{"total":221,"rows":[{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"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":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"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":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133,"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":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112,"area":null},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104,"area":null},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102,"area":null},{"id":"2302.05160","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","created":"2023-02-10","cited_by_count":90,"area":null},{"id":"2406.11815","title":"LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning","created":"2024-06-17","cited_by_count":87,"area":"mllm"},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"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":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68,"area":null},{"id":"2104.14913","title":"Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification","created":"2021-04-30","cited_by_count":63,"area":null},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51,"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":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"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":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46,"area":null},{"id":"2103.14470","title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","created":"2021-03-26","cited_by_count":43,"area":null},{"id":"2106.11958","title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","created":"2021-06-22","cited_by_count":43,"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":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37,"area":null},{"id":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35,"area":null},{"id":"2309.17116","title":"Sheaf Hypergraph Networks","created":"2023-09-29","cited_by_count":34,"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":"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":"2112.03587","title":"TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning","created":"2021-12-07","cited_by_count":31,"area":null},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","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":"2106.13432","title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2112.00302","title":"Graph Convolutional Module for Temporal Action Localization in Videos","created":"2021-12-01","cited_by_count":29,"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":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28,"area":"distill"},{"id":"2106.01603","title":"CT-Net: Channel Tensorization Network for Video Classification","created":"2021-06-03","cited_by_count":26,"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":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","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":"2112.10992","title":"Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition","created":"2021-12-21","cited_by_count":23,"area":null},{"id":"2207.12783","title":"Equivariant and Invariant Grounding for Video Question Answering","created":"2022-07-26","cited_by_count":22,"area":null},{"id":"2111.12527","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","created":"2021-11-24","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":"2312.12429","title":"The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and Benchmark","created":"2023-12-19","cited_by_count":21,"area":null},{"id":"2403.10261","title":"Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection","created":"2024-03-15","cited_by_count":21,"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":"2206.06931","title":"Stand-Alone Inter-Frame Attention in Video Models","created":"2022-06-14","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":"2104.08506","title":"Visually Guided Sound Source Separation and Localization using Self-Supervised Motion Representations","created":"2021-04-17","cited_by_count":18,"area":null},{"id":"2109.07701","title":"SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving","created":"2021-09-16","cited_by_count":18,"area":null},{"id":"2109.14834","title":"IntentVizor: Towards Generic Query Guided Interactive Video Summarization","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2109.13227","title":"TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device","created":"2021-09-27","cited_by_count":17,"area":null},{"id":"2106.10506","title":"Exploring Visual Context for Weakly Supervised Person Search","created":"2021-06-19","cited_by_count":16,"area":null},{"id":"2107.10771","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","created":"2021-07-22","cited_by_count":16,"area":null},{"id":"2109.13499","title":"Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning","created":"2021-09-28","cited_by_count":16,"area":null},{"id":"2111.14673","title":"3D Compositional Zero-shot Learning with DeCompositional Consensus","created":"2021-11-29","cited_by_count":16,"area":null},{"id":"2103.03655","title":"Foundations of Population-Based SHM, Part IV: The Geometry of Spaces of Structures and their Feature Spaces","created":"2021-03-05","cited_by_count":15,"area":null},{"id":"2109.12946","title":"Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks","created":"2021-09-27","cited_by_count":15,"area":null},{"id":"2111.01673","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","created":"2021-11-02","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":"2404.04565","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","created":"2024-04-06","cited_by_count":15,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2312.06829","title":"Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning","created":"2023-12-11","cited_by_count":14,"area":null},{"id":"2405.19917","title":"Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition","created":"2024-05-30","cited_by_count":14,"area":"distill"},{"id":"2105.12085","title":"DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning","created":"2021-05-25","cited_by_count":13,"area":null},{"id":"2202.13402","title":"Concept Graph Neural Networks for Surgical Video Understanding","created":"2022-02-27","cited_by_count":13,"area":null},{"id":"2302.08672","title":"Multimodal Subtask Graph Generation from Instructional Videos","created":"2023-02-17","cited_by_count":13,"area":null},{"id":"2309.14339","title":"Chop & Learn: Recognizing and Generating Object-State Compositions","created":"2023-09-25","cited_by_count":13,"area":null},{"id":"2311.03550","title":"United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos","created":"2023-11-06","cited_by_count":13,"area":null},{"id":"2401.08086","title":"Spatial-Semantic Collaborative Cropping for User Generated Content","created":"2024-01-16","cited_by_count":13,"area":null},{"id":"2104.14236","title":"Learning Multi-Attention Context Graph for Group-Based Re-Identification","created":"2021-04-29","cited_by_count":12,"area":null},{"id":"2108.08633","title":"Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2110.00698","title":"Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance","created":"2021-10-02","cited_by_count":12,"area":null},{"id":"2204.09303","title":"Attention in Attention: Modeling Context Correlation for Efficient Video Classification","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2305.18797","title":"Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic Space","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2104.01198","title":"Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories","created":"2021-04-02","cited_by_count":11,"area":null},{"id":"2110.14381","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2207.03656","title":"Video Dialog as Conversation about Objects Living in Space-Time","created":"2022-07-08","cited_by_count":11,"area":null},{"id":"2212.06795","title":"GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2104.00646","title":"Motion Guided Attention Fusion to Recognize Interactions from Videos","created":"2021-04-01","cited_by_count":10,"area":null},{"id":"2105.12419","title":"Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge","created":"2021-05-26","cited_by_count":10,"area":null},{"id":"2208.09424","title":"Hierarchical Compositional Representations for Few-shot Action Recognition","created":"2022-08-19","cited_by_count":10,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2106.13201","title":"DROID: Driver-centric Risk Object Identification","created":"2021-06-24","cited_by_count":9,"area":null},{"id":"2107.03824","title":"Instance-Level Relative Saliency Ranking with Graph Reasoning","created":"2021-07-08","cited_by_count":9,"area":null},{"id":"2202.12116","title":"Motion-driven Visual Tempo Learning for Video-based Action Recognition","created":"2022-02-24","cited_by_count":9,"area":null}],"next_cursor":"100"}