Papers › Auto-Encoding Score Distribution Regression for Action Quality Assessment

Auto-Encoding Score Distribution Regression for Action Quality Assessment

22 Nov 2021arXiv:2111.11029archive 2025-07-28

Boyu Zhang, Jiayuan Chen, Yinfei Xu, HUI ZHANG, Xu Yang, Xin Geng

The action quality assessment (AQA) of videos is a challenging vision task since the relation between videos and action scores is difficult to model. Thus, AQA has been widely studied in the literature. Traditionally, AQA is treated as a regression problem to learn the underlying mappings between videos and action scores. But previous methods ignored data uncertainty in AQA dataset. To address aleatoric uncertainty, we further develop a plug-and-play module Distribution Auto-Encoder (DAE). Specifically, it encodes videos into distributions and uses the reparameterization trick in variational auto-encoders (VAE) to sample scores, which establishes a more accurate mapping between videos and scores. Meanwhile, a likelihood loss is used to learn the uncertainty parameters. We plug our DAE approach into MUSDL and CoRe. Experimental results on public datasets demonstrate that our method achieves state-of-the-art on AQA-7, MTL-AQA, and JIGSAWS datasets. Our code is available at https://github.com/InfoX-SEU/DAE-AQA.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

InfoX-SEU/DAE-AQA officialmentioned in papermentioned on GitHubpytorch report
InfoX-SEU/DAE_AQA mentioned on GitHubpytorch report
luciferbobo/dae-aqa mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action Quality Assessmentregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Quality Assessment AQA-7 DAE-CoRe Spearman Correlation 85.20% #1 of 9 Archive leaderboard report
Action Quality Assessment AQA-7 DAE-MLP Spearman Correlation 82.58% #3 of 9 Archive leaderboard report
Action Quality Assessment JIGSAWS DAE-CoRe Spearman Correlation 0.86 #3 of 5 Archive leaderboard report
Action Quality Assessment JIGSAWS DAE-MT Spearman Correlation 0.76 #4 of 5 Archive leaderboard report
Action Quality Assessment JIGSAWS DAE-MLP Spearman Correlation 0.72 #5 of 5 Archive leaderboard report
Action Quality Assessment MTL-AQA DAE-CoRe Spearman Correlation 95.89 #4 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA DAE-MT Spearman Correlation 94.52 #7 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA DAE-MLP Spearman Correlation 92.31 #13 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections