Unsupervised Human Pose Estimation

13 papers with code • 3 benchmarks • 3 datasets

This task has no description! Would you like to contribute one?

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 7 Apr 2020

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

NVlabs/SCOPS CVPR 2019

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

DELTA37/LatentKeypointGAN 29 Mar 2021

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.