{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107},{"id":"1904.04346","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","created":"2019-04-08","cited_by_count":100},{"id":"1611.05125","title":"Learning To Score Olympic Events","created":"2016-11-16","cited_by_count":88},{"id":"2205.09443","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","created":"2022-05-19","cited_by_count":83},{"id":"2006.07665","title":"Uncertainty-aware Score Distribution Learning for Action Quality Assessment","created":"2020-06-13","cited_by_count":80},{"id":"1812.06367","title":"Action Quality Assessment Across Multiple Actions","created":"2018-12-15","cited_by_count":79},{"id":"2108.07797","title":"Group-aware Contrastive Regression for Action Quality Assessment","created":"2021-08-17","cited_by_count":75},{"id":"1802.02774","title":"Learning to score the figure skating sports videos","created":"2018-02-08","cited_by_count":73},{"id":"1812.05538","title":"The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos","created":"2018-12-13","cited_by_count":69},{"id":"2403.09508","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","created":"2024-03-14","cited_by_count":47},{"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},{"id":"2201.03746","title":"TSA-Net: Tube Self-Attention Network for Action Quality Assessment","created":"2022-01-11","cited_by_count":36},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36},{"id":"2207.09270","title":"Action Quality Assessment with Temporal Parsing Transformer","created":"2022-07-19","cited_by_count":31},{"id":"2404.05029","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","created":"2024-04-07","cited_by_count":31},{"id":"2406.06087","title":"GAIA: Rethinking Action Quality Assessment for AI-Generated Videos","created":"2024-06-10","cited_by_count":30},{"id":"2202.14019","title":"Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment","created":"2022-02-28","cited_by_count":25},{"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},{"id":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23},{"id":"2412.02725","title":"emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation","created":"2024-12-02","cited_by_count":22},{"id":"2402.09444","title":"Multimodal Action Quality Assessment","created":"2024-01-31","cited_by_count":20},{"id":"2404.14471","title":"Narrative Action Evaluation with Prompt-Guided Multimodal Interaction","created":"2024-04-22","cited_by_count":19},{"id":"2111.11029","title":"Auto-Encoding Score Distribution Regression for Action Quality Assessment","created":"2021-11-22","cited_by_count":18},{"id":"2101.04884","title":"Piano Skills Assessment","created":"2021-01-13","cited_by_count":16},{"id":"2403.13798","title":"Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment","created":"2024-03-20","cited_by_count":14},{"id":"2503.07860","title":"Video Action Differencing","created":"2025-03-10","cited_by_count":14},{"id":"2512.15153","title":"Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning","created":"2025-12-17","cited_by_count":14},{"id":"2404.01299","title":"CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes","created":"2024-04-01","cited_by_count":13},{"id":"2408.02138","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","created":"2024-08-04","cited_by_count":13},{"id":"2303.09097","title":"IRIS: Interpretable Rubric-Informed Segmentation for Action Quality Assessment","created":"2023-03-16","cited_by_count":9},{"id":"2008.04999","title":"VI-Net: View-Invariant Quality of Human Movement Assessment","created":"2020-08-11","cited_by_count":8},{"id":"2401.02841","title":"Multi-Stage Contrastive Regression for Action Quality Assessment","created":"2024-01-05","cited_by_count":8},{"id":"2207.14513","title":"Uncertainty-Driven Action Quality Assessment","created":"2022-07-29","cited_by_count":7},{"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},{"id":"2402.11057","title":"Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos","created":"2024-02-16","cited_by_count":5},{"id":"2303.00952","title":"Towards Activated Muscle Group Estimation in the Wild","created":"2023-03-02","cited_by_count":4},{"id":"2511.19629","title":"SkillSight: Efficient First-Person Skill Assessment with Gaze","created":"2025-11-24","cited_by_count":4},{"id":"2401.10805","title":"Learning to Visually Connect Actions and their Effects","created":"2024-01-19","cited_by_count":2},{"id":"2603.26938","title":"From 3D Pose to Prose: Biomechanics-Grounded Vision--Language Coaching","created":"2026-03-27","cited_by_count":2},{"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}],"next_cursor":null}