{"total":115,"rows":[{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"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":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153,"area":"lr"},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"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":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"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":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77,"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":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59,"area":null},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59,"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":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48,"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":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41,"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":"2306.11248","title":"Dynamic Perceiver for Efficient Visual Recognition","created":"2023-06-20","cited_by_count":33,"area":null},{"id":"2111.11631","title":"Self-Regulated Learning for Egocentric Video Activity Anticipation","created":"2021-11-23","cited_by_count":32,"area":null},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","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":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28,"area":null},{"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":"2308.04549","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","created":"2023-08-08","cited_by_count":24,"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":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2106.15827","title":"When Video Classification Meets Incremental Classes","created":"2021-06-30","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":"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":"2112.10977","title":"ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization","created":"2021-12-21","cited_by_count":17,"area":null},{"id":"2210.05370","title":"DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks","created":"2022-10-10","cited_by_count":17,"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":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","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":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2303.13505","title":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","created":"2023-03-23","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2310.01324","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","created":"2023-10-02","cited_by_count":14,"area":null},{"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":"2204.04387","title":"Dual-Stage Approach Toward Hyperspectral Image Super-Resolution","created":"2022-04-09","cited_by_count":13,"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":"2110.14381","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2303.17228","title":"Streaming Video Model","created":"2023-03-30","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":"2303.15742","title":"System-status-aware Adaptive Network for Online Streaming Video Understanding","created":"2023-03-28","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":"2102.06448","title":"The MSR-Video to Text Dataset with Clean Annotations","created":"2021-02-12","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":"2209.12797","title":"Rethinking Resolution in the Context of Efficient Video Recognition","created":"2022-09-26","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":"2308.04770","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","created":"2023-08-09","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":"2411.13626","title":"Principles of Visual Tokens for Efficient Video Understanding","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2108.04212","title":"AutoVideo: An Automated Video Action Recognition System","created":"2021-08-09","cited_by_count":6,"area":null},{"id":"2211.09992","title":"Look More but Care Less in Video Recognition","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","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":"2108.06458","title":"Cross-Modal Graph with Meta Concepts for Video Captioning","created":"2021-08-14","cited_by_count":4,"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":"2308.04834","title":"View while Moving: Efficient Video Recognition in Long-untrimmed Videos","created":"2023-08-09","cited_by_count":4,"area":null},{"id":"2309.04723","title":"Frequency-Aware Self-Supervised Long-Tailed Learning","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2501.07087","title":"Video Quality Assessment for Online Processing: From Spatial to Temporal Sampling","created":"2025-01-13","cited_by_count":4,"area":null},{"id":"2506.21080","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","created":"2025-06-26","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":"2204.05976","title":"Video Captioning: a comparative review of where we are and which could be the route","created":"2022-04-12","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":"2306.11341","title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2103.12278","title":"Learning Comprehensive Motion Representation for Action Recognition","created":"2021-03-23","cited_by_count":2,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2112.07338","title":"Temporal Transformer Networks with Self-Supervision for Action Recognition","created":"2021-12-14","cited_by_count":2,"area":null},{"id":"2201.06304","title":"Action Keypoint Network for Efficient Video Recognition","created":"2022-01-17","cited_by_count":2,"area":null},{"id":"2401.08609","title":"F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2104.13051","title":"Three-stream network for enriched Action Recognition","created":"2021-04-27","cited_by_count":1,"area":null},{"id":"2106.01088","title":"TSI: Temporal Saliency Integration for Video Action Recognition","created":"2021-06-02","cited_by_count":1,"area":null},{"id":"2106.11173","title":"TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification","created":"2021-06-21","cited_by_count":1,"area":null},{"id":"2109.02137","title":"Efficient Action Recognition Using Confidence Distillation","created":"2021-09-05","cited_by_count":1,"area":null},{"id":"2112.02523","title":"STSM: Spatio-Temporal Shift Module for Efficient Action Recognition","created":"2021-12-05","cited_by_count":1,"area":null},{"id":"2212.03384","title":"DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2306.03835","title":"Atrial Septal Defect Detection in Children Based on Ultrasound Video Using Multiple Instances Learning","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2308.13866","title":"Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds","created":"2023-08-26","cited_by_count":1,"area":null},{"id":"2409.05260","title":"Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space","created":"2024-09-09","cited_by_count":1,"area":null},{"id":"2412.01267","title":"EdgeOAR: Real-time Online Action Recognition On Edge Devices","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2104.10492","title":"Skimming and Scanning for Untrimmed Video Action Recognition","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2105.08665","title":"A multimodal deep learning framework for scalable content based visual media retrieval","created":"2021-05-18","cited_by_count":0,"area":null},{"id":"2106.15787","title":"Long-Short Temporal Modeling for Efficient Action Recognition","created":"2021-06-30","cited_by_count":0,"area":null},{"id":"2107.11813","title":"Adaptive Recursive Circle Framework for Fine-grained Action Recognition","created":"2021-07-25","cited_by_count":0,"area":null},{"id":"2109.02145","title":"Temporal Shift Reinforcement Learning","created":"2021-09-05","cited_by_count":0,"area":null},{"id":"2110.10348","title":"GTM: Gray Temporal Model for Video Recognition","created":"2021-10-20","cited_by_count":0,"area":null},{"id":"2110.11626","title":"Rethinking Generalization Performance of Surgical Phase Recognition with Expert-Generated Annotations","created":"2021-10-22","cited_by_count":0,"area":null},{"id":"2110.15574","title":"ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2202.08399","title":"Shift-Memory Network for Temporal Scene Segmentation","created":"2022-02-17","cited_by_count":0,"area":null},{"id":"2208.12940","title":"Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos","created":"2022-08-27","cited_by_count":0,"area":null}],"next_cursor":"100"}