mlsanityData to 14 Oct 2026

FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions

arXiv 2105.14185 ↗First posted 29 May 2021cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

We propose a fully convolutional multi-person pose estimation framework using dynamic instance-aware convolutions, termed FCPose. Different from existing methods, which often require ROI (Region of Interest) operations and/or grouping post-processing, FCPose eliminates the ROIs and grouping post-processing with dynamic instance-aware keypoint estimation heads. The dynamic keypoint heads are conditioned on each instance (person), and can encode the instance concept in the dynamically-generated weights of their filters. Moreover, with the strong representation capacity of dynamic convolutions, the keypoint heads in FCPose are designed to be very compact, resulting in fast inference and making FCPose have almost constant inference time regardless of the number of persons in the image. For example, on the COCO dataset, a real-time version of FCPose using the DLA-34 backbone infers about 4.5x faster than Mask R-CNN (ResNet-101) (41.67 FPS vs. 9.26FPS) while achieving improved performance. FCPose also offers better speed/accuracy trade-off than other state-of-the-art methods. Our experiment results show that FCPose is a simple yet effective multi-person pose estimation framework. Code is available at: https://git.io/AdelaiDet

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 32 of its 34 references that are in the map. First posted on arXiv 29 May 2021.

Builds on

32 of 34 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2017Mask R-CNNcited by 7,277
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  9. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  10. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  11. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  12. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
20 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  2. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  3. 2017Deep Layer Aggregationcited by 436
  4. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  5. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  6. 2016Dynamic Filter Networkscited by 319
  7. 2020Conditional Convolutions for Instance Segmentationcited by 314
  8. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
  9. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  10. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  11. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 212
  12. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  13. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  14. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  15. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  16. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  17. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  18. 2018MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Networkcited by 47
  19. 2018Revisiting RCNN: On Awakening the Classification Power of Faster RCNNcited by 28
  20. 2016Multi-Person Pose Estimation with Local Joint-to-Person Associationscited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 13; 2024: 4; 2025: 3; 2026: 2.

34 papers.

Sort:

  1. 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
  2. 2023Human Pose as Compositional Tokenscited by 45
  3. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 34
  4. 2023Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimationcited by 26
  5. 20222D Human Pose Estimation: A Surveycited by 21
  6. 2024SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimationcited by 21
  7. 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
  8. 2021InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimationcited by 13
  9. 2023You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perceptioncited by 9
  10. 2021Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating roomcited by 7
  11. 2021AdaptivePose: Human Parts as Adaptive Pointscited by 6
  12. 2022AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regressioncited by 6
22 more
  1. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  2. 2024Referring Human Pose and Mask Estimation in the Wildcited by 6
  3. 2022Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Personscited by 5
  4. 2022Body-Part Joint Detection and Association via Extended Object Representationcited by 5
  5. 2022Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videoscited by 4
  6. 2023LAMP: Leveraging Language Prompts for Multi-person Pose Estimationcited by 4
  7. 2022RepParser: End-to-End Multiple Human Parsing with Representative Partscited by 3
  8. 20222D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraintscited by 3
  9. 2023BPJDet: Extended Object Representation for Generic Body-Part Joint Detectioncited by 2
  10. 2023Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approachcited by 2
  11. 2023BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimationcited by 2
  12. 2024DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimationcited by 2
  13. 2022Location-free Human Pose Estimationcited by 1
  14. 2023MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Modelcited by 1
  15. 2024Waterfall Transformer for Multi-person Pose Estimationcited by 1
  16. 2025DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypointscited by 1
  17. 2026UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimationcited by 1
  18. 2023Towards High Performance One-Stage Human Pose Estimationcited by 0
  19. 2023CIParsing: Unifying Causality Properties into Multiple Human Parsingcited by 0
  20. 2025Keypoints as Dynamic Centroids for Unified Human Pose and Segmentationcited by 0
  21. 2025Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifoldscited by 0
  22. 2026ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose Estimationcited by 0