{"total":79,"rows":[{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107,"area":null},{"id":"2108.07797","title":"Group-aware Contrastive Regression for Action Quality Assessment","created":"2021-08-17","cited_by_count":75,"area":null},{"id":"2408.02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","created":"2024-08-05","cited_by_count":67,"area":"mllm"},{"id":"2106.01035","title":"Towards Unified Surgical Skill Assessment","created":"2021-06-02","cited_by_count":49,"area":null},{"id":"2401.01505","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","created":"2024-01-03","cited_by_count":41,"area":null},{"id":"2104.11452","title":"SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos","created":"2021-04-23","cited_by_count":40,"area":null},{"id":"2201.03746","title":"TSA-Net: Tube Self-Attention Network for Action Quality Assessment","created":"2022-01-11","cited_by_count":36,"area":null},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36,"area":null},{"id":"2207.09270","title":"Action Quality Assessment with Temporal Parsing Transformer","created":"2022-07-19","cited_by_count":31,"area":null},{"id":"2404.05029","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","created":"2024-04-07","cited_by_count":31,"area":null},{"id":"2406.06087","title":"GAIA: Rethinking Action Quality Assessment for AI-Generated Videos","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2202.14019","title":"Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment","created":"2022-02-28","cited_by_count":25,"area":null},{"id":"2405.06887","title":"FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment","created":"2024-05-11","cited_by_count":25,"area":null},{"id":"2501.03674","title":"Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression","created":"2025-01-07","cited_by_count":21,"area":null},{"id":"2203.03990","title":"Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs","created":"2022-03-08","cited_by_count":20,"area":null},{"id":"2412.11149","title":"A Comprehensive Survey of Action Quality Assessment: Method and Benchmark","created":"2024-12-15","cited_by_count":20,"area":null},{"id":"2311.07603","title":"PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment","created":"2023-11-11","cited_by_count":19,"area":null},{"id":"2404.14471","title":"Narrative Action Evaluation with Prompt-Guided Multimodal Interaction","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2111.11029","title":"Auto-Encoding Score Distribution Regression for Action Quality Assessment","created":"2021-11-22","cited_by_count":18,"area":null},{"id":"2101.04884","title":"Piano Skills Assessment","created":"2021-01-13","cited_by_count":16,"area":null},{"id":"2204.09271","title":"A Survey of Video-based Action Quality Assessment","created":"2022-04-20","cited_by_count":14,"area":null},{"id":"2403.13798","title":"Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment","created":"2024-03-20","cited_by_count":14,"area":null},{"id":"2512.15153","title":"Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning","created":"2025-12-17","cited_by_count":14,"area":"lr"},{"id":"2208.02611","title":"Surgical Skill Assessment via Video Semantic Aggregation","created":"2022-08-04","cited_by_count":13,"area":null},{"id":"2309.17105","title":"Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling","created":"2023-09-29","cited_by_count":12,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2505.19972","title":"PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2301.06103","title":"Learning Sparse Temporal Video Mapping for Action Quality Assessment in Floor Gymnastics","created":"2023-01-15","cited_by_count":9,"area":null},{"id":"2303.09097","title":"IRIS: Interpretable Rubric-Informed Segmentation for Action Quality Assessment","created":"2023-03-16","cited_by_count":9,"area":null},{"id":"2207.14513","title":"Uncertainty-Driven Action Quality Assessment","created":"2022-07-29","cited_by_count":7,"area":null},{"id":"2408.11687","title":"Interpretable Long-term Action Quality Assessment","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2408.16638","title":"3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach","created":"2024-08-29","cited_by_count":7,"area":null},{"id":"2502.02817","title":"A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2208.11191","title":"Towards cumulative race time regression in sports: I3D ConvNet transfer learning in ultra-distance running events","created":"2022-08-23","cited_by_count":6,"area":null},{"id":"2411.17130","title":"TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching","created":"2024-11-26","cited_by_count":6,"area":null},{"id":"2402.11057","title":"Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2102.07355","title":"Win-Fail Action Recognition","created":"2021-02-15","cited_by_count":4,"area":null},{"id":"2102.10555","title":"Improving Action Quality Assessment using Weighted Aggregation","created":"2021-02-21","cited_by_count":4,"area":null},{"id":"2309.11718","title":"CPR-Coach: