{"total":96,"rows":[{"id":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","cited_by_count":40,"area":null},{"id":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37,"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":"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":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"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":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23,"area":null},{"id":"2404.05392","title":"T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos","created":"2024-04-08","cited_by_count":21,"area":null},{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21,"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":"2402.09444","title":"Multimodal Action Quality Assessment","created":"2024-01-31","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":"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":"2404.01891","title":"ASTRA: An Action Spotting TRAnsformer for Soccer Videos","created":"2024-04-02","cited_by_count":16,"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":"2503.07860","title":"Video Action Differencing","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2408.02138","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","created":"2024-08-04","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":"2402.00293","title":"FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation","created":"2024-02-01","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":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","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":"2512.11016","title":"SoccerMaster: A Vision Foundation Model for Soccer Understanding","created":"2025-12-11","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":"2411.16619","title":"Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric","created":"2024-11-25","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":"2404.09951","title":"Unifying Global and Local Scene Entities Modelling for Precise Action Spotting","created":"2024-04-15","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":"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":"2504.08222","title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","created":"2025-04-11","cited_by_count":7,"area":null},{"id":"2311.00556","title":"ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab","created":"2023-11-01","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":"2312.00055","title":"LEAP: LLM-Generation of Egocentric Action Programs","created":"2023-11-29","cited_by_count":5,"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":"2506.04996","title":"PATS: Proficiency-Aware Temporal Sampling for Multi-View Sports Skill Assessment","created":"2025-06-05","cited_by_count":5,"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":"2312.11024","title":"Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis","created":"2023-12-18","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":"2506.05274","title":"From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos","created":"2025-06-05","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":"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":"2408.10073","title":"Modelling the Distribution of Human Motion for Sign Language Assessment","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2409.01448","title":"FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2505.03991","title":"Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challenges","created":"2025-05-06","cited_by_count":3,"area":null},{"id":"2507.17844","title":"SV3.3B: A Sports Video Understanding Model for Action Recognition","created":"2025-07-23","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":"2209.12221","title":"Hand Hygiene Assessment via Joint Step Segmentation and Key Action Scorer","created":"2022-09-25","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":"2404.10383","title":"Learning to Score Sign Language with Two-stage Method","created":"2024-04-16","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":"2509.21595","title":"Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2 Feature Representations for Video Action Analysis","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2602.22073","title":"AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting","created":"2026-02-25","cited_by_count":2,"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":"2309.13962","title":"Egocentric RGB+Depth Action Recognition in Industry-Like Settings","created":"2023-09-25","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":"2507.07381","title":"Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos","created":"2025-07-10","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":"2603.13397","title":"TennisExpert: Towards Expert-Level Analytical Sports Video Understanding","created":"2026-03-11","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":"2604.15736","title":"RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2606.29531","title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2607.01117","title":"MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2405.17729","title":"Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2504.00149","title":"Towards Precise Action Spotting: Addressing Temporal Misalignment in Labels with Dynamic Label Assignment","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2508.19647","title":"UTAL-GNN: Unsupervised Temporal Action Localization using Graph Neural Networks","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.20715","title":"Beyond the Individual: Introducing Group Intention Forecasting with SHOT Dataset","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2511.01194","title":"A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessment","created":"2025-11-03","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":"2511.21653","title":"CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow","created":"2025-11-26","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":"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":"2604.19834","title":"KD-Judge: A Knowledge-Driven Automated Judge Framework for Functional Fitness Movements on Edge Devices","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2604.22839","title":"From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.02834","title":"VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition","created":"2026-05-04","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":"2606.23118","title":"LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions","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":"2606.29230","title":"Again-Pose: Anchor-Guided Adaptive Inter-Frame Motion Cues Propagating for High-quality Human Pose Reconstruction","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.07438","title":"Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.10998","title":"Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videos","created":"2026-07-13","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":"2608.03047","title":"AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.14377","title":"A Survey of Large Models in Sports","created":"2026-08-14","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":"2610.01188","title":"When Does Exercise-Specific Joint Selection Help? An Audit of Evaluation and Control Design","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.16383","title":"Throwing4: Phase-Aware Pose Modeling for Throw-Distance Prediction in Elite Athletics","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}