AI Paper Atlas

Research map / Video / Action recognition

Group-Aware Contrastive Regression for Action Quality Assessment

Xumin Yu, Yongming Rao, Wenliang Zhao, Jiwen Lu, Jie Zhou

ICCV 2021 · Video › Action recognition · approach: Action anticipation and latent actions · 163 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
replace MLP regressor with group-aware regression tree (GART) (ablation)I3D + MLP · MTL-AQA (w/ DD)Spearman correlation: 0.9381 -> 0.9403Improved
replace MLP regressor with group-aware regression tree (GART) (ablation)I3D + MLP · MTL-AQA (w/ DD)R-l2 (x100): 0.394 -> 0.366Improved
add contrastive regression (CoRe) with exemplars on top of GART (ablation)I3D + GART · MTL-AQA (w/ DD)Spearman correlation: 0.9403 -> 0.9512Improved
add contrastive regression (CoRe) with exemplars on top of GART (ablation)I3D + GART · MTL-AQA (w/ DD)R-l2 (x100): 0.366 -> 0.260Improved
train and test with degree of difficulty (DD) labels for exemplar selectionCoRe + GART · MTL-AQASpearman correlation: 0.9341 -> 0.9512Improved
train and test with degree of difficulty (DD) labels for exemplar selectionCoRe + GART · MTL-AQAR-l2 (x100): 0.365 -> 0.260Improved
replace direct regression with CoRe + GARTI3D + MLP* · AQA-7 averageSpearman correlation: 0.7601 -> 0.8401Improved
replace direct regression with CoRe + GARTI3D + MLP* · AQA-7 averageR-l2 (x100): 3.20 -> 2.12Improved
replace direct regression with CoRe + GARTI3D + MLP* · JIGSAWS averageSpearman correlation: 0.65 -> 0.85Improved
replace direct regression with CoRe + GARTI3D + MLP* · JIGSAWS averageR-l2 (x100): 7.373 -> 4.556Improved
CoRe + GART versus USDL per classUSDL · AQA-7 Big SnowSpearman correlation: 0.7109 -> 0.6624Hurt
increase regression tree depth from small (below 4) or beyond 7 (ablation)CoRe + GART · AQA-7 DivingSpearman correlationHurt

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