Skip to content

ZhouKanglei/Awesome-AQA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

148 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

Awesome Action Quality Assessment (AQA)

Recommended: Survey / Project entry points

  • ๐Ÿ” Project page (keyword-friendly search): https://zhoukanglei.github.io/AQA-Survey โ€” quickly search and filter all papers/notes.
  • ๐Ÿ“˜ Bibliography bundle: this repo ships the latest reference list; use the project page for fast discovery.

Notes / Contributions / Community (click to expand)
Item Details Link / Image
Contribute Open an issue or submit full Pull requests to add or correct papers/links. Issue tracker ยท Pull requests
WeChat group Join via QR; if the main one expires, use the personal link. Main QR ยท Personal QR
Updates Project page and issues carry the latest notes and announcements. Project page ยท Issue tracker

Survey list

Venue / Year Title Project / Code
A Comprehensive Survey of Action Quality Assessment: Method and Benchmark (Survey, Benchmark) ๐ŸŒ
A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions (Survey) ๐ŸŒ
Vision-Based Human Action Quality Assessment: A Systematic Review (Survey)
A Survey of Video-Based Action Quality Assessment (Survey)
A Survey of Vision-Based Human Action Evaluation Methods (Survey)

Reference list (sorted by year โ†’ venue โ†’ title)

Auto-compiled from the bundled bibliography. If you spot a mistake, please open an issue.

