mlsanityData to 7 Oct 2026

SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation

arXiv 2107.03332 ↗First posted 7 Jul 2021cs.CVcited by 68

Not on the map. Why?

Abstract (arXiv)

The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance. However, the long-standing quantization error problem in the 2D heatmap-based methods leads to several well-known drawbacks: 1) The performance for the low-resolution inputs is limited; 2) To improve the feature map resolution for higher localization precision, multiple costly upsampling layers are required; 3) Extra post-processing is adopted to reduce the quantization error. To address these issues, we aim to explore a brand new scheme, called textitSimCC, which reformulates HPE as two classification tasks for horizontal and vertical coordinates. The proposed SimCC uniformly divides each pixel into several bins, thus achieving sub-pixel localization precision and low quantization error. Benefiting from that, SimCC can omit additional refinement post-processing and exclude upsampling layers under certain settings, resulting in a more simple and effective pipeline for HPE. Extensive experiments conducted over COCO, CrowdPose, and MPII datasets show that SimCC outperforms heatmap-based counterparts, especially in low-resolution settings by a large margin.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Builds on 39 of its 44 references that are in the map. First posted on arXiv 7 Jul 2021.

Builds on

39 of 44 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2017Mask R-CNNcited by 7,259
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2018YOLOv3: An Incremental Improvementcited by 2,652
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2019Objects as Pointscited by 1,172
  11. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  12. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
27 more
  1. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  2. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  3. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  4. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  5. 2017Integral Human Pose Regressioncited by 255
  6. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  7. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  8. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  9. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  10. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  11. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  12. 2017Compositional Human Pose Regressioncited by 124
  13. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  14. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
  15. 2021Pose Recognition with Cascade Transformerscited by 99
  16. 2019Single-Stage Multi-Person Pose Machinescited by 95
  17. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  18. 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
  19. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  20. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  21. 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
  22. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  23. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  24. 2018MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Networkcited by 47
  25. 2021TFPose: Direct Human Pose Estimation with Transformerscited by 42
  26. 2020Gaussian Vector: An Efficient Solution for Facial Landmark Detectioncited by 7
  27. 2020Attentive One-Dimensional Heatmap Regression for Facial Landmark Detection and Trackingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 16; 2025: 25; 2026: 12.

68 papers.

Sort:

By area:

  1. 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 307
  2. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  3. 2023Improving Deep Regression with Ordinal Entropycited by 44
  4. 2023GPGait: Generalized Pose-based Gait Recognitioncited by 39
  5. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  6. 2024RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimationcited by 18
  7. 2024LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Modelcited by 17
  8. 2024The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiencescited by 15
  9. 2023VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Spacecited by 13
  10. 2025MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videoscited by 8
  11. 2023Lightweight Super-Resolution Head for Human Pose Estimationcited by 7
  12. 2023SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognitioncited by 7
38 more
  1. 2025EDM: Efficient Deep Feature Matchingcited by 7
  2. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  3. 2024UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cuescited by 6
  4. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  5. 2024Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimizationcited by 5
  6. 2025Finger Pose Estimation for Under-screen Fingerprint Sensorcited by 5
  7. 2024PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptionscited by 4
  8. 2023FastPoseGait: A Toolbox and Benchmark for Efficient Pose-based Gait Recognitioncited by 3
  9. 2024LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imagingcited by 3
  10. 2024Occluded Human Pose Estimation based on Limb Joint Augmentationcited by 3
  11. 2025Synergistic Bleeding Region and Point Detection in Laparoscopic Surgical Videoscited by 3
  12. 2024Pixel-Wise Symbol Spotting via Progressive Points Location for Parsing CAD Imagescited by 2
  13. 2024The Influence of Faulty Labels in Data Sets on Human Pose Estimationcited by 2
  14. 2024Bilateral Sharpness-Aware Minimization for Flatter Minimacited by 2
  15. 2025ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Modelcited by 2
  16. 2025DroneKey: Drone 3D Pose Estimation in Image Sequences using Gated Key-representation and Pose-adaptive Learningcited by 2
  17. 2025UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretationcited by 2
  18. 2023SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Drivingcited by 1
  19. 2024PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkitcited by 1
  20. 2025Improving Deep Regression with Tightnesscited by 1
  21. 2025RT-DEMT: A hybrid real-time acupoint detection model combining mamba and transformercited by 1
  22. 2025PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimationcited by 1
  23. 2025DiffPose-Animal: A Language-Conditioned Diffusion Framework for Animal Pose Estimationcited by 1
  24. 2025Heatmap Pooling Network for Action Recognition from RGB Videoscited by 1
  25. 2026SURE: Semi-dense Uncertainty-REfined Feature Matchingcited by 1
  26. 2026Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregationcited by 1
  27. 2023MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devicescited by 0
  28. 20231DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Trackingcited by 0
  29. 2023A comprehensive framework for occluded human pose estimationcited by 0
  30. 2023Active headrest combined with a depth camera-based ear-positioning systemcited by 0
  31. 2024Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimationcited by 0
  32. 2024HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimationcited by 0
  33. 2024OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUscited by 0
  34. 2025Refinement Module based on Parse Graph for Human Pose Estimationcited by 0
  35. 2025AI-Driven Automated Tool for Abdominal CT Body Composition Analysis in Gastrointestinal Cancer Managementcited by 0
  36. 2025Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimationcited by 0
  37. 2025Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimationcited by 0
  38. 2025Differentially Private 2D Human Pose Estimationcited by 0

50 most cited of 68 All 68 (JSON)