mlsanityData to 14 Oct 2026

VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation

arXiv 2504.19032 ↗First posted 26 Apr 2025cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce VISUALCENT, a unified human pose and instance segmentation framework to address generalizability and scalability limitations to multi person visual human analysis. VISUALCENT leverages centroid based bottom up keypoint detection paradigm and uses Keypoint Heatmap incorporating Disk Representation and KeyCentroid to identify the optimal keypoint coordinates. For the unified segmentation task, an explicit keypoint is defined as a dynamic centroid called MaskCentroid to swiftly cluster pixels to specific human instance during rapid changes in human body movement or significantly occluded environment. Experimental results on COCO and OCHuman datasets demonstrate VISUALCENTs accuracy and real time performance advantages, outperforming existing methods in mAP scores and execution frame rate per second. The implementation is available on the project page.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 26 Apr 2025.

Builds on

37 of 46 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2017Mask R-CNNcited by 7,277
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  7. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  8. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  9. 2018Path Aggregation Network for Instance Segmentationcited by 798
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2019YOLACT: Real-time Instance Segmentationcited by 443
  12. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
25 more
  1. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  2. 2016Convolutional Pose Machinescited by 325
  3. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  4. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 212
  5. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  6. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  7. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  8. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  9. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  10. 2019Single-Stage Multi-Person Pose Machinescited by 95
  11. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  12. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  13. 2020Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimationcited by 52
  14. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  15. 2018MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Networkcited by 47
  16. 2016Instance-sensitive Fully Convolutional Networkscited by 36
  17. 2019Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Informationcited by 35
  18. 2020Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinementcited by 33
  19. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  20. 2021Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimationcited by 14
  21. 2022PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimationcited by 14
  22. 2022Learning Quality-aware Representation for Multi-person Pose Regressioncited by 6
  23. 2021SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimationcited by 5
  24. 2023Disentangled Representation Learning for Controllable Person Image Generationcited by 4
  25. 2024Occluded Human Pose Estimation based on Limb Joint Augmentationcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Keypoints as Dynamic Centroids for Unified Human Pose and Segmentationcited by 0