DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
Not on the map. Why?
Abstract (arXiv)
The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. Evaluation is done on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation. Models and code available at http://pose.mpi-inf.mpg.de
Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 May 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 33; 2022: 20; 2023: 22; 2024: 12; 2025: 9.
96 papers.
Sort:
- 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
- 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
- 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
- 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
- 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
- 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
- 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
- 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
- 2021Regressive Domain Adaptation for Unsupervised Keypoint Detectioncited by 34
- 2021Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsingcited by 31
- 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
- 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
38 more
- 2021AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wildcited by 29
- 2021A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videoscited by 28
- 2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
- 2022ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wildcited by 23
- 20222D Human Pose Estimation: A Surveycited by 21
- 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
- 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
- 2022Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluationcited by 19
- 2021The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimationcited by 18
- 2023Reconstructing Groups of People with Hypergraph Relational Reasoningcited by 18
- 2022Lite Pose: Efficient Architecture Design for 2D Human Pose Estimationcited by 16
- 2022PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimationcited by 14
- 2022Deep learning for table detection and structure recognition: A surveycited by 14
- 2021InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimationcited by 13
- 2022Dual networks based 3D Multi-Person Pose Estimation from Monocular Videocited by 13
- 2023Prior-guided Source-free Domain Adaptation for Human Pose Estimationcited by 13
- 2021Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Trackingcited by 12
- 2021mmPose-NLP: A Natural Language Processing Approach to Precise Skeletal Pose Estimation using mmWave Radarscited by 11
- 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10
- 2021Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Viewscited by 9
- 2021Estimating 3D Motion and Forces of Human-Object Interactions from Internet Videoscited by 9
- 2023You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perceptioncited by 9
- 2024Markerless Multi-view 3D Human Pose Estimation: a surveycited by 9
- 2021An Adversarial Human Pose Estimation Network Injected with Graph Structurecited by 8
- 2021Location-Sensitive Visual Recognition with Cross-IOU Losscited by 8
- 2021G2DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identificationcited by 8
- 2022Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifierscited by 8
- 2023Few-shot Geometry-Aware Keypoint Localizationcited by 6
- 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
- 2024Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Reviewcited by 6
- 2024Automatic infant 2D pose estimation from videos: comparing seven deep neural network methodscited by 6
- 2024Referring Human Pose and Mask Estimation in the Wildcited by 6
- 2021SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimationcited by 5
- 2021HR-Crime: Human-Related Anomaly Detection in Surveillance Videoscited by 5
- 2022Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networkscited by 5
- 2022Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Personscited by 5
- 2022A Temporal Densely Connected Recurrent Network for Event-based Human Pose Estimationcited by 5
- 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Modelscited by 5
50 most cited of 96 All 96 (JSON)
- 2025Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activities2 Oct 2025
- 2025Deep Learning-based Animal Behavior Analysis: Insights from Mouse Chronic Pain Models7 Aug 2025
- 2025From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras30 Jul 2025
- 2025VirtualFencer: Generating Fencing Bouts based on Strategies Extracted from In-the-Wild Videos30 Jun 2025
- 2025Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation17 May 2025
- 2025VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation26 Apr 2025
- 2025Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation8 Apr 2025
- 2025STEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans17 Mar 2025
- 2025Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements5 Mar 2025
- 2024RatBodyFormer: Rat Body Surface from Keypoints12 Dec 2024
- 2024Referring Human Pose and Mask Estimation in the Wild27 Oct 2024
