{"total":302,"rows":[{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"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":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"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":"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":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310,"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":"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":"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":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182,"area":null},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169,"area":null},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"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":"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":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112,"area":null},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"area":null},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","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":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91,"area":null},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85,"area":null},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84,"area":null},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84,"area":null},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77,"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":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"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":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59,"area":null},{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58,"area":null},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56,"area":null},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50,"area":null},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2204.13423","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","created":"2022-04-28","cited_by_count":50,"area":null},{"id":"2104.09952","title":"MGSampler: An Explainable Sampling Strategy for Video Action Recognition","created":"2021-04-20","cited_by_count":49,"area":null},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49,"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":"2108.11974","title":"Learning Cross-modal Contrastive Features for Video Domain Adaptation","created":"2021-08-26","cited_by_count":47,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2203.13611","title":"Class-Incremental Learning for Action Recognition in Videos","created":"2022-03-25","cited_by_count":46,"area":null},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46,"area":null},{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46,"area":null},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46,"area":null},{"id":"2411.05222","title":"Don't Look Twice: Faster Video Transformers with Run-Length Tokenization","created":"2024-11-07","cited_by_count":43,"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":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41,"area":null},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2307.08476","title":"SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training","created":"2023-07-17","cited_by_count":41,"area":null},{"id":"2104.11452","title":"SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos","created":"2021-04-23","cited_by_count":40,"area":null},{"id":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","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":"2112.14238","title":"AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition","created":"2021-12-28","cited_by_count":37,"area":null},{"id":"2304.00946","title":"MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition","created":"2023-04-03","cited_by_count":37,"area":null},{"id":"2105.05165","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","created":"2021-05-11","cited_by_count":36,"area":null},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2110.06178","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","created":"2021-10-12","cited_by_count":36,"area":null},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","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":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35,"area":null},{"id":"2306.11248","title":"Dynamic Perceiver for Efficient Visual Recognition","created":"2023-06-20","cited_by_count":33,"area":null},{"id":"2102.07092","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","created":"2021-02-14","cited_by_count":31,"area":null},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2112.03587","title":"TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning","created":"2021-12-07","cited_by_count":31,"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":"2107.04932","title":"Aligning Correlation Information for Domain Adaptation in Action Recognition","created":"2021-07-11","cited_by_count":30,"area":null},{"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":"2112.09690","title":"Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition","created":"2021-12-17","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":"2101.08085","title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","created":"2021-01-20","cited_by_count":28,"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":"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":"2104.05107","title":"Towards a Collective Agenda on AI for Earth Science Data Analysis","created":"2021-04-11","cited_by_count":27,"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":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27,"area":null},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"area":null},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","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":"2501.11340","title":"GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection","created":"2025-01-20","cited_by_count":25,"area":null},{"id":"2103.15395","title":"No frame left behind: Full Video Action Recognition","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2308.09346","title":"Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching","created":"2023-08-18","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":"2208.07365","title":"Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective","created":"2022-08-15","cited_by_count":21,"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":"2107.09262","title":"FoleyGAN: Visually Guided Generative Adversarial Network-Based Synchronous Sound Generation in Silent Videos","created":"2021-07-20","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":"2201.03080","title":"The State of Aerial Surveillance: A Survey","created":"2022-01-09","cited_by_count":20,"area":null},{"id":"2104.02967","title":"ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization","created":"2021-04-07","cited_by_count":19,"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":"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":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"id":"2106.15827","title":"When Video Classification Meets Incremental Classes","created":"2021-06-30","cited_by_count":18,"area":null}],"next_cursor":"100"}