Unsupervised Human Pose Estimation
13 papers with code • 3 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Unsupervised Human Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Human3.6M
DeepFashion
Tai-Chi-HD
Most implemented papers
Deep Feature Factorization For Concept Discovery
jacobgil/pytorch-grad-cam
•
•
ECCV 2018
We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images.
Unsupervised Part-Based Disentangling of Object Shape and Appearance
NVIDIA/UnsupervisedLandmarkLearning
•
•
CVPR 2019
Large intra-class variation is the result of changes in multiple object characteristics.
Motion-supervised Co-Part Segmentation
AliaksandrSiarohin/motion-cosegmentation
•
•
To overcome this limitation, we propose a self-supervised deep learning method for co-part segmentation.
Unsupervised Human Pose Estimation through Transforming Shape Templates
lschmidtke/shape_templates
•
•
CVPR 2021
Human pose estimation is a major computer vision problem with applications ranging from augmented reality and video capture to surveillance and movement tracking.
Unsupervised learning of object landmarks by factorized spatial embeddings
alldbi/Factorized-Spatial-Embeddings
•
•
ICCV 2017
Learning automatically the structure of object categories remains an important open problem in computer vision.
Unsupervised Discovery of Object Landmarks as Structural Representations
YutingZhang/lmdis-rep
•
•
CVPR 2018
Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way.
SCOPS: Self-Supervised Co-Part Segmentation
Parts provide a good intermediate representation of objects that is robust with respect to the camera, pose and appearance variations.
LatentKeypointGAN: Controlling GANs via Latent Keypoints
Generative adversarial networks (GANs) have attained photo-realistic quality in image generation.
GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation
xingzhehe/ganseg
•
•
CVPR 2022
Segmenting an image into its parts is a frequent preprocess for high-level vision tasks such as image editing.
Self-Supervised Keypoint Discovery in Behavioral Videos
neuroethology/bkind
•
•
CVPR 2022
We propose a method for learning the posture and structure of agents from unlabelled behavioral videos.
