{"total":38,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328,"area":null},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2203.02149","title":"HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging","created":"2022-03-04","cited_by_count":66,"area":null},{"id":"2112.12782","title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","created":"2021-12-23","cited_by_count":55,"area":null},{"id":"2203.13349","title":"Occluded Human Mesh Recovery","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2305.13563","title":"Efficient Multi-Scale Attention Module with Cross-Spatial Learning","created":"2023-05-23","cited_by_count":41,"area":null},{"id":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28,"area":null},{"id":"2301.01208","title":"Mask Matching Transformer for Few-Shot Segmentation","created":"2022-12-05","cited_by_count":22,"area":null},{"id":"2407.08634","title":"RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2309.13646","title":"ILNet: Low-level Matters for Salient Infrared Small Target Detection","created":"2023-09-24","cited_by_count":17,"area":null},{"id":"2206.08778","title":"CTooth: A Fully Annotated 3D Dataset and Benchmark for Tooth Volume Segmentation on Cone Beam Computed Tomography Images","created":"2022-06-17","cited_by_count":11,"area":null},{"id":"2208.00453","title":"One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement","created":"2022-07-31","cited_by_count":8,"area":null},{"id":"2304.05152","title":"PP-MobileSeg: Explore the Fast and Accurate Semantic Segmentation Model on Mobile Devices","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2401.07579","title":"PMFSNet: Polarized Multi-scale Feature Self-attention Network For Lightweight Medical Image Segmentation","created":"2024-01-15","cited_by_count":6,"area":null},{"id":"2309.08919","title":"Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution","created":"2023-09-16","cited_by_count":5,"area":null},{"id":"2108.11695","title":"PAENet: A Progressive Attention-Enhanced Network for 3D to 2D Retinal Vessel Segmentation","created":"2021-08-26","cited_by_count":4,"area":null},{"id":"2403.02689","title":"Deep Common Feature Mining for Efficient Video Semantic Segmentation","created":"2024-03-05","cited_by_count":4,"area":null},{"id":"2404.14135","title":"Text in the Dark: Extremely Low-Light Text Image Enhancement","created":"2024-04-22","cited_by_count":3,"area":null},{"id":"2411.18855","title":"Improving Accuracy and Generalization for Efficient Visual Tracking","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2305.10126","title":"Fusion-S2iGan: An Efficient and Effective Single-Stage Framework for Speech-to-Image Generation","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2307.06737","title":"Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data","created":"2023-07-13","cited_by_count":2,"area":null},{"id":"2404.04155","title":"MarsSeg: Mars Surface Semantic Segmentation with Multi-level Extractor and Connector","created":"2024-04-05","cited_by_count":2,"area":null},{"id":"2310.12031","title":"SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environment","created":"2023-10-18","cited_by_count":1,"area":null},{"id":"2311.17475","title":"CLiSA: A Hierarchical Hybrid Transformer Model using Orthogonal Cross Attention for Satellite Image Cloud Segmentation","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2504.06357","title":"From Broadcast to Minimap: Achieving State-of-the-Art SoccerNet Game State Reconstruction","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2203.15228","title":"SHOP: A Deep Learning Based Pipeline for near Real-Time Detection of Small Handheld Objects Present in Blurry Video","created":"2022-03-29","cited_by_count":0,"area":null},{"id":"2211.15467","title":"Progressively Dual Prior Guided Few-shot Semantic Segmentation","created":"2022-11-20","cited_by_count":0,"area":null},{"id":"2304.12001","title":"Diabetic Foot Ulcer Grand Challenge 2022 Summary","created":"2023-04-24","cited_by_count":0,"area":null},{"id":"2311.16490","title":"High-resolution Multi-spectral Image Guided DEM Super-resolution using Sinkhorn Regularized Adversarial Network","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2404.14709","title":"SC-HVPPNet: Spatial and Channel Hybrid-Attention Video Post-Processing Network with CNN and Transformer","created":"2024-04-23","cited_by_count":0,"area":null},{"id":"2409.14198","title":"A Sinkhorn Regularized Adversarial Network for Image Guided DEM Super-resolution using Frequency Selective Hybrid Graph Transformer","created":"2024-09-21","cited_by_count":0,"area":null},{"id":"2411.08488","title":"UNSCT-HRNet: Modeling Anatomical Uncertainty for Landmark Detection in Total Hip Arthroplasty","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2511.11032","title":"MPCGNet: A Multiscale Feature Extraction and Progressive Feature Aggregation Network Using Coupling Gates for Polyp Segmentation","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2601.07310","title":"Revisiting the Ordering of Channel and Spatial Attention: A Comprehensive Study on Sequential and Parallel Designs","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2603.22323","title":"A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.23215","title":"PoseDriver: A Unified Approach to Multi-Category Skeleton Detection for Autonomous Driving","created":"2026-03-24","cited_by_count":0,"area":null}],"next_cursor":null}