Venue / Year Title Project / Code New Dataset (modality)
MCMOE: Completing Missing Modalities with Mixture of Experts for Incomplete Multimodal Action Quality Assessment (Sports; Multi-Modal AQA, Incomplete Multi-Modal Learning)
UIL-AQA: Uncertainty-Aware Clip-Level Interpretable Action Quality Assessment (Sports; Interpretable Feedback, Uncertainty, Long-Term AQA, Transformer)
STAR Block: Adaptive spatio-temporal recalibration for action quality assessment (Sports)
SkillNet: Human Actions Assessment via Human-AI Collaboration (Skill Assessment; Human-AI Collaboration)
A Contrastive Video Language Multimodal Method for Teacher Action Quality Assessment (Skill Assessment; Multi-Modal AQA, Contrastive Learning, Teaching) TAQA
RGB
TaiChi-AQA: A Dataset and Framework for Action Quality Assessment and Visual Analysis (Sports) TaiChi-AQA
RGB
CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow (Sports; Causality, Long-Term AQA)
DanceFix: An Exploration in Group Dance Neatness Assessment through Fixing Abnormal Challenges of Human Pose (Skill Assessment; Dance, Multi-Modal AQA) DNV
RGB
Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric (Sports) Human-AGVQA
RGB
BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation (Skill Assessment; Basketball) BASKET
RGB
ExpertAF: Expert Actionable Feedback from Video (Sports; Interpretable Feedback, Multi-Modal AQA, Foundation Model) ๐ŸŒ
Language-Guided Audio-Visual Learning for Long-Term Sports Assessment (Sports; Multi-Modal AQA, Long-Term AQA)
Achieving Procedure-Aware Instructional Video Correlation Learning under Weak Supervision from A Collaborative Perspective (Sports; Contrastive AQA)
Learning Skill-Attributes for Transferable Assessment in Video (Skill Assessment; Multi-Modal AQA, Foundation Model) ๐ŸŒ
Action Quality Assessment Via Hierarchical Pose-Guided Multi-Stage Contrastive Regression (Sports; Contrastive AQA) FineDiving-Pose
RGB
PHI: Bridging Domain Shift in Long-Term Action Quality Assessment Via Progressive Hierarchical Instruction (Sports; Domain Shift, Long-Term AQA)
Human-Centric Fine-Grained Action Quality Assessment (Sports; Multi-Modal AQA, Contrastive AQA) AQA-7-HM
RGB
MTL-AQA-HM
Mask
A Teacher Action Quality Assessment Method Based on Label Constraint Strategy (Skill Assessment; Contrastive Learning, Teaching) TTAQA
RGB
Decoupling Representations with Quantized Vectors for Semi-Supervised Action Quality Assessment (Sports; Semi-Supervised AQA)
Adaptive Spatiotemporal Graph Transformer Network for Action Quality Assessment (Sports; GNN, Long-Term AQA)
Pose-Guided Transformer for Fine-Grained Action Quality Assessment (Sports; Pose, Fine-Grained AQA)
Rhythmer: Ranking-Based Skill Assessment with Rhythm-Aware Transformer (Skill Assessment; Ranking)
Visual-Semantic Alignment Temporal Parsing for Action Quality Assessment (Sports; Multi-Modal AQA)
Comprehensive Action Quality Assessment through Multi-Branch Modeling (Sports; Multi-Modal AQA)
Quality-Guided Vision-Language Learning for Long-Term Action Quality Assessment (Sports; Multi-Modal AQA, Long-Term AQA)
Scaled Background Swap: Video Augmentation for Action Quality Assessment with Background Debiasing (Sports; Data Augmentation, Debiasing)
Adaptive Frequency-Aware Network for Action Quality Assessment (Sports; Baduanjin) BDJ
RGB
Learning Referee Evaluation and Assessing Action Quality from Coarse to Fine in Diving Sport (Sports; Diving, Contrastive AQA)
Interpretable Two-Stage Action Quality Assessment Via 3D Human Pose Estimation and Dynamic Feature Alignment (Sports; Interpretable Feedback, Pose, TaiChi)
Scene-Aware Contrastive Regression for Multi-Person Action Quality Assessment (Sports; Contrastive AQA, Multi-Person AQA) MELO
RGB
FLEX: A Large-Scale Multi-Modal Multi-Action Dataset for Fitness Action Quality Assessment (Sports; Multi-Modal AQA, Weight Lifting) ๐ŸŒ FLEX
RGB
Continual Action Quality Assessment Via Adaptive Manifold-Aligned Graph Regularization (Sports; Continual AQA)
Fineskiing: A Fine-Grained Benchmark for Skiing Action Quality Assessment (Sports; Interpretable Feedback) FineSkiing
RGB
SkillSight: Efficient First-Person Skill Assessment with Gaze (Skill Assessment) ๐ŸŒ
