{"total":106,"rows":[{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"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":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100,"area":"mllm"},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"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":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58,"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":"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":"2303.07863","title":"You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos","created":"2023-03-14","cited_by_count":41,"area":null},{"id":"2104.00862","title":"Self-supervised Video Representation Learning by Context and Motion Decoupling","created":"2021-04-02","cited_by_count":34,"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":"2308.12962","title":"Motion-Guided Masking for Spatiotemporal Representation Learning","created":"2023-08-24","cited_by_count":30,"area":null},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28,"area":null},{"id":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2309.12867","title":"Accurate and Fast Compressed Video Captioning","created":"2023-09-22","cited_by_count":22,"area":null},{"id":"2209.01578","title":"Spatial-Temporal Transformer for Video Snapshot Compressive Imaging","created":"2022-09-04","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":"2304.08451","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","created":"2023-04-17","cited_by_count":20,"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":"2211.16421","title":"RGB no more: Minimally-decoded JPEG Vision Transformers","created":"2022-11-29","cited_by_count":18,"area":null},{"id":"2202.02813","title":"A Coding Framework and Benchmark towards Low-Bitrate Video Understanding","created":"2022-02-06","cited_by_count":17,"area":null},{"id":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2203.15336","title":"End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2203.16795","title":"Deformable Video Transformer","created":"2022-03-31","cited_by_count":15,"area":null},{"id":"2102.13644","title":"Surgical Visual Domain Adaptation: Results from the MICCAI 2020 SurgVisDom Challenge","created":"2021-02-26","cited_by_count":14,"area":null},{"id":"2103.04677","title":"Behavior-Driven Synthesis of Human Dynamics","created":"2021-03-08","cited_by_count":14,"area":null},{"id":"2203.03014","title":"Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2210.04889","title":"Turbo Training with Token Dropout","created":"2022-10-10","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":"2105.07085","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","created":"2021-05-14","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":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","cited_by_count":13,"area":null},{"id":"2402.03019","title":"Taylor Videos for Action Recognition","created":"2024-02-05","cited_by_count":12,"area":null},{"id":"2406.04765","title":"SMC++: Masked Learning of Unsupervised Video Semantic Compression","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2104.06699","title":"Change Detection in Synthetic Aperture Radar Images Using a Dual-Domain Network","created":"2021-04-14","cited_by_count":11,"area":null},{"id":"2111.10800","title":"FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform","created":"2021-11-21","cited_by_count":11,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2107.12192","title":"Accelerating Video Object Segmentation with Compressed Video","created":"2021-07-26","cited_by_count":10,"area":null},{"id":"2201.10394","title":"Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition","created":"2022-01-25","cited_by_count":10,"area":null},{"id":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2101.00317","title":"Identity-aware Facial Expression Recognition in Compressed Video","created":"2021-01-01","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":"2311.14294","title":"Decouple Content and Motion for Conditional Image-to-Video Generation","created":"2023-11-24","cited_by_count":9,"area":null},{"id":"2210.02995","title":"Compressed Vision for Efficient Video Understanding","created":"2022-10-06","cited_by_count":8,"area":null},{"id":"2303.07224","title":"Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos","created":"2023-03-13","cited_by_count":8,"area":null},{"id":"2602.16412","title":"ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding","created":"2026-02-18","cited_by_count":8,"area":"mllm"},{"id":"2201.10162","title":"Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks","created":"2022-01-25","cited_by_count":7,"area":null},{"id":"2308.01568","title":"MVFlow: Deep Optical Flow Estimation of Compressed Videos with Motion Vector Prior","created":"2023-08-03","cited_by_count":7,"area":null},{"id":"2407.12622","title":"Rethinking the Architecture Design for Efficient Generic Event Boundary Detection","created":"2024-07-17","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":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"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":"2204.02081","title":"Real-time Online Multi-Object Tracking in Compressed Domain","created":"2022-04-05","cited_by_count":6,"area":null},{"id":"2207.00588","title":"CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics","created":"2022-07-02","cited_by_count":6,"area":null},{"id":"2304.06896","title":"Machine Perception-Driven Image Compression: A Layered Generative