{"total":316,"rows":[{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681,"area":null},{"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":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"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":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435,"area":null},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363,"area":null},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311,"area":null},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293,"area":null},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272,"area":null},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264,"area":null},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230,"area":null},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215,"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":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156,"area":null},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151,"area":null},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","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":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133,"area":null},{"id":"2103.07976","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","created":"2021-03-14","cited_by_count":132,"area":null},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129,"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":"2111.12082","title":"PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer","created":"2021-11-23","cited_by_count":120,"area":null},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117,"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":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111,"area":null},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106,"area":null},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103,"area":null},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99,"area":null},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96,"area":null},{"id":"2211.15098","title":"MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection","created":"2022-11-28","cited_by_count":89,"area":null},{"id":"2203.17030","title":"Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks","created":"2022-03-31","cited_by_count":88,"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":"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":"2108.05988","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","created":"2021-08-12","cited_by_count":81,"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":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","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":"2109.02303","title":"Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation","created":"2021-09-06","cited_by_count":62,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2207.12647","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","created":"2022-07-26","cited_by_count":57,"area":"lr"},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55,"area":null},{"id":"2105.00637","title":"ISTR: End-to-End Instance Segmentation with Transformers","created":"2021-05-03","cited_by_count":52,"area":null},{"id":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2103.06982","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","created":"2021-03-11","cited_by_count":50,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2110.01401","title":"MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction","created":"2021-09-30","cited_by_count":48,"area":null},{"id":"2302.03548","title":"PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer","created":"2023-02-07","cited_by_count":48,"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":"2210.07503","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","created":"2022-10-14","cited_by_count":43,"area":null},{"id":"2105.00335","title":"Audio Transformers","created":"2021-05-01","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":"2101.03904","title":"Trear: Transformer-based RGB-D Egocentric Action Recognition","created":"2021-01-05","cited_by_count":39,"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":"2203.04570","title":"CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction","created":"2022-03-09","cited_by_count":39,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","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":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"id":"2109.02613","title":"Class Semantics-based Attention for Action Detection","created":"2021-09-06","cited_by_count":36,"area":null},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35,"area":null},{"id":"2107.00977","title":"Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation","created":"2021-07-02","cited_by_count":34,"area":null},{"id":"2108.05307","title":"Video Transformer for Deepfake Detection with Incremental Learning","created":"2021-08-11","cited_by_count":33,"area":null},{"id":"2109.08409","title":"Expression Snippet Transformer for Robust Video-based Facial Expression Recognition","created":"2021-09-17","cited_by_count":33,"area":null},{"id":"2205.12551","title":"Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers","created":"2022-05-25","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":"2111.12476","title":"Hierarchical Modular Network for Video Captioning","created":"2021-11-24","cited_by_count":32,"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":"2112.09828","title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs","created":"2021-12-18","cited_by_count":31,"area":null},{"id":"2202.09277","title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","created":"2022-02-18","cited_by_count":30,"area":null},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29,"area":null},{"id":"2104.01745","title":"A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification","created":"2021-04-05","cited_by_count":28,"area":null},{"id":"2108.02607","title":"UniCon: Unified Context Network for Robust Active Speaker Detection","created":"2021-08-05","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":"2110.09310","title":"Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention","created":"2021-10-18","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":"2203.11113","title":"No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces","created":"2022-03-21","cited_by_count":25,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2301.02240","title":"Skip-Attention: Improving Vision Transformers by Paying Less Attention","created":"2023-01-05","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":"2203.13639","title":"Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness","created":"2022-03-25","cited_by_count":23,"area":null},{"id":"2104.01353","title":"Deepfake Detection Scheme Based on Vision Transformer and Distillation","created":"2021-04-03","cited_by_count":22,"area":null},{"id":"2110.09783","title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences","created":"2021-10-19","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":"2305.03277","title":"FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing","created":"2023-05-05","cited_by_count":22,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2107.08031","title":"Is attention to bounding boxes all you need for pedestrian action prediction?","created":"2021-07-16","cited_by_count":21,"area":null},{"id":"2207.13516","title":"Online Continual Learning with Contrastive Vision Transformer","created":"2022-07-24","cited_by_count":21,"area":null},{"id":"2303.15591","title":"Learning Expressive Prompting With Residuals for Vision Transformers","created":"2023-03-27","cited_by_count":21,"area":null},{"id":"2308.08885","title":"Event-Guided Procedure Planning from Instructional Videos with Text Supervision","created":"2023-08-17","cited_by_count":21,"area":null}],"next_cursor":"100"}