Explainable Action Form Assessment by Exploiting Multimodal Chain-Of-Thoughts Reasoning (Sports; Interpretable Feedback, Foundation Model, Multi-Modal AQA) CoT-AFA
RGB
Attention-Driven Multimodal Alignment for Long-Term Action Quality Assessment (Sports; Multi-Modal AQA, Long-Term AQA)
Finecausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment (Sports; Interpretable Feedback, Causality, Contrastive AQA)
Vaqa-SS: Vision-Based Action Quality Assessment for Style-Based Skiing (Sports; Skiing) Skiing-6
RGB
Enhancing Long-Term Action Quality Assessment: A Dual-Modality Dataset and Causal Cross-Modal Framework for Trampoline Gymnastics (Sports; Multi-Modal AQA, Causality, Trampoline) ๐ŸŒ Trampoline-AQA
RGB
I3D-AE-LSTM: A 2-Stream Autoencoder for Action Quality Assessment Using A Newly Created Cricket Batsman Video Dataset (Sports; Cricket) UJ-AQA-CricketVision
RGB
Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis (Sports; Instructional Video, Weak Supervision)
Dancemvp: Self-Supervised Learning for Multi-Task Primitive-Based Dance Performance Assessment Via Transformer Text Prompting (Skill Assessment; Dance, Multi-Modal AQA)
2M-AF: A Strong Multi-Modality Framework for Human Action Quality Assessment with Self-Supervised Representation Learning (Sports; Multi-Modal AQA, Self-Supervised)
EgoExoLearn: A Dataset for Bridging Asynchronous Ego-And Exo-Centric View of Procedural Activities in Real World (Sports; Egocentric) EgoExoLearn
RGB
FineParser: A Fine-Grained Spatio-Temporal Action Parser for Human-Centric Action Quality Assessment (Sports; Contrastive AQA) FineDiving-HM
Narrative Action Evaluation with Prompt-Guided Multimodal Interaction (Sports; Multi-Modal AQA, Narrative Action Evaluation, Video Captioning, MTL-AQA (re-annotated), FineGym (re-annotated))
Cofinal: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment (Sports; Instruction-Tuning, Domain Shift, Long-Term AQA)
Procedure-Aware Action Quality Assessment: Datasets and Performance Evaluation (Sports) FineDiving+
RGB
GAIA: Rethinking Action Quality Assessment for AI-Generated Videos (Sports; AIGC AQA, Benchmark) GAIA
RGB
LucidAction: A Hierarchical and Multi-Model Dataset for Comprehensive Action Quality Assessment (Sports; Multi-Modal AQA, Multi-View, Curriculum Learning) LucidAction
RGB
Multimodal Action Quality Assessment (Sports; Multi-Modal AQA, Audio-Visual, Fusion)
Self-Supervised Sub-Action Parsing Network for Semi-Supervised Action Quality Assessment (Sports; Semi-Supervised AQA)
EGCN++: A New Fusion Strategy for Ensemble Learning in Skeleton-Based Rehabilitation Exercise Assessment (Healthcare; Rehabilitation, GCN)
EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding (Sports; Egocentric AQA) EgoExo-Fitness
RGB
MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment (Sports; Continual AQA, Benchmark)
RICA2: Rubric-Informed, Calibrated Assessment of Actions (Skill Assessment; Interpretable Feedback, Uncertainty) ๐ŸŒ
Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment (Skill Assessment; Semi-Supervised AQA)
Vision-Language Action Knowledge Learning for Semantic-Aware Action Quality Assessment (Sports; Multi-Modal AQA)
Multi-Stage Contrastive Regression for Action Quality Assessment (Sports; Contrastive AQA, Multi-Stage Modeling)
Which Is the Better Teacher Action? A New Ranking Model and Dataset (Skill Assessment; Ranking, Teaching)
Continual Action Assessment Via Task-Consistent Score-Discriminative Feature Distribution Modeling (Sports; Continual AQA)
Kinematic Diversity and Rhythmic Alignment in Choreographic Quality Transformers for Dance Quality Assessment (Skill Assessment; Dance, Multi-Modal AQA) OptiTrack
RGB
Adaptive Stage-Aware Assessment Skill Transfer for Skill Determination (Skill Assessment; Skill Transfer)
Interpretable Long-Term Action Quality Assessment (Sports; Interpretable Feedback, Long-Term AQA)
An Attention-Based Adaptive Spatial--Temporal Graph Convolutional Network for Long-Video Ergonomic Risk Assessment (Skill Assessment; Ergonomics, GCN)
TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching (Sports; Interpretable Feedback, Action Coaching, DescCoach) EE4D-DescCoach
RGB
FineRehab: A Multi-Modality and Multi-Task Dataset for Rehabilitation Analysis (Healthcare; Multi-Modal AQA) ๐ŸŒ FineRehab
