mlsanityData to 14 Oct 2026

Deep High-Resolution Representation Learning for Visual Recognition

arXiv 1908.07919 ↗First posted 20 Aug 2019cs.CVcited by 1,420

Not on the map. Why?

Cited by 31 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at~urlhttps://github.com/HRNet.

Key facts. Cited by 1,420 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 266; 2022: 303; 2023: 291; 2024: 262; 2025: 184; 2026: 113.

1,420 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  3. 2021Vision Transformers for Dense Predictioncited by 1,803
  4. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  5. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  6. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  7. 2021Conditional DETR for Fast Training Convergencecited by 424
  8. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 366
  9. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 342
  10. 2023Segment Anything Model for Medical Image Analysis: an Experimental Studycited by 291
  11. 2021Mesh Graphormercited by 265
  12. 2023DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectorycited by 264
38 more
  1. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 261
  2. 2021TransFuse: Fusing Transformers and CNNs for Medical Image Segmentationcited by 258
  3. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  4. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  5. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 231
  6. 2021Co-Scale Conv-Attentional Image Transformerscited by 224
  7. 2022Visual Attention Networkcited by 210
  8. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  9. 2023A Survey on Video Diffusion Modelscited by 206
  10. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  11. 2022DaViT: Dual Attention Vision Transformerscited by 175
  12. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 166
  13. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  14. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  15. 2021Reviving Iterative Training with Mask Guidance for Interactive Segmentationcited by 163
  16. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  17. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  18. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  19. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  20. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  21. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  22. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  23. 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
  24. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 126
  25. 2021DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentationcited by 126
  26. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 124
  27. 2021AP-10K: A Benchmark for Animal Pose Estimation in the Wildcited by 123
  28. 2022Two-Stream Network for Sign Language Recognition and Translationcited by 123
  29. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  30. 2021Vision Transformer for Small-Size Datasetscited by 122
  31. 2022Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learningcited by 115
  32. 2022Gait Recognition in the Wild with Dense 3D Representations and A Benchmarkcited by 114
  33. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  34. 2023Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentationcited by 112
  35. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  36. 2022SimpleClick: Interactive Image Segmentation with Simple Vision Transformerscited by 111
  37. 2022VLT: Vision-Language Transformer and Query Generation for Referring Segmentationcited by 111
  38. 2022Highly Accurate Dichotomous Image Segmentationcited by 110

50 most cited of 1,420 All 1,420 (JSON)