Papers › What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment

What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment

8 Apr 2019CVPR 2019 6arXiv:1904.04346archive 2025-07-28

Paritosh Parmar, Brendan Tran Morris

Can performance on the task of action quality assessment (AQA) be improved by exploiting a description of the action and its quality? Current AQA and skills assessment approaches propose to learn features that serve only one task - estimating the final score. In this paper, we propose to learn spatio-temporal features that explain three related tasks - fine-grained action recognition, commentary generation, and estimating the AQA score. A new multitask-AQA dataset, the largest to date, comprising of 1412 diving samples was collected to evaluate our approach (https://github.com/ParitoshParmar/MTL-AQA). We show that our MTL approach outperforms STL approach using two different kinds of architectures: C3D-AVG and MSCADC. The C3D-AVG-MTL approach achieves the new state-of-the-art performance with a rank correlation of 90.44%. Detailed experiments were performed to show that MTL offers better generalization than STL, and representations from action recognition models are not sufficient for the AQA task and instead should be learned.

PaperPDFConference PDFCode

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

Code

ParitoshParmar/MTL-AQA officialmentioned in papermentioned on GitHubpytorch report
InfoX-SEU/DAE-AQA mentioned on GitHubpytorch report
InfoX-SEU/DAE_AQA mentioned on GitHubpytorch report
luciferbobo/dae-aqa mentioned on GitHubpytorch report
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 ClassificationAction Quality AssessmentAction RecognitionFine-grained Action RecognitionMulti-Task LearningSkills AssessmentTemporal Action LocalizationVideo Captioning

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

MTL-AQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Quality Assessment MTL-AQA C3D-AVG-MTL Spearman Correlation 90.44 #17 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA C3D-AVG-STL Spearman Correlation 89.60 #18 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA MSCADC-MTL Spearman Correlation 86.12 #20 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA MSCADC-STL Spearman Correlation 84.72 #21 of 21 Archive leaderboard report
Action Recognition MTL-AQA C3D-AVG Armstand Accuracy 99.72 % #1 of 1 Archive leaderboard report
Action Recognition MTL-AQA C3D-AVG No. of Somersaults Accuracy 96.88 % #1 of 1 Archive leaderboard report
Action Recognition MTL-AQA C3D-AVG No. of Twists Accuracy 93.20 % #1 of 1 Archive leaderboard report
Action Recognition MTL-AQA C3D-AVG Position Accuracy 96.32 % #1 of 1 Archive leaderboard report
Action Recognition MTL-AQA C3D-AVG Rotation Type Accuracy 97.45 % #1 of 1 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