{"list":"other","total":52,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"id":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1903.07256","title":"Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection","created":"2019-03-18","cited_by_count":171},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138},{"id":"1811.12432","title":"AdaFrame: Adaptive Frame Selection for Fast Video Recognition","created":"2018-11-29","cited_by_count":134},{"id":"2302.05160","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","created":"2023-02-10","cited_by_count":90},{"id":"2211.15098","title":"MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection","created":"2022-11-28","cited_by_count":89},{"id":"2007.15796","title":"AR-Net: Adaptive Frame Resolution for Efficient Action Recognition","created":"2020-07-31","cited_by_count":88},{"id":"2011.12077","title":"CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection","created":"2020-11-24","cited_by_count":79},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67},{"id":"2211.10946","title":"Normalizing Flows for Human Pose Anomaly Detection","created":"2022-11-20","cited_by_count":60},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2604.17898","title":"ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval","created":"2026-04-20","cited_by_count":41},{"id":"2408.01343","title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","created":"2024-08-02","cited_by_count":39},{"id":"2509.12662","title":"Chat-Driven Text Generation and Interaction for Person Retrieval","created":"2025-09-16","cited_by_count":34},{"id":"2512.02792","title":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","created":"2025-12-02","cited_by_count":32},{"id":"2509.12040","title":"Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing","created":"2025-09-15","cited_by_count":31},{"id":"2411.16805","title":"Human Motion Instruction Tuning","created":"2024-11-25","cited_by_count":29},{"id":"2604.18051","title":"INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval","created":"2026-04-20","cited_by_count":26},{"id":"2604.18037","title":"HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval","created":"2026-04-20","cited_by_count":24},{"id":"2601.12768","title":"Delving Deeper: Hierarchical Visual Perception for Robust Video-Text Retrieval","created":"2026-01-19","cited_by_count":23},{"id":"2604.19386","title":"Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval","created":"2026-04-21","cited_by_count":18},{"id":"2508.10523","title":"Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies","created":"2025-08-14","cited_by_count":17},{"id":"2604.20358","title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","created":"2026-04-22","cited_by_count":17},{"id":"2511.07923","title":"Exploring the Underwater World Segmentation without Extra Training","created":"2025-11-11","cited_by_count":16},{"id":"2412.17629","title":"Learn from Global Correlations: Enhancing Evolutionary Algorithm via Spectral GNN","created":"2024-12-23","cited_by_count":15},{"id":"2510.15398","title":"MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment","created":"2025-10-17","cited_by_count":15},{"id":"2601.18625","title":"CONQUER: Context-Aware Representation with Query Enhancement for Text-Based Person Search","created":"2026-01-26","cited_by_count":15},{"id":"2502.18180","title":"ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis","created":"2025-02-25","cited_by_count":14},{"id":"2601.16155","title":"HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval","created":"2026-01-22","cited_by_count":14},{"id":"2405.15365","title":"U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation","created":"2024-05-24","cited_by_count":13},{"id":"2507.01439","title":"TurboReg: TurboClique for Robust and Efficient Point Cloud Registration","created":"2025-07-02","cited_by_count":13},{"id":"2603.19929","title":"RAM: Recover Any 3D Human Motion in-the-Wild","created":"2026-03-20","cited_by_count":12},{"id":"2412.00091","title":"Graph Canvas for Controllable 3D Scene Generation","created":"2024-11-27","cited_by_count":11},{"id":"2601.00796","title":"AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction","created":"2026-01-02","cited_by_count":9},{"id":"2507.09081","title":"From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion","created":"2025-07-11","cited_by_count":8},{"id":"2510.22140","title":"STG-Avatar: Animatable Human Avatars via Spacetime Gaussian","created":"2025-10-25","cited_by_count":8},{"id":"2410.03161","title":"Adaptive Masking Enhances Visual Grounding","created":"2024-10-04","cited_by_count":6},{"id":"2602.21967","title":"Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments","created":"2026-02-25","cited_by_count":3}],"next_cursor":null}