Papers › RICA2: Rubric-Informed, Calibrated Assessment of Actions

RICA2: Rubric-Informed, Calibrated Assessment of Actions

4 Aug 2024arXiv:2408.02138archive 2025-07-28

Abrar Majeedi, Viswanatha Reddy Gajjala, Satya Sai Srinath Namburi GNVV, Yin Li

The ability to quantify how well an action is carried out, also known as action quality assessment (AQA), has attracted recent interest in the vision community. Unfortunately, prior methods often ignore the score rubric used by human experts and fall short of quantifying the uncertainty of the model prediction. To bridge the gap, we present RICA^2 - a deep probabilistic model that integrates score rubric and accounts for prediction uncertainty for AQA. Central to our method lies in stochastic embeddings of action steps, defined on a graph structure that encodes the score rubric. The embeddings spread probabilistic density in the latent space and allow our method to represent model uncertainty. The graph encodes the scoring criteria, based on which the quality scores can be decoded. We demonstrate that our method establishes new state of the art on public benchmarks, including FineDiving, MTL-AQA, and JIGSAWS, with superior performance in score prediction and uncertainty calibration. Our code is available at https://abrarmajeedi.github.io/rica2_aqa/

PaperPDFCode

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

Code

abrarmajeedi/rica2_aqa officialmentioned 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 AssessmentPrediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Quality Assessment FineDiving RICA^2 (Deterministic) RL2(*100) 0.26 #3 of 4 Archive leaderboard report
Action Quality Assessment FineDiving RICA^2 (Deterministic) Spearman Correlation 0.9421 #3 of 4 Archive leaderboard report
Action Quality Assessment FineDiving RICA^2 RL2(*100) 0.2838 #4 of 4 Archive leaderboard report
Action Quality Assessment FineDiving RICA^2 Spearman Correlation 0.9402 #4 of 4 Archive leaderboard report
Action Quality Assessment JIGSAWS RICA^2 Spearman Correlation 0.92 #1 of 5 Archive leaderboard report
Action Quality Assessment JIGSAWS RICA^2 (Deterministic) Spearman Correlation 0.9 #2 of 5 Archive leaderboard report
Action Quality Assessment MTL-AQA RICA^2 (Deterministic) RL2(*100) 0.228 #1 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA RICA^2 (Deterministic) Spearman Correlation 96.20 #1 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA RICA^2 RL2(*100) 0.258 #3 of 21 Archive leaderboard report
Action Quality Assessment MTL-AQA RICA^2 Spearman Correlation 95.94 #3 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