{"list":"other","total":112,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"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":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155},{"id":"1804.04527","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","created":"2018-04-12","cited_by_count":150},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142},{"id":"2011.13367","title":"SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos","created":"2020-11-26","cited_by_count":131},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107},{"id":"2409.02889","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","created":"2024-09-04","cited_by_count":102},{"id":"1802.02774","title":"Learning to score the figure skating sports videos","created":"2018-02-08","cited_by_count":73},{"id":"2406.11303","title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning","created":"2024-06-17","cited_by_count":72},{"id":"2503.11495","title":"V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning","created":"2025-03-14","cited_by_count":68},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57},{"id":"2403.02727","title":"HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?","created":"2024-03-05","cited_by_count":54},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46},{"id":"1906.03221","title":"Data-to-text Generation with Entity Modeling","created":"2019-06-07","cited_by_count":45},{"id":"2310.10553","title":"TacticAI: an AI assistant for football tactics","created":"2023-10-16","cited_by_count":44},{"id":"2406.08407","title":"MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos","created":"2024-06-12","cited_by_count":43},{"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},{"id":"2304.04617","title":"VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views","created":"2023-04-10","cited_by_count":38},{"id":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37},{"id":"2505.00681","title":"MINERVA: Evaluating Complex Video Reasoning","created":"2025-05-01","cited_by_count":32},{"id":"2008.04524","title":"Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players","created":"2020-08-11","cited_by_count":30},{"id":"2405.06061","title":"GPTCoach: Towards LLM-Based Physical Activity Coaching","created":"2024-05-09","cited_by_count":29},{"id":"2202.14019","title":"Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment","created":"2022-02-28","cited_by_count":25},{"id":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23},{"id":"2410.05774","title":"ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition","created":"2024-10-08","cited_by_count":21},{"id":"2203.03990","title":"Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs","created":"2022-03-08","cited_by_count":20},{"id":"2412.11149","title":"A Comprehensive Survey of Action Quality Assessment: Method and Benchmark","created":"2024-12-15","cited_by_count":20},{"id":"2506.05425","title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","created":"2025-06-05","cited_by_count":18},{"id":"2309.01270","title":"COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers","created":"2023-09-03","cited_by_count":17},{"id":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17},{"id":"2511.06499","title":"SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports","created":"2025-11-09","cited_by_count":17},{"id":"2306.04948","title":"ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis","created":"2023-06-08","cited_by_count":15},{"id":"2412.00927","title":"VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation","created":"2024-12-01","cited_by_count":14},{"id":"2502.12558","title":"MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval","created":"2025-02-18","cited_by_count":14},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14},{"id":"2504.17365","title":"TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation","created":"2025-04-24","cited_by_count":13},{"id":"2407.07196","title":"Large Language Models for Wearable Sensor-Based Human Activity Recognition, Health Monitoring, and Behavioral Modeling: A Survey of Early Trends, Datasets, and Challenges","created":"2024-07-09","cited_by_count":12},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11},{"id":"2505.22810","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","created":"2025-05-28","cited_by_count":11},{"id":"2406.12252","title":"Language and Multimodal Models in Sports: A Survey of Datasets and Applications","created":"2024-06-18","cited_by_count":10},{"id":"2508.07554","title":"FineBadminton: A Multi-Level Dataset for Fine-Grained Badminton Video Understanding","created":"2025-08-11","cited_by_count":10},{"id":"2502.20480","title":"VideoA11y: Method and Dataset for Accessible Video Description","created":"2025-02-27","cited_by_count":9},{"id":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9},{"id":"2507.16878","title":"CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos","created":"2025-07-22","cited_by_count":9},{"id":"2402.10979","title":"SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs","created":"2024-02-15","cited_by_count":8},{"id":"2408.05123","title":"Sportify: Question Answering with Embedded Visualizations and Personified Narratives for Sports Video","created":"2024-08-09","cited_by_count":8},{"id":"2410.06682","title":"Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization","created":"2024-10-09","cited_by_count":8},{"id":"2505.16630","title":"SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding","created":"2025-05-22","cited_by_count":8},{"id":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8},{"id":"2110.05750","title":"SportsSum2.0: Generating High-Quality Sports News from Live Text Commentary","created":"2021-10-12","cited_by_count":7},{"id":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7},{"id":"2410.15270","title":"FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning","created":"2024-10-20","cited_by_count":7},{"id":"2412.17637","title":"SCBench: A Sports Commentary Benchmark for Video LLMs","created":"2024-12-23","cited_by_count":7},{"id":"2505.13860","title":"Domain Adaptation of VLM for Soccer Video Understanding","created":"2025-05-20","cited_by_count":7},{"id":"2507.20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","created":"2025-07-27","cited_by_count":7},{"id":"2504.19514","title":"FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding","created":"2025-04-28","cited_by_count":6},{"id":"2406.18116","title":"BADGE: BADminton report Generation and Evaluation with LLM","created":"2024-06-26","cited_by_count":5},{"id":"2509.11796","title":"FineQuest: Adaptive Knowledge-Assisted Sports Video Understanding via Agent-of-Thoughts Reasoning","created":"2025-09-15","cited_by_count":5},{"id":"2305.03851","title":"Large Language Models in Sport Science & Medicine: Opportunities, Risks and Considerations","created":"2023-05-05","cited_by_count":4},{"id":"2402.15514","title":"Large Scale Generative AI Text Applied to Sports and Music","created":"2024-01-31","cited_by_count":4},{"id":"2506.02351","title":"DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization","created":"2025-06-03","cited_by_count":4},{"id":"2506.05274","title":"From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos","created":"2025-06-05","cited_by_count":4},{"id":"2509.11698","title":"CoachMe: Decoding Sport Elements with a Reference-Based Coaching Instruction Generation Model","created":"2025-09-15","cited_by_count":4},{"id":"2212.10935","title":"Commentary Generation from Data Records of Multiplayer Strategy Esports Game","created":"2022-12-21","cited_by_count":3},{"id":"2403.04031","title":"Can Large Language Models do Analytical Reasoning?","created":"2024-03-06","cited_by_count":3},{"id":"2409.06224","title":"MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding","created":"2024-09-10","cited_by_count":3},{"id":"2502.04218","title":"Sports and Women's Sports: Gender Bias in Text Generation with Olympic Data","created":"2025-02-06","cited_by_count":3},{"id":"2503.10722","title":"TacticExpert: Spatial-Temporal Graph Language Model for Basketball Tactics","created":"2025-03-13","cited_by_count":3},{"id":"2507.17844","title":"SV3.3B: A Sports Video Understanding Model for Action Recognition","created":"2025-07-23","cited_by_count":3},{"id":"2509.06994","title":"VLMs-in-the-Wild: Bridging the Gap Between Academic Benchmarks and Enterprise Reality","created":"2025-09-03","cited_by_count":3}],"next_cursor":"100"}