{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"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":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127},{"id":"2312.01026","title":"Token Fusion: Bridging the Gap between Token Pruning and Token Merging","created":"2023-12-02","cited_by_count":125},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59},{"id":"2408.16730","title":"VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation","created":"2024-08-29","cited_by_count":55},{"id":"2503.18478","title":"Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding","created":"2025-03-24","cited_by_count":49},{"id":"2411.05222","title":"Don't Look Twice: Faster Video Transformers with Run-Length Tokenization","created":"2024-11-07","cited_by_count":43},{"id":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25},{"id":"2402.14327","title":"Subobject-level Image Tokenization","created":"2024-02-22","cited_by_count":21},{"id":"2505.14640","title":"VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation","created":"2025-05-20","cited_by_count":21},{"id":"2401.02931","title":"SPFormer: Enhancing Vision Transformer with Superpixel Representation","created":"2024-01-05","cited_by_count":13},{"id":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","cited_by_count":13},{"id":"2505.17020","title":"CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms","created":"2025-05-22","cited_by_count":11},{"id":"2505.23617","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","created":"2025-05-29","cited_by_count":7},{"id":"2508.03695","title":"Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition","created":"2025-08-05","cited_by_count":7}],"next_cursor":null}