jester-V1Accuracy (%): 88.7 -> 91.3Improved

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