{"total":638,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572,"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":"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":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2104.09367","title":"Contrastive Learning for Compact Single Image Dehazing","created":"2021-04-19","cited_by_count":219,"area":null},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"area":null},{"id":"2203.11483","title":"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation","created":"2022-03-22","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":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188,"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":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178,"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":"2103.05950","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","created":"2021-03-10","cited_by_count":168,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"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":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"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":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"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":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117,"area":null},{"id":"2205.06803","title":"VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder","created":"2022-05-13","cited_by_count":116,"area":null},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113,"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":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","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":"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":"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":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91,"area":null},{"id":"2304.04514","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","created":"2023-04-10","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":"2203.02431","title":"Rethinking Efficient Lane Detection via Curve Modeling","created":"2022-03-04","cited_by_count":88,"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":"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":"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":"2303.08498","title":"BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection","created":"2023-03-15","cited_by_count":75,"area":null},{"id":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74,"area":null},{"id":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72,"area":null},{"id":"2108.03824","title":"AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network","created":"2021-08-09","cited_by_count":71,"area":null},{"id":"2303.09101","title":"Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank","created":"2023-03-16","cited_by_count":71,"area":null},{"id":"2104.03064","title":"DG-Font: Deformable Generative Networks for Unsupervised Font Generation","created":"2021-04-07","cited_by_count":70,"area":null},{"id":"2106.01863","title":"Robust Reference-based Super-Resolution via C2-Matching","created":"2021-06-03","cited_by_count":69,"area":null},{"id":"2206.10810","title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","created":"2022-06-22","cited_by_count":68,"area":null},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67,"area":null},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66,"area":null},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66,"area":null},{"id":"2102.00690","title":"Ground-aware Monocular 3D Object Detection for Autonomous Driving","created":"2021-02-01","cited_by_count":65,"area":null},{"id":"2110.03680","title":"Burst Image Restoration and Enhancement","created":"2021-10-07","cited_by_count":64,"area":null},{"id":"2111.04076","title":"Direct Multi-view Multi-person 3D Pose Estimation","created":"2021-11-07","cited_by_count":64,"area":null},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64,"area":null},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63,"area":null},{"id":"2104.05269","title":"Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection","created":"2021-04-12","cited_by_count":58,"area":null},{"id":"2306.16175","title":"$\\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection","created":"2023-06-28","cited_by_count":58,"area":null},{"id":"2204.10485","title":"Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network","created":"2022-04-22","cited_by_count":57,"area":null},{"id":"2308.15085","title":"Learning to Upsample by Learning to Sample","created":"2023-08-29","cited_by_count":57,"area":null},{"id":"2103.10559","title":"CDFI: Compression-Driven Network Design for Frame Interpolation","created":"2021-03-18","cited_by_count":56,"area":null},{"id":"2104.10642","title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","created":"2021-04-21","cited_by_count":54,"area":null},{"id":"2105.14217","title":"Less is More: Pay Less Attention in Vision Transformers","created":"2021-05-29","cited_by_count":53,"area":null},{"id":"2206.10965","title":"Polar Parametrization for Vision-based Surround-View 3D Detection","created":"2022-06-22","cited_by_count":53,"area":null},{"id":"2303.09875","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","created":"2023-03-17","cited_by_count":53,"area":null},{"id":"2103.07254","title":"Deep Dual Consecutive Network for Human Pose Estimation","created":"2021-03-12","cited_by_count":51,"area":null},{"id":"2207.11938","title":"Reference-based Image Super-Resolution with Deformable Attention Transformer","created":"2022-07-25","cited_by_count":51,"area":null},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51,"area":null},{"id":"2104.14854","title":"NTIRE 2021 Challenge on Image Deblurring","created":"2021-04-30","cited_by_count":50,"area":null},{"id":"2401.06197","title":"Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications","created":"2024-01-11","cited_by_count":50,"area":null},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50,"area":null},{"id":"2310.08956","title":"LRRU: Long-short Range Recurrent Updating Networks for Depth Completion","created":"2023-10-13","cited_by_count":49,"area":null},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","cited_by_count":46,"area":null},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44,"area":null},{"id":"2109.03495","title":"Temporal RoI Align for Video Object Recognition","created":"2021-09-08","cited_by_count":44,"area":null},{"id":"2203.14186","title":"RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution","created":"2022-03-27","cited_by_count":44,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2107.14467","title":"DPT: Deformable Patch-based Transformer for Visual Recognition","created":"2021-07-30","cited_by_count":43,"area":null},{"id":"2204.08446","title":"VSA: Learning Varied-Size Window Attention in Vision Transformers","created":"2022-04-18","cited_by_count":43,"area":null},{"id":"2304.07803","title":"EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation","created":"2023-04-16","cited_by_count":43,"area":null},{"id":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42,"area":null},{"id":"2109.06161","title":"Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image","created":"2021-09-13","cited_by_count":42,"area":null},{"id":"2107.05188","title":"TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentation","created":"2021-07-12","cited_by_count":41,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"area":null},{"id":"2303.16450","title":"Self-positioning Point-based Transformer for Point Cloud Understanding","created":"2023-03-29","cited_by_count":40,"area":null},{"id":"2501.02464","title":"Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera","created":"2025-01-05","cited_by_count":40,"area":null},{"id":"2103.13164","title":"M3DSSD: Monocular 3D Single Stage Object Detector","created":"2021-03-24","cited_by_count":39,"area":null},{"id":"2107.00782","title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","created":"2021-07-02","cited_by_count":39,"area":null},{"id":"2104.13497","title":"ConTNet: Why not use convolution and transformer at the same time?","created":"2021-04-27","cited_by_count":38,"area":null},{"id":"2204.04655","title":"Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation","created":"2022-04-10","cited_by_count":38,"area":null},{"id":"2210.06778","title":"X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2106.03772","title":"Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking","created":"2021-06-07","cited_by_count":37,"area":null},{"id":"2203.06622","title":"Multi-Bracket High Dynamic Range Imaging with Event Cameras","created":"2022-03-13","cited_by_count":37,"area":null},{"id":"2209.07761","title":"Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation","created":"2022-09-16","cited_by_count":37,"area":null}],"next_cursor":"100"}