{"total":81,"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":"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":"2109.08409","title":"Expression Snippet Transformer for Robust Video-based Facial Expression Recognition","created":"2021-09-17","cited_by_count":33,"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":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23,"area":null},{"id":"2104.10122","title":"Improving state-of-the-art in Detecting Student Engagement with Resnet and TCN Hybrid Network","created":"2021-04-20","cited_by_count":22,"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":"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":"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":"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":"2503.07860","title":"Video Action Differencing","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2208.02611","title":"Surgical Skill Assessment via Video Semantic Aggregation","created":"2022-08-04","cited_by_count":13,"area":null},{"id":"2408.02138","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","created":"2024-08-04","cited_by_count":13,"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":"2312.05897","title":"PSCR: Patches Sampling-based Contrastive Regression for AIGC Image Quality Assessment","created":"2023-12-10","cited_by_count":10,"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":"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":"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":"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":"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":"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":"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":"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":"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":"2407.02738","title":"ZEAL: Surgical Skill Assessment with Zero-shot Tool Inference Using Unified Foundation Model","created":"2024-07-03","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":"2604.10466","title":"ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos","created":"2026-04-12","cited_by_count":1,"area":null},{"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":"2109.15063","title":"Workflow Augmentation of Video Data for Event Recognition with Time-Sensitive Neural Networks","created":"2021-09-30","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":"2412.10573","title":"ExeChecker: Where Did I Go Wrong?","created":"2024-12-13","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":"2602.16545","title":"Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding","created":"2026-02-18","cited_by_count":0,"area":null},{"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":"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":"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":"2608.25736","title":"Moving Beyond More Views: Redundancy-Aware Ego-Exo Fusion for Proficiency Estimation","created":"2026-08-26","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":"2609.09711","title":"VFNet: Multi-View Spatio-Temporal Model for Void Fraction Estimation in Gas-Liquid Two-Phase Flow","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}