{"total":100,"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":"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":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"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":"2106.01035","title":"Towards Unified Surgical Skill Assessment","created":"2021-06-02","cited_by_count":49,"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":"2411.17221","title":"AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM","created":"2024-11-26","cited_by_count":24,"area":"mllm"},{"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":"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":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17,"area":null},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17,"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":"2408.02138","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","created":"2024-08-04","cited_by_count":13,"area":null},{"id":"2203.13309","title":"Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos","created":"2022-03-24","cited_by_count":12,"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":"2110.05697","title":"Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos","created":"2021-10-12","cited_by_count":11,"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":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2401.02841","title":"Multi-Stage Contrastive Regression for Action Quality Assessment","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2407.19675","title":"Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment","created":"2024-07-29","cited_by_count":8,"area":null},{"id":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8,"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":"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":"2505.08665","title":"SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation","created":"2025-05-13","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":"2303.00952","title":"Towards Activated Muscle Group Estimation in the Wild","created":"2023-03-02","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":"2503.23911","title":"FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment","created":"2025-03-31","cited_by_count":4,"area":null},{"id":"2505.20920","title":"HuMoCon: Concept Discovery for Human Motion Understanding","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2509.26278","title":"ProfVLM: A lightweight video-language model for multi-view proficiency estimation","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2511.19629","title":"SkillSight: Efficient First-Person Skill Assessment with Gaze","created":"2025-11-24","cited_by_count":4,"area":null},{"id":"2109.08730","title":"Unsupervised View-Invariant Human Posture Representation","created":"2021-09-17","cited_by_count":3,"area":null},{"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":"2310.02894","title":"Human-centric Behavior Description in Videos: New Benchmark and Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2310.10131","title":"3DYoga90: A Hierarchical Video Dataset for Yoga Pose Understanding","created":"2023-10-16","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":"2202.00712","title":"Should I take a walk? Estimating Energy Expenditure from Video Data","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2207.12318","title":"Action Quality Assessment using Transformers","created":"2022-07-20","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":"2410.20427","title":"YourSkatingCoach: A Figure Skating Video Benchmark for Fine-Grained Element Analysis","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2507.21945","title":"Attention-Driven Multimodal Alignment for Long-term Action Quality Assessment","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2603.14252","title":"MistExit: Learning to Exit for Early Mistake Detection in Procedural Videos","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2603.26938","title":"From 3D Pose to Prose: Biomechanics-Grounded Vision--Language Coaching","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2604.08294","title":"Can Vision Language Models Judge Action Quality? An Empirical Evaluation","created":"2026-04-09","cited_by_count":2,"area":"mllm"},{"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":"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":"2507.12617","title":"Predicting Soccer Penalty Kick Direction Using Human Action Recognition","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2508.16942","title":"HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2602.19004","title":"MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment","created":"2026-02-22","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":"2604.10466","title":"ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos","created":"2026-04-12","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":"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":"2409.20116","title":"REST-HANDS: Rehabilitation with Egocentric Vision Using Smartglasses for Treatment of Hands after Surviving Stroke","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2412.10573","title":"ExeChecker: Where Did I Go Wrong?","created":"2024-12-13","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":"2511.05611","title":"Focus on What Matters: Constraining Spatial-Temporal Attention via Action-Units for Noise-Resilient AQA","created":"2025-11-06","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":"2602.08996","title":"Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case Study","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2603.00108","title":"SurgFusion-Net: Diversified Adaptive Multimodal Fusion Network for Surgical Skill Assessment","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.26400","title":"SHANDS: A Multi-View Dataset and Benchmark for Surgical Hand-Gesture and Error Recognition Toward Medical Training","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.03848","title":"Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback","created":"2026-05-05","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":"2606.17615","title":"SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.23061","title":"MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.28104","title":"Cross-view Multimodal Vision-Based Assessment Framework for Traditional Chinese Medicine Rehabilitation Training","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.31127","title":"SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos","created":"2026-06-30","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":"2607.21267","title":"BasketEvent: Understanding Who Did What and When in Basketball Videos","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.23474","title":"What's the Catch? Evaluating Temporal Consistency in Vision-Language Models","created":"2026-08-24","cited_by_count":0,"area":"mllm"},{"id":"2608.26094","title":"MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.26056","title":"CricRAG: Retrieval Augmented Vision-Language Models for Personalized Cricket Coaching","created":"2026-08-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}