- 2024Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis12 Oct 2024
38 more
- 2024Deep-Learning-Based Markerless Pose Estimation Systems in Gait Analysis: DeepLabCut Custom Training and the Refinement Function15 Jul 2024
- 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation10 Jul 2024
- 2024Graph-Boosted Attentive Network for Semantic Body Parsing8 Jul 2024
- 2024Markerless Multi-view 3D Human Pose Estimation: a survey4 Jul 2024
- 2024Human Modelling and Pose Estimation Overview27 Jun 2024
- 2024Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods25 Jun 2024
- 2024Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion2 May 2024
- 2024Enhancing Surgical Performance in Cardiothoracic Surgery with Innovations from Computer Vision and Artificial Intelligence: A Narrative Review17 Feb 2024
- 2024Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Review22 Jan 2024
- 2023Deformable 3D Gaussian Splatting for Animatable Human Avatars22 Dec 2023
- 2023Diffusion Models Enable Zero-Shot Pose Estimation for Lower-Limb Prosthetic Users13 Dec 2023
- 2023You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception9 Dec 2023
- 2023Reality's Canvas, Language's Brush: Crafting 3D Avatars from Monocular Video8 Dec 2023
- 2023Spatial Attention-based Distribution Integration Network for Human Pose Estimation9 Nov 2023
- 2023Improving Multi-Person Pose Tracking with A Confidence Network29 Oct 2023
- 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey19 Oct 2023
- 2023PoseAction: Action Recognition for Patients in the Ward using Deep Learning Approaches5 Oct 2023
- 2023Sparse and Privacy-enhanced Representation for Human Pose Estimation18 Sep 2023
- 2023Reconstructing Groups of People with Hypergraph Relational Reasoning30 Aug 2023
- 2023Prior-guided Source-free Domain Adaptation for Human Pose Estimation26 Aug 2023
- 2023Vision-Based Human Pose Estimation via Deep Learning: A Survey26 Aug 2023
- 2023Of Mice and Pose: 2D Mouse Pose Estimation from Unlabelled Data and Synthetic Prior25 Jul 2023
- 2023LAMP: Leveraging Language Prompts for Multi-person Pose Estimation21 Jul 2023
- 2023SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving6 Jun 2023
- 2023Error Estimation for Single-Image Human Body Mesh Reconstruction26 May 2023
- 2023Assessment of Anterior Cruciate Ligament Injury Risk Based on Human Key Points Detection Algorithm24 May 2023
- 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models23 May 2023
- 2023Hybrid model for Single-Stage Multi-Person Pose Estimation2 May 2023
- 2023Few-shot Geometry-Aware Keypoint Localization30 Mar 2023
- 2023A Survey of Advanced Computer Vision Techniques for Sports18 Jan 2023
- 2023CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey15 Jan 2023
- 2022ViTPose++: Vision Transformer for Generic Body Pose Estimation7 Dec 2022
- 2022Deep learning for table detection and structure recognition: A survey15 Nov 2022
- 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time7 Nov 2022
- 2022Performance of different machine learning methods on activity recognition and pose estimation datasets19 Oct 2022
- 2022Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifiers2 Oct 2022
- 2022A Temporal Densely Connected Recurrent Network for Event-based Human Pose Estimation15 Sep 2022
- 2022Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons25 Aug 2022
50 newest of 96 All 96 (JSON)
- 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
- 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
- 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
- 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
- 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
- 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
- 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
- 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
- 2021Regressive Domain Adaptation for Unsupervised Keypoint Detectioncited by 34
- 2021Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsingcited by 31
- 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
- 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
12 most cited of 96 All 96 (JSON)
- 2025Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activities2 Oct 2025
- 2025Deep Learning-based Animal Behavior Analysis: Insights from Mouse Chronic Pain Models7 Aug 2025
- 2025From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras30 Jul 2025
- 2025VirtualFencer: Generating Fencing Bouts based on Strategies Extracted from In-the-Wild Videos30 Jun 2025
- 2025Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation17 May 2025
- 2025VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation26 Apr 2025
- 2025Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation8 Apr 2025
- 2025STEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans17 Mar 2025
- 2025Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements5 Mar 2025
- 2024RatBodyFormer: Rat Body Surface from Keypoints12 Dec 2024
- 2024Referring Human Pose and Mask Estimation in the Wild27 Oct 2024
- 2024Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis12 Oct 2024
12 newest of 96 All 96 (JSON)