{"total":44,"rows":[{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77,"area":null},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68,"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":"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":"2105.05165","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","created":"2021-05-11","cited_by_count":36,"area":null},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35,"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":"2110.09075","title":"Boosting the Transferability of Video Adversarial Examples via Temporal Translation","created":"2021-10-18","cited_by_count":21,"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":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2207.10388","title":"NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition","created":"2022-07-21","cited_by_count":15,"area":null},{"id":"2211.11210","title":"Contrastive Masked Autoencoders for Self-Supervised Video Hashing","created":"2022-11-21","cited_by_count":13,"area":null},{"id":"2106.08570","title":"Anomaly Detection in Video Sequences: A Benchmark and Computational Model","created":"2021-06-16","cited_by_count":10,"area":null},{"id":"2305.15762","title":"Dynamic Enhancement Network for Partial Multi-modality Person Re-identification","created":"2023-05-25","cited_by_count":10,"area":null},{"id":"2207.10379","title":"Temporal Saliency Query Network for Efficient Video Recognition","created":"2022-07-21","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":"2207.11805","title":"Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions","created":"2022-07-24","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":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2303.13635","title":"Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training","created":"2023-03-22","cited_by_count":5,"area":null},{"id":"2203.06555","title":"Label-only Model Inversion Attack: The Attack that Requires the Least Information","created":"2022-03-13","cited_by_count":4,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2207.09927","title":"ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network","created":"2022-07-20","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":"2308.09322","title":"Audio-Visual Glance Network for Efficient Video Recognition","created":"2023-08-18","cited_by_count":4,"area":null},{"id":"2310.08009","title":"Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2111.11653","title":"Modeling Temporal Concept Receptive Field Dynamically for Untrimmed Video Analysis","created":"2021-11-23","cited_by_count":3,"area":null},{"id":"2304.10316","title":"Search-Map-Search: A Frame Selection Paradigm for Action Recognition","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2310.18926","title":"CHAIN: Exploring Global-Local Spatio-Temporal Information for Improved Self-Supervised Video Hashing","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2504.03587","title":"AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2104.09760","title":"HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2203.04301","title":"Live Laparoscopic Video Retrieval with Compressed Uncertainty","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2101.07855","title":"Machine-Generated Hierarchical Structure of Human Activities to Reveal How Machines Think","created":"2021-01-19","cited_by_count":1,"area":null},{"id":"2308.12163","title":"NPF-200: A Multi-Modal Eye Fixation Dataset and Method for Non-Photorealistic Videos","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2309.00347","title":"Towards Contrastive Learning in Music Video Domain","created":"2023-09-01","cited_by_count":1,"area":null},{"id":"2511.12162","title":"Codebook-Centric Deep Hashing: End-to-End Joint Learning of Semantic Hash Centers and Neural Hash Function","created":"2025-11-15","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":"2106.03283","title":"Video Imprint","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2111.06532","title":"Nonlinear Tensor Ring Network","created":"2021-11-12","cited_by_count":0,"area":null},{"id":"2112.05379","title":"Cross-Modal Transferable Adversarial Attacks from Images to Videos","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2305.13704","title":"FlowChroma -- A Deep Recurrent Neural Network for Video Colorization","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2508.16739","title":"Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detection","created":"2025-08-22","cited_by_count":0,"area":null}],"next_cursor":null}