RGB-D
Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment (Sports; Interpretable Feedback, Neuro-Symbolic, Diving, Temporal Segmentation, Action Recognition)
Two-Path Target-Aware Contrastive Regression for Action Quality Assessment (Sports; Contrastive AQA)
Auto-Encoding Score Distribution Regression for Action Quality Assessment (Sports; Uncertainty)
An Expert-Knowledge-Based Graph Convolutional Network for Skeleton-Based Physical Rehabilitation Exercises Assessment (Healthcare; Rehabilitation, GCN)
Automatic Assessment of Upper Extremity Function and Mobile Application for Self-Administered Stroke Rehabilitation (Healthcare; Rehabilitation, Multi-Modal AQA)
PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment (Skill Assessment; Continual AQA, Parameter-Efficient Fine-Tuning, Self-Supervised Pretraining, Domain Shift, Adapter) PD4T
RGB
Skating-Mixer: Long-Term Sport Audio-Visual Modeling with Mlps (Sports; Multi-Modal AQA, Figure Skating) FS1000
RGB
A Figure Skating Jumping Dataset for Replay-Guided Action Quality Assessment (Sports) RFSJ
RGB
Localization-Assisted Uncertainty Score Disentanglement Network for Action Quality Assessment (Sports; Multi-Modal AQA, Figure Skating) FineFS
RGB
LOGO: A Long-Form Video Dataset for Group Action Quality Assessment (Sports; Multi-Modal AQA, Long-Term AQA, Multi-Person AQA) LOGO
RGB
Automatic Modelling for Interactive Action Assessment (Healthcare)
Fine-Grained Spatio-Temporal Parsing Network for Action Quality Assessment (Sports; Fine-Grained AQA)
A Video-Based Augmented Reality System for Human-In-The-Loop Muscle Strength Assessment of Juvenile Dermatomyositis (Healthcare; Human-in-the-Loop) JDM
RGB
Attention-Guided Deep Learning Framework for Movement Quality Assessment (Healthcare; Rehabilitation, Attention)
Contrastive Self-Supervised Learning for Automated Multi-Modal Dance Performance Assessment (Skill Assessment; Multi-Modal AQA, Dance, Contrastive AQA)
Sedskill: Surgical Events Driven Method for Skill Assessment from Thoracoscopic Surgical Videos (Skill Assessment; Surgical AQA, Event-Driven) MVR
RGB
Hierarchical Graph Convolutional Networks for Action Quality Assessment (Sports; GCN Hierarchical Modeling)
Learning Semantics-Guided Representations for Scoring Figure Skating (Sports; Figure Skating, Multi-Modal AQA) OlympicFS
RGB
Portable Vision-Based Gait Assessment for Post-Stroke Rehabilitation Using an Attention-Based Lightweight CNN (Healthcare; Gait Assessment, Rehabilitation)
Improving Action Quality Assessment with Across-Staged Temporal Reasoning on Imbalanced Data (Sports; Diving, Temporal Reasoning)
Label-Reconstruction-Based Pseudo-Subscore Learning for Action Quality Assessment in Sporting Events (Sports; Pseudo-Subscore)
Multi-Skeleton Structures Graph Convolutional Network for Action Quality Assessment in Long Videos (Sports; Figure Skating, Skeleton AQA)
A Contrastive Learning Network for Performance Metric and Assessment of Physical Rehabilitation Exercises (Healthcare; Rehabilitation, Contrastive AQA)
A Skeleton-Based Rehabilitation Exercise Assessment System with Rotation Invariance (Healthcare; Rehabilitation, Rotation Invariance)
FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment (Sports) FineDiving
RGB
Likert Scoring with Grade Decoupling for Long-Term Action Assessment (Sports; Long-Term AQA)
EGCN: An Ensemble-Based Learning Framework for Exploring Effective Skeleton-Based Rehabilitation Exercise Assessment (Healthcare; Rehabilitation, Skeleton AQA, Ensemble)
Adaptive Action Assessment (Sports; Adaptive AQA, Graph-Based AQA)
Action Quality Assessment with Temporal Parsing Transformer (Sports; Transformer)
Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment (Sports; Self-Supervised AQA) Fitness-AQA
RGB
Pairwise Contrastive Learning Network for Action Quality Assessment (Sports; Contrastive AQA)
Surgical Skill Assessment Via Video Semantic Aggregation (Skill Assessment; Surgical AQA, Semantic Aggregation) ๐ŸŒ
Video-Based Surgical Skills Assessment Using Long Term Tool Tracking (Skill Assessment; Surgical AQA)
Semi-Supervised Action Quality Assessment with Self-Supervised Segment Feature Recovery (Sports; Semi-Supervised AQA)
