{"total":1410,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658,"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":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447,"area":null},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342,"area":null},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316,"area":null},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295,"area":null},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252,"area":null},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245,"area":null},{"id":"2204.07143","title":"Neighborhood Attention Transformer","created":"2022-04-14","cited_by_count":239,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2103.03024","title":"CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation","created":"2021-03-04","cited_by_count":227,"area":null},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224,"area":null},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220,"area":null},{"id":"2104.09367","title":"Contrastive Learning for Compact Single Image Dehazing","created":"2021-04-19","cited_by_count":219,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204,"area":null},{"id":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203,"area":null},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200,"area":null},{"id":"2209.15616","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197,"area":null},{"id":"2211.14830","title":"Medical Image Segmentation Review: The success of U-Net","created":"2022-11-27","cited_by_count":191,"area":null},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187,"area":null},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180,"area":null},{"id":"2206.02146","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","created":"2022-06-05","cited_by_count":170,"area":null},{"id":"2111.06881","title":"Multimodal Virtual Point 3D Detection","created":"2021-11-12","cited_by_count":166,"area":null},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"area":null},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156,"area":null},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156,"area":null},{"id":"2204.05088","title":"M$^2$BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation","created":"2022-04-11","cited_by_count":156,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153,"area":null},{"id":"2303.08810","title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","created":"2023-03-15","cited_by_count":151,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2204.12463","title":"Focal Sparse Convolutional Networks for 3D Object Detection","created":"2022-04-26","cited_by_count":142,"area":null},{"id":"2103.10039","title":"RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection","created":"2021-03-18","cited_by_count":140,"area":null},{"id":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140,"area":null},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140,"area":null},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135,"area":null},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129,"area":null},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128,"area":null},{"id":"2103.16206","title":"XVFI: eXtreme Video Frame Interpolation","created":"2021-03-30","cited_by_count":126,"area":null},{"id":"2208.02797","title":"Vision-Centric BEV Perception: A Survey","created":"2022-08-04","cited_by_count":126,"area":null},{"id":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121,"area":null},{"id":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121,"area":null},{"id":"2304.03608","title":"ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation","created":"2023-04-07","cited_by_count":121,"area":null},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120,"area":null},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117,"area":null},{"id":"2306.10013","title":"PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation","created":"2023-06-16","cited_by_count":115,"area":null},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112,"area":null},{"id":"2401.03407","title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","created":"2024-01-07","cited_by_count":112,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2205.14620","title":"IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation","created":"2022-05-29","cited_by_count":109,"area":null},{"id":"2108.09017","title":"DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection","created":"2021-08-20","cited_by_count":106,"area":null},{"id":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105,"area":null},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101,"area":null},{"id":"2206.04647","title":"VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution","created":"2022-06-09","cited_by_count":101,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2209.05588","title":"CenterFormer: Center-based Transformer for 3D Object Detection","created":"2022-09-12","cited_by_count":99,"area":null},{"id":"2111.14330","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","created":"2021-11-29","cited_by_count":98,"area":null},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98,"area":null},{"id":"2105.12723","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","created":"2021-05-26","cited_by_count":97,"area":null},{"id":"2207.11549","title":"Self-Support Few-Shot Semantic Segmentation","created":"2022-07-23","cited_by_count":96,"area":null},{"id":"2203.09283","title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","created":"2022-03-17","cited_by_count":95,"area":null},{"id":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94,"area":null},{"id":"2211.05776","title":"High-Quality Entity Segmentation","created":"2022-11-10","cited_by_count":93,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2205.00613","title":"MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries","created":"2022-05-02","cited_by_count":91,"area":null},{"id":"2107.12292","title":"Contextual Transformer Networks for Visual Recognition","created":"2021-07-26","cited_by_count":90,"area":null},{"id":"2111.15193","title":"Shunted Self-Attention via Multi-Scale Token Aggregation","created":"2021-11-30","cited_by_count":90,"area":null},{"id":"2104.01431","title":"Aggregated Contextual Transformations for High-Resolution Image Inpainting","created":"2021-04-03","cited_by_count":89,"area":null},{"id":"2103.13425","title":"Diverse Branch Block: Building a Convolution as an Inception-like Unit","created":"2021-03-24","cited_by_count":87,"area":null},{"id":"2210.02025","title":"GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models","created":"2022-10-05","cited_by_count":87,"area":null},{"id":"2103.16470","title":"Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":84,"area":null},{"id":"2203.14335","title":"Deep Hierarchical Semantic Segmentation","created":"2022-03-27","cited_by_count":84,"area":null},{"id":"2307.08388","title":"Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation","created":"2023-07-17","cited_by_count":84,"area":null},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2108.07058","title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","created":"2021-08-16","cited_by_count":81,"area":null},{"id":"2308.14036","title":"MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing","created":"2023-08-27","cited_by_count":81,"area":null},{"id":"2104.10442","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","created":"2021-04-21","cited_by_count":80,"area":null},{"id":"2106.02299","title":"MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution","created":"2021-06-04","cited_by_count":80,"area":null},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80,"area":null},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79,"area":null},{"id":"2209.08290","title":"Changer: Feature Interaction is What You Need for Change Detection","created":"2022-09-17","cited_by_count":79,"area":null},{"id":"2303.12787","title":"EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation","created":"2023-03-22","cited_by_count":79,"area":null},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78,"area":null},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null}],"next_cursor":"100"}