Adapted human pose: monocular 3D human pose estimation with zero real 3D pose data
Explore this paper's citation graph
Summary
This paper focuses on alleviating the negative effect of domain shift in both appearance and pose space for 3D human pose estimation by presenting the adapted human pose (AHuP) approach, which is built upon two key components: semantically aware adaptation (SAA) and skeletal pose adaptation (SPA).
- Type
- article
- Published
- 2021-05-23
- Cited by
- 11
- References
- 76
- Access
- Open access
- OpenAlex
- https://openalex.org/W3165753266
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:235166382
Keywords
Pose, Computer science, Articulated body pose estimation, 3D pose estimation, Artificial intelligence
References
- Understanding the difficulty of training deep feedforward neural networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- Pose-conditioned joint angle limits for 3D human pose reconstruction
- SCAPE: shape completion and animation of people
- Generalized procrustes analysis
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
- ImageNet: A large-scale hierarchical image database
- MoSh
- Domain adaptation for object recognition: An unsupervised approach
- ViHASi: Virtual human action silhouette data for the performance evaluation of silhouette-based action recognition methods
- Multi-view object class detection with a 3D geometric model
- Learning appearance in virtual scenarios for pedestrian detection
- Learning Transferable Features with Deep Adaptation Networks
- Visualizing Data using t-SNE
- Deep Residual Learning for Image Recognition
- Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach
- Subspace Alignment Based Domain Adaptation for RCNN Detector
- Synthesizing Training Images for Boosting Human 3D Pose Estimation
Cited by
- Joint Classification and Trajectory Regression of Online Handwriting using a Multi-Task Learning Approach
- Monocular 3D Human Pose Estimation with Domain Feature Alignment and Self Training
- Anatomy-guided domain adaptation for 3D in-bed human pose estimation
- Optimizing offset-regression by relay point for bottom-up human pose estimation
- Multi-sensor fusion federated learning method of human posture recognition for dual-arm nursing robots
- Clustering-based multi-featured self-supervised learning for human activities and video retrieval
- A residual semantic graph convolutional network with high-resolution representation for 3D human pose estimation in a virtual fashion show
- Automated Monitoring of Gym Exercises through Human Pose Analysis
- Vibrator Rack Pose Estimation for Monitoring the Vibration Quality of Concrete Using Improved YOLOv8-Pose and Vanishing Points
- 3d human pose estimation based on conditional dual-branch diffusion
- LiteSpiralGCN: Lightweight 3D hand mesh reconstruction via spiral graph convolution
Related papers
- A Comparison on Different 2D Human Pose Estimation Method
- Learning to Refine Human Pose Estimation
- Real Time Head Model Creation and Head Pose Estimation on Consumer Depth Cameras
- Shape-Constraint Recurrent Flow for 6D Object Pose Estimation
- Non-parametric hand pose estimation with object context
- Recent Advances in 3D Human Pose Estimation: From Optimization to Implementation and Beyond