{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"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":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138},{"id":"2505.21374","title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","created":"2025-05-27","cited_by_count":118},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82},{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77},{"id":"2411.18211","title":"TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability","created":"2024-11-27","cited_by_count":70},{"id":"2412.06171","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","created":"2024-12-09","cited_by_count":70},{"id":"2406.04292","title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","created":"2024-06-06","cited_by_count":67},{"id":"2511.20785","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","created":"2025-11-25","cited_by_count":61},{"id":"2501.05874","title":"VideoRAG: Retrieval-Augmented Generation over Video Corpus","created":"2025-01-10","cited_by_count":57},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42},{"id":"2308.10045","title":"An Empirical Study of CLIP for Text-based Person Search","created":"2023-08-19","cited_by_count":38},{"id":"2504.13092","title":"EventVAD: Training-Free Event-Aware Video Anomaly Detection","created":"2025-04-17","cited_by_count":36},{"id":"2412.01095","title":"VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models","created":"2024-12-02","cited_by_count":24},{"id":"2502.02449","title":"TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes","created":"2025-02-04","cited_by_count":23},{"id":"2505.12589","title":"SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models","created":"2025-05-19","cited_by_count":18},{"id":"2503.09149","title":"Memory-enhanced Retrieval Augmentation for Long Video Understanding","created":"2025-03-12","cited_by_count":17},{"id":"2502.12558","title":"MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval","created":"2025-02-18","cited_by_count":14},{"id":"2505.13928","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","created":"2025-05-20","cited_by_count":14},{"id":"2411.16173","title":"SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis","created":"2024-11-25","cited_by_count":13},{"id":"2505.23990","title":"Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video Understanding","created":"2025-05-29","cited_by_count":13},{"id":"2509.25638","title":"Generalized Contrastive Learning for Universal Multimodal Retrieval","created":"2025-09-30","cited_by_count":7},{"id":"2406.10079","title":"Localizing Events in Videos with Multimodal Queries","created":"2024-06-14","cited_by_count":6},{"id":"2506.12992","title":"SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models","created":"2025-06-15","cited_by_count":4}],"next_cursor":null}