Data to 7 Oct 2026

Convolutional Pose Machines

arXiv 1602.00134 ↗First posted 30 Jan 2016cs.CVcited by 325

Not on the map. Why?

Abstract (arXiv)

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets.

Key facts. Cited by 325 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jan 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 115; 2022: 67; 2023: 62; 2024: 37; 2025: 33; 2026: 10.

325 papers.

Sort:

By area:

2023Style Aligned Image Generation via Shared Attentioncited by 214
2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
2024OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-oncited by 150
2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
2021Pose Recognition with Cascade Transformerscited by 99
2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 90

38 more

2023Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmarkcited by 75
2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
2021Neural Monocular 3D Human Motion Capture with Physical Awarenesscited by 70
2023LooseControl: Lifting ControlNet for Generalized Depth Conditioningcited by 68
2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animationcited by 63
2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
2022Drivable Volumetric Avatars using Texel-Aligned Featurescited by 62
2021Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Featurescited by 57
2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
2021Online Knowledge Distillation for Efficient Pose Estimationcited by 55
2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
2021From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimationcited by 48
2023Human Pose as Compositional Tokenscited by 45
2023Neural Haircut: Prior-Guided Strand-Based Hair Reconstructioncited by 43
2021When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarkscited by 41
2022Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classificationcited by 39
2023Sign Language Translation from Instructional Videoscited by 39
2022Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddingscited by 38
2021FANet: A Feedback Attention Network for Improved Biomedical Image Segmentationcited by 36
2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimationcited by 36
2021Regressive Domain Adaptation for Unsupervised Keypoint Detectioncited by 34
2021Toward Accurate and Realistic Outfits Visualization with Attention to Detailscited by 33
2021Test-Time Personalization with a Transformer for Human Pose Estimationcited by 33
2021ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignmentcited by 33
2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 32
2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
2023Human101: Training 100+FPS Human Gaussians in 100s from 1 Viewcited by 32
2021Hand Image Understanding via Deep Multi-Task Learningcited by 31
2021Supervision by Registration and Triangulation for Landmark Detectioncited by 30
2024InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generationcited by 30
2021Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Settingcited by 27
2022Semi-Supervised Keypoint Detector and Descriptor for Retinal Image Matchingcited by 27
2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
2021Skeletor: Skeletal Transformers for Robust Body-Pose Estimationcited by 26
2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
2021ViPNAS: Efficient Video Pose Estimation via Neural Architecture Searchcited by 26

50 most cited of 325 All 325 (JSON)