{"total":413,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"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,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"area":null},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576,"area":null},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528,"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":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447,"area":null},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429,"area":null},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"area":null},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290,"area":null},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265,"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":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227,"area":null},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214,"area":null},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"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":"2207.02595","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","created":"2022-07-06","cited_by_count":179,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140,"area":null},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130,"area":null},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117,"area":null},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107,"area":null},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99,"area":null},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95,"area":null},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"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":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","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":"2112.06197","title":"Video as Conditional Graph Hierarchy for Multi-Granular Question Answering","created":"2021-12-12","cited_by_count":68,"area":null},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66,"area":null},{"id":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65,"area":null},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62,"area":null},{"id":"2105.11107","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","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":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53,"area":null},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53,"area":null},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51,"area":null},{"id":"2210.05357","title":"Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment","created":"2022-10-11","cited_by_count":50,"area":null},{"id":"2401.11174","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","created":"2024-01-20","cited_by_count":49,"area":null},{"id":"2211.09648","title":"HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors","created":"2022-11-17","cited_by_count":47,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2101.00545","title":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","created":"2021-01-03","cited_by_count":45,"area":null},{"id":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42,"area":null},{"id":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40,"area":null},{"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,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"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":"2104.03178","title":"The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods","created":"2021-04-07","cited_by_count":38,"area":null},{"id":"2303.14124","title":"Towards Scalable Neural Representation for Diverse Videos","created":"2023-03-24","cited_by_count":37,"area":null},{"id":"2101.10241","title":"RGB-D Salient Object Detection via 3D Convolutional Neural Networks","created":"2021-01-25","cited_by_count":36,"area":null},{"id":"2110.06014","title":"Rethinking Supervised Pre-training for Better Downstream Transferring","created":"2021-10-12","cited_by_count":35,"area":null},{"id":"2307.01630","title":"ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour","created":"2023-07-04","cited_by_count":35,"area":null},{"id":"2404.00989","title":"360+x: A Panoptic Multi-modal Scene Understanding Dataset","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2212.04582","title":"Towards Holistic Surgical Scene Understanding","created":"2022-12-08","cited_by_count":33,"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":"2111.09887","title":"PyTorchVideo: A Deep Learning Library for Video Understanding","created":"2021-11-18","cited_by_count":32,"area":null},{"id":"2304.01199","title":"On the Benefits of 3D Pose and Tracking for Human Action Recognition","created":"2023-04-03","cited_by_count":32,"area":null},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31,"area":null},{"id":"2105.09803","title":"Weakly-Supervised Physically Unconstrained Gaze Estimation","created":"2021-05-20","cited_by_count":28,"area":null},{"id":"2112.04294","title":"A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos","created":"2021-12-08","cited_by_count":28,"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":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","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":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27,"area":null},{"id":"2109.09920","title":"Survey: Transformer based Video-Language Pre-training","created":"2021-09-21","cited_by_count":27,"area":null},{"id":"2109.05569","title":"MovieCuts: A New Dataset and Benchmark for Cut Type Recognition","created":"2021-09-12","cited_by_count":26,"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":"2305.07214","title":"MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition","created":"2023-05-12","cited_by_count":26,"area":null},{"id":"2403.17103","title":"Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos","created":"2024-03-25","cited_by_count":26,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25,"area":null},{"id":"2305.13495","title":"Type-to-Track: Retrieve Any Object via Prompt-based Tracking","created":"2023-05-22","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":"2203.14221","title":"How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?","created":"2022-03-27","cited_by_count":23,"area":null},{"id":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23,"area":null},{"id":"2302.05011","title":"Context Understanding in Computer Vision: A Survey","created":"2023-02-10","cited_by_count":23,"area":null},{"id":"2302.06294","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","created":"2023-02-13","cited_by_count":23,"area":null},{"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,"area":null},{"id":"2103.01933","title":"PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception","created":"2021-03-02","cited_by_count":22,"area":null},{"id":"2111.07868","title":"Tracking People with 3D Representations","created":"2021-11-15","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":"2312.03050","title":"HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding","created":"2023-12-05","cited_by_count":22,"area":null},{"id":"2503.21751","title":"Reconstructing Humans with a Biomechanically Accurate Skeleton","created":"2025-03-27","cited_by_count":22,"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}],"next_cursor":"100"}