Approach","created":"2023-04-14","cited_by_count":6,"area":null},{"id":"2404.04848","title":"Task-Aware Encoder Control for Deep Video Compression","created":"2024-04-07","cited_by_count":6,"area":null},{"id":"2103.14529","title":"Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation","created":"2021-03-25","cited_by_count":5,"area":null},{"id":"2107.05122","title":"Interpretable Deep Feature Propagation for Early Action Recognition","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2110.08814","title":"TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding","created":"2021-10-17","cited_by_count":5,"area":null},{"id":"2112.00891","title":"Event Neural Networks","created":"2021-12-02","cited_by_count":5,"area":null},{"id":"2407.12067","title":"MaskVD: Region Masking for Efficient Video Object Detection","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2104.07135","title":"Adaptive Intermediate Representations for Video Understanding","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2209.04780","title":"MAiVAR: Multimodal Audio-Image and Video Action Recognizer","created":"2022-09-11","cited_by_count":3,"area":null},{"id":"2309.15431","title":"Local Compressed Video Stream Learning for Generic Event Boundary Detection","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2311.10788","title":"Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors","created":"2023-11-17","cited_by_count":3,"area":null},{"id":"2603.24539","title":"CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2103.03465","title":"Unsupervised Motion Representation Enhanced Network for Action Recognition","created":"2021-03-05","cited_by_count":2,"area":null},{"id":"2107.07305","title":"Training for temporal sparsity in deep neural networks, application in video processing","created":"2021-07-15","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":"2503.13724","title":"Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2509.13255","title":"ResidualViT for Efficient Temporally Dense Video Encoding","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2509.17084","title":"MoCLIP-Lite: Efficient Video Recognition by Fusing CLIP with Motion Vectors","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2509.18388","title":"MVP: Motion Vector Propagation for Zero-Shot Video Object Detection","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2602.14705","title":"It's a Matter of Time: Three Lessons on Long-Term Motion for Perception","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2101.00359","title":"Video Captioning in Compressed Video","created":"2021-01-02","cited_by_count":1,"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":"2109.02137","title":"Efficient Action Recognition Using Confidence Distillation","created":"2021-09-05","cited_by_count":1,"area":null},{"id":"2205.03569","title":"Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement","created":"2022-05-07","cited_by_count":1,"area":null},{"id":"2312.06598","title":"Early Action Recognition with Action Prototypes","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2407.02713","title":"Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation","created":"2024-07-02","cited_by_count":1,"area":"distill"},{"id":"2412.01267","title":"EdgeOAR: Real-time Online Action Recognition On Edge Devices","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2508.05001","title":"CRAM: Large-scale Video Continual Learning with Bootstrapped Compression","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2604.03640","title":"ComPrivDet: Efficient Privacy Object Detection in Compressed Domains Through Inference Reuse","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2606.31004","title":"Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2610.04318","title":"Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency","created":"2026-10-03","cited_by_count":1,"area":"lr"},{"id":"2107.12744","title":"Real-Time Activity Recognition and Intention Recognition Using a Vision-based Embedded System","created":"2021-07-27","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":"2209.14757","title":"Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain","created":"2022-09-29","cited_by_count":0,"area":null},{"id":"2303.00138","title":"Texture-Based Input Feature Selection for Action Recognition","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2403.10558","title":"Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2502.07277","title":"Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2503.08819","title":"Residual Learning and Filtering Networks for End-to-End Lossless Video Compression","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2509.18473","title":"MoCrop: Training Free Motion Guided Cropping for Efficient Video Action Recognition","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.10986","title":"Mixup Helps Understanding Multimodal Video Better","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2603.26835","title":"ANVIL: Accelerator-Native Video Interpolation via Codec Motion Vector Priors","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.03351","title":"VLMaxxing through FrameMogging Training-Free Anti-Recomputation for Video Vision-Language Models","created":"2026-05-05","cited_by_count":0,"area":"mllm"},{"id":"2605.08158","title":"HY-Himmel Technical Report: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding","created":"2026-05-04","cited_by_count":0,"area":"mllm"},{"id":"2608.06691","title":"CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":"100"}