mlsanityData to 14 Oct 2026

A Comprehensive Survey of Action Quality Assessment: Method and Benchmark

arXiv 2412.11149 ↗First posted 15 Dec 2024cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Action Quality Assessment (AQA) aims to automatically evaluate how well human actions are performed and has been widely applied in sports analysis, skill assessment, and healthcare. However, AQA studies are often developed under heterogeneous datasets and evaluation settings, making systematic comparison across methods difficult. To address these challenges, we present a comprehensive survey of recent advances in AQA. In particular, we propose a modality-driven hierarchical taxonomy that organizes existing methods into video-based, skeleton-based, and multi-modal approaches, and analyze the methodological evolution of representative models. We further establish a unified benchmark for representative video-based AQA methods by integrating diverse datasets and standardized evaluation protocols, enabling consistent comparison in terms of both accuracy and computational efficiency. Finally, we analyze emerging research trends, identify key challenges in current AQA research, and outline future directions ranging from near-term methodological advances to longer-term opportunities enabled by emerging AI paradigms. The project web page can be found at https://ZhouKanglei.github.io/AQA-Survey.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 59 of its 159 references that are in the map. First posted on arXiv 15 Dec 2024.

Builds on

59 of 159 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  3. 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 1,471
  4. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  5. 2021Video Swin Transformercited by 1,091
  6. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  7. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  8. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 528
  9. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  10. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  11. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  12. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 387
38 more
  1. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
  2. 2016Convolutional Pose Machinescited by 325
  3. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
  4. 2019Learnable Triangulation of Human Posecited by 161
  5. 2022FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessmentcited by 107
  6. 2019What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessmentcited by 100
  7. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 95
  8. 2016Learning To Score Olympic Eventscited by 88
  9. 2020Uncertainty-aware Score Distribution Learning for Action Quality Assessmentcited by 80
  10. 2018Action Quality Assessment Across Multiple Actionscited by 79
  11. 2021Group-aware Contrastive Regression for Action Quality Assessmentcited by 75
  12. 2018Learning to score the figure skating sports videoscited by 73
  13. 2018The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videoscited by 69
  14. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 64
  15. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 60
  16. 2021Towards Unified Surgical Skill Assessmentcited by 49
  17. 2016Am I a Baller? Basketball Performance Assessment from First-Person Videoscited by 40
  18. 2022TSA-Net: Tube Self-Attention Network for Action Quality Assessmentcited by 36
  19. 2024EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understandingcited by 36
  20. 2022Action Quality Assessment with Temporal Parsing Transformercited by 31
  21. 2024LOGO: A Long-Form Video Dataset for Group Action Quality Assessmentcited by 31
  22. 2024GAIA: Rethinking Action Quality Assessment for AI-Generated Videoscited by 30
  23. 2019Manipulation-skill Assessment from Videos with Spatial Attention Networkcited by 29
  24. 2019A Deep Learning Framework for Assessing Physical Rehabilitation Exercisescited by 26
  25. 2024FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessmentcited by 25
  26. 2024VideoMamba: Spatio-Temporal Selective State Space Modelcited by 25
  27. 2022Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPscited by 20
  28. 2024Multimodal Action Quality Assessmentcited by 20
  29. 2023PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessmentcited by 19
  30. 2024Narrative Action Evaluation with Prompt-Guided Multimodal Interactioncited by 19
  31. 2021Auto-Encoding Score Distribution Regression for Action Quality Assessmentcited by 18
  32. 2024CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignmentcited by 17
  33. 2024ExpertAF: Expert Actionable Feedback from Videocited by 17
  34. 2021Piano Skills Assessmentcited by 16
  35. 2022A Survey of Video-based Action Quality Assessmentcited by 14
  36. 2024Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessmentcited by 14
  37. 2022Surgical Skill Assessment via Video Semantic Aggregationcited by 13
  38. 2024MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessmentcited by 13

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 11.

20 papers.

Sort:

By area:

  1. 2025Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regressioncited by 21
  2. 2025A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directionscited by 7
  3. 2025SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimationcited by 6
  4. 2025PATS: Proficiency-Aware Temporal Sampling for Multi-View Sports Skill Assessmentcited by 5
  5. 2025FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessmentcited by 4
  6. 2025ProfVLM: A lightweight video-language model for multi-view proficiency estimationcited by 4
  7. 2026FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learningcited by 2
  8. 2025HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysiscited by 1
  9. 2025A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessmentcited by 0
  10. 2025CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flowcited by 0
  11. 2026Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedbackcited by 0
  12. 2026SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimationcited by 0
8 more
  1. 2026Cross-view Multimodal Vision-Based Assessment Framework for Traditional Chinese Medicine Rehabilitation Trainingcited by 0
  2. 2026SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videoscited by 0
  3. 2026Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessmentcited by 0
  4. 2026A Survey of Large Models in Sportscited by 0
  5. 2026NeuroPath: Brain-Inspired Dual-Pathway Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 0
  6. 2026UniH3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restorationcited by 0
  7. 2026CE4L: Continual Ego, Exo, and Ego-Exo Learningcited by 0
  8. 2026Impact of Patient Orientation in Single- and Multi-View Camera Environments for AI-based Rehabilitation Monitoringcited by 0