Human Pose Estimation Papers

[CVPR 2016] - 201511

[IJCAI 2016] - 201602

Other

• Action Recognition with Joints-Pooled 3D Deep Convolutional Descriptors [paper]

[ECCV 2016] - 201603

2D Pose

• Human pose estimation using deep consensus voting [paper] [poster] [code]
• Human pose estimation via Convolutional Part Heatmap Regression [paper] [code] [poster]
• Stacked Hourglass Networks for Human Pose Estimation [paper] [project] [Demo Code] [Training Code] [poster]
• DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model [paper] [code] [project] [poster]

3D Pose

• Towards Viewpoint Invariant 3D Human Pose Estimation [paper] [project] [poster]
• Bayesian Image based 3D Pose Estimation [paper] [poster]
• Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image （Spotlight） [paper] [project] [code1] [code2] [poster]
• A Sequential Approach to 3D Human Pose Estimation: Separation of Localization and Identification of Body Joints [paper] [poster]

[NIPS 2016] - 201605

2D Pose

• CRF-CNN: Modeling Structured Information in Human Pose Estimation [paper]

3D Pose

• MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild [paper]

[AAAI 2017] - 201609

none

[CVPR 2017] - 201611

[IJCAI 2017] - 201702

none

[ICCV 2017] - 201703

2D Pose

• Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation [paper] [project] [code] [supplemental]
• Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation [paper]
• Learning Feature Pyramids for Human Pose Estimation [paper] [code] [supplemental] [author:Wei Yang]
• RMPE: Regional Multi-Person Pose Estimation [paper] [project] [code] [author:Hao-Shu Fang]
• Compositional Human Pose Regression [paper] [slides] [video] [author:Xiao Sun 孙骁]
• Deep Globally Constrained MRFs for Human Pose Estimation [paper]
• Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment With Limited Resources （Oral）[paper] [project] [code] [supplemental] [video] [author:Adrian Bulat]
• Self-Supervised Learning of Pose Embeddings From Spatiotemporal Relations in Videos [paper] [supplemental]
• Active Learning for Human Pose Estimation [paper]
• Human Pose Estimation using Global and Local Normalization [paper] [supplemental]
• A Coarse-Fine Network for Keypoint Localization （Spotlight） [paper] [video]

3D Pose

• Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach [paper] [code:Torch] [code:PyTorch] [supplemental] [poster] [slides] [author:Xingyi Zhou]
• A Simple yet Effective Baseline for 3D Human Pose Estimation [paper] [code] [video] [author:Julieta Martinez]
• Monocular 3D Human Pose Estimation by Predicting Depth on Joints [paper]
• Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation [paper] [project] [code] [supplemental] [author:Bugra Tekin]

Other

• Chained Multi-Stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection [paper] [project] [code] [supplemental]
• The Pose Knows: Video Forecasting by Generating Pose Futures [paper]
• RPAN: An End-To-End Recurrent Pose-Attention Network for Action Recognition in Videos （Oral） [paper] [code] [supplemental] ) [video]
• Pose-Driven Deep Convolutional Model for Person Re-Identification [paper]
• Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization [paper] [code]

[NIPS 2017] - 201705

Other

• Pose Guided Person Image Generation [paper] [code] [slides] [author: Liqian Ma]

[AAAI 2018] - 201709

2D Pose

• A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation [paper]

3D Pose

• Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation [paper] [code]

Other

• An Adversarial Hierarchical Hidden Markov Model for Human Pose Modeling and Generation [paper] [project] [PPT]
• Cross-View Person Identification by Matching Human Poses Estimated With Confidence on Each Body Joint [paper]
• PoseHD: Boosting Human Detectors Using Human Pose Information [paper]

[CVPR 2018] - 201711

2D Pose

• Detect-and-Track: Efficient Pose Estimation in Videos [paper] [code]
• Human Pose Estimation With Parsing Induced Learner [paper] [code] [author:NIE Xuecheng 聂学成]
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation [paper] [code]
• 2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning [paper] [supplemental]
• PoseTrack: A Benchmark for Human Pose Estimation and Tracking [paper]
• LSTM Pose Machines [paper] [code]
• Cascaded Pyramid Network for Multi-Person Pose Estimation [paper] [code] [slides]
• DensePose: Dense Human Pose Estimation in the Wild (Oral) [paper] [project] [code]
• Through-Wall Human Pose Estimation Using Radio Signals (Spotlight) [paper] [project]

3D Pose

• V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth Map [paper] [code] [supplemental]
• 3D Human Pose Estimation in the Wild by Adversarial Learning [paper] [video] [author:Wei Yang]
• Ordinal Depth Supervision for 3D Human Pose Estimation (Oral) [paper] [project] [code] [supplemental] [video] [author:Xiaowei Zhou 周晓巍]
• Learning Monocular 3D Human Pose Estimation From Multi-View Images (Spotlight) [paper] [project] [supplemental] [video] [author:Helge Rhodin]

Other

• Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer (Spotlight) [paper] [code] [author:Hao-Shu Fang]
• Multistage Adversarial Losses for Pose-Based Human Image Synthesis (Spotlight) [paper]
• A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-Ranking [paper] [code]
• Learning to Estimate 3D Human Pose and Shape From a Single Color Image [paper] [project] [supplemental]
• Recognizing Human Actions as the Evolution of Pose Estimation Maps [paper]
• Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints [paper]
• Deformable GANs for Pose-Based Human Image Generation [paper] [code] [supplemental]
• Pose Transferrable Person Re-Identification [paper]
• PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos [paper]
• PoTion: Pose MoTion Representation for Action Recognition [paper]
• End-to-End Recovery of Human Shape and Pose [paper] [project] [code]
• Synthesizing Images of Humans in Unseen Poses (Oral) [paper] [code] [author:Adrian Vasile Dalca]
• Unsupervised Person Image Synthesis in Arbitrary Poses (Spotlight) [paper]

arXiv 2017

2D Pose

• Human Pose Regression by Combining Indirect Part Detection and Contextual Information [paper] [code] [PPT]

[IJCAI 2018] - 201801

3D Pose

• DRPose3D: Depth Ranking in 3D Human Pose Estimation [paper]

ECCV 2018 - 201803

2D Pose

• Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling (Oral) [paper]
• Inner Space Preserving Generative Pose Machine [paper] [project] [code]
• Multi-Scale Structure-Aware Network for Human Pose Estimation [paper]
• MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network [paper][code]

3D Pose

• Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation (Oral) [paper] [project]

Other

• Good Line Cutting: towards Accurate Pose Tracking of Line-assisted VO/VSLAM [paper]