{"total":39,"rows":[{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112,"area":null},{"id":"2403.05234","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","created":"2024-03-08","cited_by_count":48,"area":null},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"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":"2412.14719","title":"Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition","created":"2024-12-19","cited_by_count":22,"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":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"id":"2106.15827","title":"When Video Classification Meets Incremental Classes","created":"2021-06-30","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":"2403.01560","title":"XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition","created":"2024-03-03","cited_by_count":15,"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":"2507.21977","title":"Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition","created":"2025-07-29","cited_by_count":11,"area":null},{"id":"2212.11115","title":"What Makes for Good Tokenizers in Vision Transformer?","created":"2022-12-21","cited_by_count":9,"area":null},{"id":"2407.10860","title":"Human-Centric Transformer for Domain Adaptive Action Recognition","created":"2024-07-15","cited_by_count":8,"area":null},{"id":"2406.00639","title":"An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2207.05526","title":"Long-term Leap Attention, Short-term Periodic Shift for Video Classification","created":"2022-07-12","cited_by_count":5,"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":"2206.11459","title":"Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline","created":"2022-06-23","cited_by_count":2,"area":null},{"id":"2503.23266","title":"OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition","created":"2025-03-30","cited_by_count":2,"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":"2107.12618","title":"Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021","created":"2021-07-27","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":"2405.08344","title":"No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2502.12415","title":"Gaseous Object Detection","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2509.21261","title":"Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.10060","title":"Multivariate Gaussian Representation Learning for Medical Action Evaluation","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2606.16742","title":"Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detection","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2305.09539","title":"Learning Higher-order Object Interactions for Keypoint-based Video Understanding","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2305.18310","title":"Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark","created":"2023-05-17","cited_by_count":0,"area":null},{"id":"2401.13414","title":"GTAutoAct: An Automatic Datasets Generation Framework Based on Game Engine Redevelopment for Action Recognition","created":"2024-01-24","cited_by_count":0,"area":null},{"id":"2407.16514","title":"Is 3D Convolution with 5D Tensors Really Necessary for Video Analysis?","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2503.00796","title":"An Efficient 3D Convolutional Neural Network with Channel-wise, Spatial-grouped, and Temporal Convolutions","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2506.08612","title":"Data-Efficient Challenges in Visual Inductive Priors: A Retrospective","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2604.15718","title":"NeuroLip: An Event-driven Spatiotemporal Learning Framework for Cross-Scene Lip-Motion-based Visual Speaker Recognition","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.21011","title":"Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.17133","title":"CAM-VFD: Cross-Attention Multimodal Video Forgery Detection","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.17437","title":"Spatio-Temporal Fusion Model for Standard View Classification of Echocardiographic Videos","created":"2026-06-16","cited_by_count":0,"area":null}],"next_cursor":null}