{"total":151,"rows":[{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091,"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":"2211.01367","title":"Two-Stream Network for Sign Language Recognition and Translation","created":"2022-11-02","cited_by_count":123,"area":null},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112,"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":"2107.10161","title":"Evidential Deep Learning for Open Set Action Recognition","created":"2021-07-21","cited_by_count":96,"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":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","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":"2110.06510","title":"The Dawn of Quantum Natural Language Processing","created":"2021-10-13","cited_by_count":61,"area":null},{"id":"2111.12374","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","created":"2021-11-24","cited_by_count":39,"area":null},{"id":"2211.15393","title":"Video Test-Time Adaptation for Action Recognition","created":"2022-11-24","cited_by_count":35,"area":null},{"id":"2507.00583","title":"AI-Generated Video Detection via Perceptual Straightening","created":"2025-07-01","cited_by_count":34,"area":null},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32,"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":"2211.11236","title":"Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization","created":"2022-11-21","cited_by_count":29,"area":null},{"id":"2110.01823","title":"Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations","created":"2021-10-05","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":"2106.14447","title":"Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection","created":"2021-06-28","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":"2111.13241","title":"Learning from Temporal Gradient for Semi-supervised Action Recognition","created":"2021-11-25","cited_by_count":26,"area":null},{"id":"2108.04536","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","created":"2021-08-10","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":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","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":"2201.04029","title":"Motion-Focused Contrastive Learning of Video Representations","created":"2022-01-11","cited_by_count":23,"area":null},{"id":"2103.16565","title":"Learning Representational Invariances for Data-Efficient Action Recognition","created":"2021-03-30","cited_by_count":22,"area":null},{"id":"2110.09075","title":"Boosting the Transferability of Video Adversarial Examples via Temporal Translation","created":"2021-10-18","cited_by_count":21,"area":null},{"id":"2205.13349","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","created":"2022-05-26","cited_by_count":21,"area":null},{"id":"2303.11917","title":"Efficient Decision-based Black-box Patch Attacks on Video Recognition","created":"2023-03-21","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":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","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":"2304.00553","title":"From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding","created":"2023-04-02","cited_by_count":19,"area":null},{"id":"2101.03049","title":"InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation","created":"2021-01-08","cited_by_count":18,"area":null},{"id":"2203.09694","title":"Group Contextualization for Video Recognition","created":"2022-03-18","cited_by_count":18,"area":null},{"id":"2401.00416","title":"SVFAP: Self-supervised Video Facial Affect Perceiver","created":"2023-12-31","cited_by_count":18,"area":null},{"id":"2209.01425","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","created":"2022-09-03","cited_by_count":17,"area":null},{"id":"2311.02538","title":"Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols","created":"2023-11-05","cited_by_count":17,"area":null},{"id":"2110.00529","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","created":"2021-10-01","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":"2105.14158","title":"SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation","created":"2021-05-29","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":"2206.08016","title":"Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches","created":"2022-06-16","cited_by_count":15,"area":null},{"id":"2207.13259","title":"Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition","created":"2022-07-27","cited_by_count":15,"area":null},{"id":"2301.07944","title":"Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition","created":"2023-01-19","cited_by_count":15,"area":null},{"id":"2304.08210","title":"ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding","created":"2023-04-17","cited_by_count":14,"area":null},{"id":"2107.13155","title":"Improving Video Instance Segmentation via Temporal Pyramid Routing","created":"2021-07-28","cited_by_count":13,"area":null},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","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":"2210.09138","title":"An Open-source Benchmark of Deep Learning Models for Audio-visual Apparent and Self-reported Personality Recognition","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2303.11003","title":"Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization","created":"2023-03-20","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":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"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":"2208.06105","title":"Motion Sensitive Contrastive Learning for Self-supervised Video Representation","created":"2022-08-12","cited_by_count":11,"area":null},{"id":"2111.15266","title":"Two-stage Temporal Modelling Framework for Video-based Depression Recognition using Graph Representation","created":"2021-11-30","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},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"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},{"id":"2311.10366","title":"Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models","created":"2023-11-17","cited_by_count":9,"area":null},{"id":"2501.08415","title":"Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics","created":"2025-01-14","cited_by_count":9,"area":null},{"id":"2201.08625","title":"VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2022-01-21","cited_by_count":8,"area":null},{"id":"2203.01933","title":"Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations","created":"2022-03-02","cited_by_count":8,"area":null},{"id":"2404.09951","title":"Unifying Global and Local Scene Entities Modelling for Precise Action Spotting","created":"2024-04-15","cited_by_count":8,"area":null},{"id":"2108.06647","title":"Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning","created":"2021-08-15","cited_by_count":7,"area":null},{"id":"2207.14513","title":"Uncertainty-Driven Action Quality Assessment","created":"2022-07-29","cited_by_count":7,"area":null},{"id":"2309.12067","title":"Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives","created":"2023-09-21","cited_by_count":7,"area":null},{"id":"2410.01304","title":"Deep learning for action spotting in association football videos","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2203.16244","title":"CycDA: Unsupervised Cycle Domain Adaptation from Image to Video","created":"2022-03-30","cited_by_count":6,"area":null},{"id":"2312.13746","title":"Video Recognition in Portrait Mode","created":"2023-12-21","cited_by_count":6,"area":null},{"id":"2401.11790","title":"Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Review","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2301.02307","title":"What You Say Is What You Show: Visual Narration Detection in Instructional Videos","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2401.11847","title":"SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning","created":"2024-01-22","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2110.05904","title":"Video Is Graph: Structured Graph Module for Video Action Recognition","created":"2021-10-12","cited_by_count":4,"area":null},{"id":"2203.10183","title":"RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression","created":"2022-03-18","cited_by_count":4,"area":null},{"id":"2206.10491","title":"Bi-Calibration Networks for Weakly-Supervised Video Representation Learning","created":"2022-06-21","cited_by_count":4,"area":null},{"id":"2302.02136","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","created":"2023-02-04","cited_by_count":4,"area":null},{"id":"2305.19688","title":"VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2309.11718","title":"CPR-Coach: Recognizing Composite Error Actions based on Single-class Training","created":"2023-09-21","cited_by_count":4,"area":null},{"id":"2407.16341","title":"Motion Capture from Inertial and Vision Sensors","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2409.17091","title":"Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2410.12018","title":"LocoMotion: Learning Motion-Focused Video-Language Representations","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2502.11897","title":"DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2602.18043","title":"Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2104.00179","title":"Selective Feature Compression for Efficient Activity Recognition Inference","created":"2021-04-01","cited_by_count":3,"area":null},{"id":"2104.12106","title":"Temp-Frustum Net: 3D Object Detection with Temporal Fusion","created":"2021-04-25","cited_by_count":3,"area":null},{"id":"2206.09082","title":"Context-aware Proposal Network for Temporal Action Detection","created":"2022-06-18","cited_by_count":3,"area":null},{"id":"2208.12257","title":"Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2209.11870","title":"Leveraging Self-Supervised Training for Unintentional Action Recognition","created":"2022-09-23","cited_by_count":3,"area":null},{"id":"2303.15467","title":"Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition","created":"2023-03-25","cited_by_count":3,"area":null},{"id":"2304.14601","title":"Improve Video Representation with Temporal Adversarial Augmentation","created":"2023-04-28","cited_by_count":3,"area":null},{"id":"2306.02548","title":"Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos","created":"2023-06-05","cited_by_count":3,"area":null},{"id":"2308.12447","title":"MOFO: MOtion FOcused Self-Supervision for Video Understanding","created":"2023-08-23","cited_by_count":3,"area":null},{"id":"2404.01643","title":"A Closer Look at Spatial-Slice Features Learning for COVID-19 Detection","created":"2024-04-02","cited_by_count":3,"area":null},{"id":"2408.12099","title":"Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computing","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2411.15284","title":"When Spatial meets Temporal in Action Recognition","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2104.06813","title":"Global Information Guided Video Anomaly Detection","created":"2021-04-14","cited_by_count":2,"area":null}],"next_cursor":"100"}