Recognizing Composite Error Actions based on Single-class Training","created":"2023-09-21","cited_by_count":4,"area":null},{"id":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2603.22756","title":"MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding","created":"2026-03-24","cited_by_count":4,"area":"mllm"},{"id":"2307.02730","title":"Fine-grained Action Analysis: A Multi-modality and Multi-task Dataset of Figure Skating","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2312.15236","title":"Classifying Soccer Ball-on-Goal Position Through Kicker Shooting Action","created":"2023-12-23","cited_by_count":3,"area":null},{"id":"2510.01362","title":"EvoStruggle: A Dataset Capturing the Evolution of Struggle across Activities and Skill Levels","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2111.03819","title":"Will You Ever Become Popular? Learning to Predict Virality of Dance Clips","created":"2021-11-06","cited_by_count":2,"area":null},{"id":"2312.00856","title":"QAFE-Net: Quality Assessment of Facial Expressions with Landmark Heatmaps","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2401.10805","title":"Learning to Visually Connect Actions and their Effects","created":"2024-01-19","cited_by_count":2,"area":null},{"id":"2410.14161","title":"Unlabeled Action Quality Assessment Based on Multi-dimensional Adaptive Constrained Dynamic Time Warping","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2508.16291","title":"Learning Long-Range Action Representation by Two-Stream Mamba Pyramid Network for Figure Skating Assessment","created":"2025-08-22","cited_by_count":2,"area":"ssm"},{"id":"2203.06749","title":"Decontextualized I3D ConvNet for ultra-distance runners performance analysis at a glance","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2306.14490","title":"TaiChi Action Capture and Performance Analysis with Multi-view RGB Cameras","created":"2023-06-26","cited_by_count":1,"area":null},{"id":"2307.12183","title":"An X3D Neural Network Analysis for Runner's Performance Assessment in a Wild Sporting Environment","created":"2023-07-22","cited_by_count":1,"area":null},{"id":"2504.09530","title":"Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorders","created":"2025-04-13","cited_by_count":1,"area":null},{"id":"2506.03198","title":"FLEX: A Largescale Multimodal, Multiview Dataset for Learning Structured Representations for Fitness Action Quality Assessment","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.12292","title":"Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2603.25163","title":"SportSkills: Physical Skill Learning from Sports Instructional Videos","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2608.08736","title":"FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models","created":"2026-08-09","cited_by_count":1,"area":"mllm"},{"id":"2108.02572","title":"SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.02725","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2109.05778","title":"Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2202.02830","title":"Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2203.11011","title":"Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2205.08335","title":"Explanation-Guided Fairness Testing through Genetic Algorithm","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2207.14648","title":"Using Graph Neural Networks for Program Termination","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2303.09664","title":"Tribe or Not? Critical Inspection of Group Differences Using TribalGram","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2311.00401","title":"A Spatial-Temporal Transformer based Framework For Human Pose Assessment And Correction in Education Scenarios","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2508.10281","title":"VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2511.10250","title":"FineSkiing: A Fine-grained Benchmark for Skiing Action Quality Assessment","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2601.20661","title":"ProSkill: Segment-Level Skill Assessment in Procedural Videos","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.08945","title":"MLCR: Multi-Level Cue Refinement for Long-Term Multimodal Action Quality Assessment","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.15992","title":"Multi-Task Tennis Stroke Biomechanics Analysis Using MediaPipe Pose","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2607.19826","title":"MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Experts","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.03047","title":"AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.26094","title":"MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.19354","title":"Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2610.06972","title":"BoT-Feedback: Grounding Multimodal Reasoning in Biomechanical Evidence for Explainable Human Action Feedback","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}