Skeleton-Based Deep Pose Feature Learning for Action Quality Assessment on Figure Skating Videos (Sports; Figure Skating, Pose-Based AQA)
Skeleton-Based Action Quality Assessment Via Partially Connected LSTM with Triplet Losses (Sports; Tai Chi, Skeleton AQA)
Tai Chi Action Quality Assessment and Visual Analysis with A Consumer RGB-D Camera (Sports; Tai Chi) TaiChi-24
RGB-D
Graph Convolutional Networks for Assessment of Physical Rehabilitation Exercises (Healthcare; Rehabilitation, Skeleton AQA)
TSA-Net: Tube Self-Attention Network for Action Quality Assessment (Sports) FR-FS
RGB
Aifit: Automatic 3D Human-Interpretable Feedback Models for Fitness Training (Healthcare; Interpretable Feedback, Multi-Modal AQA) Fit3D
RGB
Towards Unified Surgical Skill Assessment (Skill Assessment) ๐ŸŒ
Group-Aware Contrastive Regression for Action Quality Assessment (Sports; Contrastive AQA)
Skeleton-Based Human Action Evaluation Using Graph Convolutional Network for Monitoring Alzheimerโ€™s Progression (Healthcare; Rehabilitation, Alzheimer's)
Action Quality Assessment Using Siamese Network-Based Deep Metric Learning (Sports; Siamese AQA, Metric Learning)
Action Quality Assessment with Ignoring Scene Context (Sports; Adversarial AQA, Scene-Invariant AQA)
Learning and Fusing Multiple Hidden Substages for Action Quality Assessment (Sports)
Piano Skills Assessment (Skill Assessment; Piano, Multi-Modal AQA) PISA
RGB
EAGLE-EYE: Extreme-Pose Action Grader Using Detail Bird's-Eye View (Sports; Figure Skating, Gymnastics, Multi-Stream AQA)
Hybrid Dynamic-Static Context-Aware Attention Network for Action Assessment in Long Videos (Sports; Long-Term AQA) Rhythmic Gymnastics
RGB
Uncertainty-Aware Score Distribution Learning for Action Quality Assessment (Sports; Uncertainty, Multi-Modal Score)
An Asymmetric Modeling for Action Assessment (Sports; Asymmetric Interaction) TASD-2
RGB
Towards Accurate and Interpretable Surgical Skill Assessment: A Video-Based Method Incorporating Recognized Surgical Gestures and Skill Levels (Skill Assessment; Interpretable Feedback, Surgical AQA)
Efficient and Robust Skeleton-Based Quality Assessment and Abnormality Detection in Human Action Performance (Healthcare; Abnormality Detection)
Assessing Action Quality Via Attentive Spatio-Temporal Convolutional Networks (Sports; Attention)
A Deep Learning Framework for Assessing Physical Rehabilitation Exercises (Healthcare; Rehabilitation)
The Pros and Cons: Rank-Aware Temporal Attention for Skill Determination in Long Videos (Skill Assessment; Ranking) ๐ŸŒ BEST
RGB
What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment (Sports; Multitask Learning, Diving) MTL-AQA
RGB
Action Assessment by Joint Relation Graphs (Sports; Pose, Graph)
Manipulation-Skill Assessment from Videos with Spatial Attention Network (Skill Assessment; Attention, Manipulation)
Surgical Skill Assessment on In-Vivo Clinical Data Via the Clearness of Operating Field (Healthcare; Surgical AQA)
Learning to Score Figure Skating Sport Videos (Sports; Figure Skating) Fis-V
RGB
Scoringnet: Learning Key Fragment for Action Quality Assessment with Ranking Loss in Skilled Sports (Skill Assessment; Key Fragments)
The Kimore Dataset: Kinematic Assessment of Movement and Clinical Scores for Remote Monitoring of Physical Rehabilitation (Healthcare) KIMORE
RGB-D
Action Quality Assessment across Multiple Actions (Sports; Multi-Action Dataset) ๐ŸŒ AQA-7
RGB
Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination (Skill Assessment; Ranking)
S3D: Stacking Segmental P3D for Action Quality Assessment (Sports; Diving)
Am I A Baller? Basketball Performance Assessment from First-Person Videos (Sports; Basketball, Egocentric AQA)
Learning to Score Olympic Events (Sports; Diving, Vault, Figure Skating)
Relative Hidden Markov Models for Video-Based Evaluation of Motion Skills in Surgical Training (Skill Assessment)
Assessing the Quality of Actions (Sports; Diving, Vault)
JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS): A Surgical Activity Dataset for Human Motion Modeling (Skill Assessment) ๐ŸŒ JIGSAWS
RGB

Total entries: 138

About

Awesome Action Quality Assessment (AQA)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •