{"total":223,"rows":[{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"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":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","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":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168,"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":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112,"area":null},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2107.03377","title":"Long Short-Term Transformer for Online Action Detection","created":"2021-07-07","cited_by_count":88,"area":null},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2203.09463","title":"FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos","created":"2022-03-17","cited_by_count":69,"area":null},{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","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":"2205.13713","title":"PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences","created":"2022-05-27","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":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"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":"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":"2304.04617","title":"VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views","created":"2023-04-10","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":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","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":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2305.17473","title":"A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2201.04029","title":"Motion-Focused Contrastive Learning of Video Representations","created":"2022-01-11","cited_by_count":23,"area":null},{"id":"2201.04388","title":"OCSampler: Compressing Videos to One Clip with Single-step Sampling","created":"2022-01-12","cited_by_count":23,"area":null},{"id":"2207.14698","title":"Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding","created":"2022-07-29","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":"2308.08885","title":"Event-Guided Procedure Planning from Instructional Videos with Text Supervision","created":"2023-08-17","cited_by_count":21,"area":null},{"id":"2109.00829","title":"SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos","created":"2021-09-02","cited_by_count":20,"area":null},{"id":"2203.16000","title":"StyleFool: Fooling Video Classification Systems via Style Transfer","created":"2022-03-30","cited_by_count":20,"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":"2207.12817","title":"Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluation","created":"2022-07-26","cited_by_count":19,"area":null},{"id":"2303.15270","title":"Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling","created":"2023-03-27","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":"2108.08363","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","created":"2021-08-18","cited_by_count":18,"area":null},{"id":"2209.13465","title":"AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition","created":"2022-09-27","cited_by_count":18,"area":null},{"id":"2307.06947","title":"Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition","created":"2023-07-13","cited_by_count":18,"area":null},{"id":"2101.01060","title":"Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming","created":"2021-01-04","cited_by_count":17,"area":null},{"id":"2105.12043","title":"Temporal Action Proposal Generation with Transformers","created":"2021-05-25","cited_by_count":17,"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":"2110.00529","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","created":"2021-10-01","cited_by_count":16,"area":null},{"id":"2303.10280","title":"Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances","created":"2023-03-17","cited_by_count":16,"area":null},{"id":"2204.03017","title":"Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency","created":"2022-04-06","cited_by_count":15,"area":null},{"id":"2311.13793","title":"Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception","created":"2023-11-23","cited_by_count":15,"area":null},{"id":"2205.09445","title":"Cross-Enhancement Transformer for Action Segmentation","created":"2022-05-19","cited_by_count":14,"area":null},{"id":"2211.06742","title":"Deep Unsupervised Key Frame Extraction for Efficient Video Classification","created":"2022-11-12","cited_by_count":14,"area":null},{"id":"2104.09371","title":"Non-linear Functional Modeling using Neural Networks","created":"2021-04-19","cited_by_count":13,"area":null},{"id":"2105.13033","title":"SSAN: Separable Self-Attention Network for Video Representation Learning","created":"2021-05-27","cited_by_count":13,"area":null},{"id":"2109.00953","title":"TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction","created":"2021-09-02","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":"2203.05928","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","created":"2022-03-11","cited_by_count":12,"area":null},{"id":"2307.08908","title":"What Can Simple Arithmetic Operations Do for Temporal Modeling?","created":"2023-07-18","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":"2201.12626","title":"Assessing Cross-dataset Generalization of Pedestrian Crossing Predictors","created":"2022-01-29","cited_by_count":11,"area":null},{"id":"2208.05251","title":"Consistency-based Self-supervised Learning for Temporal Anomaly Localization","created":"2022-08-10","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":"2304.06403","title":"Leveraging triplet loss for unsupervised action segmentation","created":"2023-04-13","cited_by_count":10,"area":null},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2106.00050","title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","created":"2021-05-31","cited_by_count":9,"area":null},{"id":"2210.14714","title":"TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction","created":"2022-10-26","cited_by_count":9,"area":null},{"id":"2211.09146","title":"A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition","created":"2022-11-16","cited_by_count":9,"area":null},{"id":"2412.11228","title":"Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition","created":"2024-12-15","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":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2104.05758","title":"Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2201.04027","title":"Representing Videos as Discriminative Sub-graphs for Action Recognition","created":"2022-01-11","cited_by_count":8,"area":null},{"id":"2103.11313","title":"PGT: A Progressive Method for Training Models on Long Videos","created":"2021-03-21","cited_by_count":7,"area":null},{"id":"2106.06736","title":"Multi-level Attention Fusion Network for Audio-visual Event Recognition","created":"2021-06-12","cited_by_count":7,"area":null},{"id":"2107.05202","title":"Delta Sampling R-BERT for limited data and low-light action recognition","created":"2021-07-12","cited_by_count":7,"area":null},{"id":"2201.04906","title":"Hand-Object Interaction Reasoning","created":"2022-01-13","cited_by_count":7,"area":null},{"id":"2206.09149","title":"Piecewise Linear Neural Networks and Deep Learning","created":"2022-06-18","cited_by_count":7,"area":null},{"id":"2208.03775","title":"Video-based Human Action Recognition using Deep Learning: A Review","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2211.08252","title":"Dynamic Temporal Filtering in Video Models","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2309.11569","title":"Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding","created":"2023-09-20","cited_by_count":7,"area":null},{"id":"2310.09744","title":"Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attacks","created":"2023-10-15","cited_by_count":7,"area":null},{"id":"2312.00826","title":"DEVIAS: Learning Disentangled Video Representations of Action and Scene","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2106.10137","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2201.04022","title":"Condensing a Sequence to One Informative Frame for Video Recognition","created":"2022-01-11","cited_by_count":6,"area":null},{"id":"2203.08942","title":"ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2311.17938","title":"Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations","created":"2023-11-28","cited_by_count":6,"area":null},{"id":"2403.16128","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","created":"2024-03-24","cited_by_count":6,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2101.00468","title":"Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models","created":"2021-01-02","cited_by_count":5,"area":null},{"id":"2101.00604","title":"Privacy-sensitive Objects Pixelation for Live Video Streaming","created":"2021-01-03","cited_by_count":5,"area":null},{"id":"2102.00565","title":"CyclingNet: Detecting cycling near misses from video streams in complex urban scenes with deep learning","created":"2021-01-31","cited_by_count":5,"area":null},{"id":"2102.05843","title":"Driving Style Representation in Convolutional Recurrent Neural Network Model of Driver Identification","created":"2021-02-11","cited_by_count":5,"area":null},{"id":"2111.13675","title":"Weakly-guided Self-supervised Pretraining for Temporal Activity Detection","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2203.04738","title":"Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences","created":"2022-03-07","cited_by_count":5,"area":null},{"id":"2207.12730","title":"P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos","created":"2022-07-26","cited_by_count":5,"area":null},{"id":"2209.14647","title":"Bounded Future MS-TCN++ for surgical gesture recognition","created":"2022-09-29","cited_by_count":5,"area":null},{"id":"2305.15551","title":"Malicious or Benign? Towards Effective Content Moderation for Children's Videos","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2402.13546","title":"LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2102.07355","title":"Win-Fail Action Recognition","created":"2021-02-15","cited_by_count":4,"area":null}],"next_cursor":"100"}