AI Paper Atlas

Research map / Video / Action recognition

Vision-Language Action Knowledge Learning for Semantic-Aware Action Quality Assessment

Huangbiao Xu, Xiao Ke, Yuezhou Li, Rui Xu, Huanqi Wu, Xiaofeng Lin, Wenzhong Guo

ECCV 2024 · Video › Action recognition · approach: Temporal action segmentation · 23 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
plug MVLA (textual semantics via CLIP) into TSATSA · FineDiving (w/ DN)AIoU@0.75: 34.31 -> 67.16Improved
plug MVLA into six existing AQA methodsUSDL, MUSDL, CoRe, TSA, TPT, HGCN · MTL-AQA (w/o DD)Spearman rho: 0.8861 -> 0.9142 (USDL); 0.9431 -> 0.9529 (TPT)Improved
plug MVLA into five methods on JIGSAWSUSDL, MUSDL, CoRe, TPT, HGCN · JIGSAWSAvg Spearman rho: 0.84 -> 0.87 (CoRe)Improved
plug MVLA into five methods on Fis-V (quality-grade text)MS-LSTM, GDLT, CoRe, TPT, MLP-Mixer · Fis-VAvg MSE: 14.01 -> 13.06 (MLP-Mixer)Improved
add frame-level, stage-level and video-level similarity together (ablation)MVLA VLKL · FineDiving (w/ DN)Spearman rho: 0.9340 -> 0.9419Improved
use only video-level similarity (ablation)MVLA VLKL · FineDiving (w/ DN)Spearman rho: 0.9340 -> 0.9243Hurt
add VLKL (text alignment) on top of CLIP-Image features (ablation)TSA · FineDiving (w/ DN)AIoU@0.5: 88.22 -> 92.52Improved
add SCA on top of CLIP-Image features (ablation)TSA · FineDiving (w/ DN)R-l2 (x100): 0.3248 -> 0.3178Improved
replace I3D-only features with added CLIP-Image visual features (ablation)TSA · FineDiving (w/ DN)Spearman rho: 0.9203 -> 0.9266Improved
add quality descriptions to multi-level texts (ablation)MVLA · FineDiving (w/ DN)Spearman rho: 0.9419 -> 0.9438No clear effect
freeze CLIP text encoder (ablation)MVLA · FineDiving (w/ DN)Spearman rho: 0.9419 -> 0.9390Hurt
use stronger backbone (VST or ViFi-CLIP) (ablation)MVLA · FineDiving (w/ DN)Spearman rho: 0.9419 -> 0.9457 (VST)Improved

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