{"total":215,"rows":[{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109,"area":"mllm"},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780,"area":"diffusion"},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"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":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484,"area":null},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272,"area":null},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253,"area":null},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212,"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":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148,"area":null},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"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":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"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":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116,"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":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2101.08515","title":"Pre-training without Natural Images","created":"2021-01-21","cited_by_count":100,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2301.00265","title":"Source-Free Unsupervised Domain Adaptation: A Survey","created":"2022-12-31","cited_by_count":80,"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":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63,"area":null},{"id":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63,"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":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"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":"2306.09486","title":"FedMultimodal: A Benchmark For Multimodal Federated Learning","created":"2023-06-15","cited_by_count":51,"area":null},{"id":"2101.10803","title":"ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning","created":"2021-01-26","cited_by_count":50,"area":null},{"id":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48,"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":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","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":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2112.07175","title":"Co-training Transformer with Videos and Images Improves Action Recognition","created":"2021-12-14","cited_by_count":41,"area":null},{"id":"2210.06583","title":"S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces","created":"2022-10-12","cited_by_count":41,"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":"2403.13044","title":"Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos","created":"2024-03-19","cited_by_count":38,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","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":"2106.03932","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30,"area":"lr"},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29,"area":null},{"id":"2207.01398","title":"Large-scale Robustness Analysis of Video Action Recognition Models","created":"2022-07-04","cited_by_count":29,"area":null},{"id":"2203.04559","title":"Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition","created":"2022-03-09","cited_by_count":28,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2203.14957","title":"Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning","created":"2022-03-28","cited_by_count":27,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2306.08713","title":"What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations","created":"2023-06-14","cited_by_count":25,"area":null},{"id":"2504.07745","title":"SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding","created":"2025-04-10","cited_by_count":25,"area":"mllm"},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","cited_by_count":24,"area":"mllm"},{"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":"2304.00571","title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks","created":"2023-04-02","cited_by_count":22,"area":null},{"id":"2106.14104","title":"Can An Image Classifier Suffice For Action Recognition?","created":"2021-06-26","cited_by_count":20,"area":null},{"id":"2108.11575","title":"Shifted Chunk Transformer for Spatio-Temporal Representational Learning","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2109.09964","title":"Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment","created":"2021-09-21","cited_by_count":20,"area":null},{"id":"2206.09852","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","created":"2022-06-20","cited_by_count":20,"area":null},{"id":"2503.19740","title":"LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings","created":"2025-03-25","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":"2503.16036","title":"Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models","created":"2025-03-20","cited_by_count":19,"area":"mllm"},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"area":"mllm"},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2203.13371","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2308.09139","title":"The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation","created":"2023-08-17","cited_by_count":16,"area":null},{"id":"2102.07887","title":"VA-RED$^2$: Video Adaptive Redundancy Reduction","created":"2021-02-15","cited_by_count":15,"area":null},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2112.06909","title":"Hallucinating Pose-Compatible Scenes","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2303.12001","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2306.17778","title":"Look, Remember and Reason: Grounded reasoning in videos with language models","created":"2023-06-30","cited_by_count":14,"area":"lr"},{"id":"2307.03166","title":"VideoGLUE: Video General Understanding Evaluation of Foundation Models","created":"2023-07-06","cited_by_count":14,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2507.13364","title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","created":"2025-07-06","cited_by_count":14,"area":null},{"id":"2408.02464","title":"Fairness and Bias Mitigation in Computer Vision: A Survey","created":"2024-08-05","cited_by_count":13,"area":null},{"id":"2412.19178","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","created":"2024-12-26","cited_by_count":13,"area":null},{"id":"2201.05916","title":"Multi-level Second-order Few-shot Learning","created":"2022-01-15","cited_by_count":12,"area":null},{"id":"2203.02480","title":"Didn't see that coming: a survey on non-verbal social human behavior forecasting","created":"2022-03-04","cited_by_count":12,"area":null},{"id":"2204.07892","title":"Video Action Detection: Analysing Limitations and Challenges","created":"2022-04-17","cited_by_count":12,"area":null},{"id":"2207.10664","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2211.10412","title":"Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2309.01265","title":"SOAR: Scene-debiasing Open-set Action Recognition","created":"2023-09-03","cited_by_count":12,"area":null},{"id":"2312.02914","title":"Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2405.17719","title":"Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2412.19794","title":"MVTamperBench: Evaluating Robustness of Vision-Language Models","created":"2024-12-27","cited_by_count":11,"area":"mllm"},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2205.02028","title":"TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition","created":"2022-05-04","cited_by_count":10,"area":null},{"id":"2209.12362","title":"Multi-dataset Training of Transformers for Robust Action Recognition","created":"2022-09-26","cited_by_count":10,"area":null}],"next_cursor":"100"}