AI Paper Atlas

Research map / Video / Action recognition

TransRAC: Encoding Multi-Scale Temporal Correlation With Transformers for Repetitive Action Counting

Huazhang Hu, Sixun Dong, Yiqun Zhao, Dongze Lian, Zhengxin Li, Shenghua Gao

CVPR 2022 · Video › Action recognition · approach: Fully supervised temporal action detection · 67 citations (OpenAlex)

Check 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
Use TransRAC with multi-scale temporal correlation and density-map regressionRepetitive action counting · RepCount part-A testMAE: 0.5267 -> 0.4431Improved
Use TransRAC rather than RepNetRepetitive action counting · RepCount part-BOBO: 0.0025 -> 0.091Improved
Use TransRAC rather than RepNetRepetitive action counting · UCFRepMAE: 0.9985 -> 0.6401Improved
Replace self-attention correlation with TSM squared Euclidean distance (ablation)TransRAC · RepCount part-A testMAE: 0.4431 -> 0.5678Hurt
Replace the classifier with a density-map regressor (ablation)ResNet counting model · RepCount part-A testMAE: 0.9950 -> 0.6905Improved
Replace the classifier with a density-map regressor (ablation)SwinT counting model · RepCount part-A testOBO: 0.118 -> 0.138Improved
Use only one temporal scale instead of fusing three scales (ablation)TransRAC · RepCount part-A testMAE: 0.4431 -> 0.5434 (Scale-4), 0.6595 (Scale-1), 0.6657 (Scale-8)Hurt
Increase the single-scale video sample count from 64 to 128 frames (ablation)TransRAC single-scale model · RepCount part-A testMAE: 0.6595 -> 0.6191Improved
Generate density-map targets with the Gaussian mean at the beginning rather than the middle of a cycle (ablation)TransRAC density-map predictor · RepCount part-A testMAE: 0.4936 -> 0.5295Hurt
Merge density maps centered at beginning, middle, and end rather than use the middle-centered map (ablation)TransRAC density-map predictor · RepCount part-A testMAE: 0.4936 -> 0.5142Hurt
Use the 8-frame scale rather than single-frame scale with 128 sampled frames (ablation)TransRAC single-scale model · RepCount part-A testMAE: 0.6191 -> 0.4926Improved

Later papers that compared with this method

4 later accepted papers report TransRAC as a baseline in their results tables; 4 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