{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"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":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108},{"id":"2412.10360","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","created":"2024-12-13","cited_by_count":89},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"1907.08340","title":"Only Time Can Tell: Discovering Temporal Data for Temporal Modeling","created":"2019-07-19","cited_by_count":67},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51},{"id":"2306.08731","title":"EPIC Fields: Marrying 3D Geometry and Video Understanding","created":"2023-06-14","cited_by_count":49},{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46},{"id":"2303.09857","title":"Dual-path Adaptation from Image to Video Transformers","created":"2023-03-17","cited_by_count":41},{"id":"2310.08584","title":"Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video","created":"2023-10-12","cited_by_count":40},{"id":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30},{"id":"2506.03340","title":"Seeing the Arrow of Time in Large Multimodal Models","created":"2025-06-03","cited_by_count":30},{"id":"1512.01848","title":"Rank Pooling for Action Recognition","created":"2015-12-06","cited_by_count":29},{"id":"1506.04714","title":"Slow and steady feature analysis: higher order temporal coherence in video","created":"2015-06-15","cited_by_count":28},{"id":"1506.03011","title":"Learning to Linearize Under Uncertainty","created":"2015-06-09","cited_by_count":25},{"id":"2501.05453","title":"An Empirical Study of Autoregressive Pre-training from Videos","created":"2025-01-09","cited_by_count":21},{"id":"2105.02545","title":"Unsupervised Visual Representation Learning by Tracking Patches in Video","created":"2021-05-06","cited_by_count":20},{"id":"1807.06980","title":"Video Time: Properties, Encoders and Evaluation","created":"2018-07-18","cited_by_count":19},{"id":"2303.16268","title":"TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition","created":"2023-03-28","cited_by_count":16},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15},{"id":"2006.09512","title":"Visual Chirality","created":"2020-06-16","cited_by_count":14},{"id":"2310.01324","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","created":"2023-10-02","cited_by_count":14},{"id":"2407.15447","title":"SIGMA: Sinkhorn-Guided Masked Video Modeling","created":"2024-07-22","cited_by_count":14},{"id":"2210.10828","title":"Grounded Video Situation Recognition","created":"2022-10-19","cited_by_count":13},{"id":"2303.11003","title":"Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization","created":"2023-03-20","cited_by_count":12},{"id":"2207.09067","title":"Time Is MattEr: Temporal Self-supervision for Video Transformers","created":"2022-07-19","cited_by_count":11},{"id":"2305.06437","title":"Self-Supervised Video Representation Learning via Latent Time Navigation","created":"2023-05-10","cited_by_count":11},{"id":"1909.09422","title":"Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos","created":"2019-09-20","cited_by_count":9},{"id":"2411.01777","title":"Learning predictable and robust neural representations by straightening image sequences","created":"2024-11-04","cited_by_count":9},{"id":"2504.00527","title":"SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning","created":"2025-04-01","cited_by_count":9},{"id":"2404.16828","title":"Made to Order: Discovering monotonic temporal changes via self-supervised video ordering","created":"2024-04-25","cited_by_count":5},{"id":"2409.02371","title":"Unfolding Videos Dynamics via Taylor Expansion","created":"2024-09-04","cited_by_count":3},{"id":"2410.24213","title":"Learning Video Representations without Natural Videos","created":"2024-10-31","cited_by_count":3},{"id":"2503.24298","title":"Order Matters: On Parameter-Efficient Image-to-Video Probing for Recognizing Nearly Symmetric Actions","created":"2025-03-31","cited_by_count":3},{"id":"2408.09220","title":"Flatten: Video Action Recognition is an Image Classification task","created":"2024-08-17","cited_by_count":1},{"id":"2408.11318","title":"TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models","created":"2024-08-21","cited_by_count":1}],"next_cursor":null}