{"total":239,"rows":[{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519,"area":null},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272,"area":null},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254,"area":null},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229,"area":"mllm"},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200,"area":null},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"area":null},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148,"area":null},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141,"area":null},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127,"area":null},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117,"area":"inference"},{"id":"2203.16761","title":"MeMOT: Multi-Object Tracking with Memory","created":"2022-03-31","cited_by_count":114,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112,"area":null},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108,"area":"ssm"},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107,"area":null},{"id":"2107.03377","title":"Long Short-Term Transformer for Online Action Detection","created":"2021-07-07","cited_by_count":88,"area":null},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84,"area":null},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"area":null},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68,"area":null},{"id":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54,"area":null},{"id":"2108.11819","title":"Mining Contextual Information Beyond Image for Semantic Segmentation","created":"2021-08-26","cited_by_count":48,"area":null},{"id":"2205.01230","title":"Retrieval-Enhanced Machine Learning","created":"2022-05-02","cited_by_count":47,"area":null},{"id":"2212.04090","title":"Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection","created":"2022-12-08","cited_by_count":47,"area":null},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45,"area":null},{"id":"2108.02722","title":"Video Contrastive Learning with Global Context","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"area":null},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41,"area":null},{"id":"2106.08827","title":"JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection","created":"2021-06-16","cited_by_count":39,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2405.15757","title":"Looking Backward: Streaming Video-to-Video Translation with Feature Banks","created":"2024-05-24","cited_by_count":38,"area":"diffusion"},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"id":"2110.10101","title":"Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition","created":"2021-10-19","cited_by_count":35,"area":null},{"id":"2105.06548","title":"Not All Memories are Created Equal: Learning to Forget by Expiring","created":"2021-05-13","cited_by_count":32,"area":null},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32,"area":null},{"id":"2202.06851","title":"HAKE: A Knowledge Engine Foundation for Human Activity Understanding","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2210.12686","title":"Holistic Interaction Transformer Network for Action Detection","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"id":"2209.10918","title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","created":"2022-09-22","cited_by_count":27,"area":null},{"id":"2303.12698","title":"Open Set Action Recognition via Multi-Label Evidential Learning","created":"2023-02-27","cited_by_count":26,"area":null},{"id":"2103.16024","title":"Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation","created":"2021-03-30","cited_by_count":25,"area":null},{"id":"2209.13502","title":"Visual Object Tracking in First Person Vision","created":"2022-09-27","cited_by_count":25,"area":null},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25,"area":null},{"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,"area":null},{"id":"2407.08476","title":"VideoMamba: Spatio-Temporal Selective State Space Model","created":"2024-07-11","cited_by_count":25,"area":"ssm"},{"id":"2103.15632","title":"Regular Polytope Networks","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24,"area":"lr"},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2310.16447","title":"ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors","created":"2023-10-25","cited_by_count":24,"area":null},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","cited_by_count":24,"area":null},{"id":"2111.11044","title":"Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos","created":"2021-11-22","cited_by_count":23,"area":null},{"id":"2406.14235","title":"Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation","created":"2024-06-20","cited_by_count":23,"area":null},{"id":"2103.16565","title":"Learning Representational Invariances for Data-Efficient Action Recognition","created":"2021-03-30","cited_by_count":22,"area":null},{"id":"2204.01184","title":"Exploiting Temporal Relations on Radar Perception for Autonomous Driving","created":"2022-04-03","cited_by_count":22,"area":null},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22,"area":null},{"id":"2303.15879","title":"STMixer: A One-Stage Sparse Action Detector","created":"2023-03-28","cited_by_count":22,"area":null},{"id":"2108.13665","title":"Is First Person Vision Challenging for Object Tracking?","created":"2021-08-31","cited_by_count":21,"area":null},{"id":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2105.11731","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","created":"2021-05-25","cited_by_count":20,"area":null},{"id":"2304.08451","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","created":"2023-04-17","cited_by_count":20,"area":null},{"id":"2304.12160","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","created":"2023-04-24","cited_by_count":20,"area":null},{"id":"2111.01936","title":"Revisiting spatio-temporal layouts for compositional action recognition","created":"2021-11-02","cited_by_count":19,"area":null},{"id":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","cited_by_count":19,"area":null},{"id":"2211.14053","title":"Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization","created":"2022-11-25","cited_by_count":19,"area":null},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2112.10977","title":"ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization","created":"2021-12-21","cited_by_count":17,"area":null},{"id":"2209.01425","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","created":"2022-09-03","cited_by_count":17,"area":null},{"id":"2108.06435","title":"Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring","created":"2021-08-14","cited_by_count":16,"area":null},{"id":"2108.06706","title":"Temporal Action Segmentation with High-level Complex Activity Labels","created":"2021-08-15","cited_by_count":16,"area":null},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2204.03017","title":"Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency","created":"2022-04-06","cited_by_count":15,"area":null},{"id":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2404.04565","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","created":"2024-04-06","cited_by_count":15,"area":null}],"next_cursor":"100"}