Papers › Uncertainty-aware Score Distribution Learning for Action Quality Assessment

Uncertainty-aware Score Distribution Learning for Action Quality Assessment

13 Jun 2020CVPR 2020 6arXiv:2006.07665archive 2025-07-28

Yansong Tang, Zanlin Ni, Jiahuan Zhou, Danyang Zhang, Jiwen Lu, Ying Wu, Jie zhou

Assessing action quality from videos has attracted growing attention in recent years. Most existing approaches usually tackle this problem based on regression algorithms, which ignore the intrinsic ambiguity in the score labels caused by multiple judges or their subjective appraisals. To address this issue, we propose an uncertainty-aware score distribution learning (USDL) approach for action quality assessment (AQA). Specifically, we regard an action as an instance associated with a score distribution, which describes the probability of different evaluated scores. Moreover, under the circumstance where fine-grained score labels are available (e.g., difficulty degree of an action or multiple scores from different judges), we further devise a multi-path uncertainty-aware score distributions learning (MUSDL) method to explore the disentangled components of a score. We conduct experiments on three AQA datasets containing various Olympic actions and surgical activities, where our approaches set new state-of-the-arts under the Spearman's Rank Correlation.

PaperPDFConference PDFCode

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

Code

nzl-thu/musdl 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 Assessment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Quality Assessment AQA-7 USDL RL2(*100) 2.57 #4 of 9 Archive leaderboard report
Action Quality Assessment AQA-7 USDL Spearman Correlation 81.02% #4 of 9 Archive leaderboard report
Action Quality Assessment AQA-7 I3D+MLP Spearman Correlation 74.72% #6 of 9 Archive leaderboard report
Action Quality Assessment MTL-AQA MUSDL(w/ DD) RL2(*100) 0.451 #11 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA MUSDL(w/ DD) Spearman Correlation 92.73 #11 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA USDL(w/ DD) RL2(*100) 0.468 #12 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA USDL(w/ DD) Spearman Correlation 92.31 #12 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA MUSDL RL2(*100) 0.654 #15 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA MUSDL Spearman Correlation 91.58 #15 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA USDL RL2(*100) 0.609 #16 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA USDL Spearman Correlation 90.66 #16 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA I3D+MLP Spearman Correlation 89.21 #19 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