• Publications
  • Influence
Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings
TLDR
We propose a novel unsupervised approach that can discover and learn landmarks in object categories, thus characterizing their structure. Expand
  • 78
  • 11
  • PDF
Unsupervised learning of object frames by dense equivariant image labelling
TLDR
We propose a new approach that, given a large number of images of an object and no other supervision, can extract a dense object-centric coordinate frame that can map image pixels to their corresponding object coordinates. Expand
  • 51
  • 6
  • PDF
Unsupervised Learning of Landmarks by Descriptor Vector Exchange
TLDR
Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as eyes and the nose in faces, without manual supervision. Expand
  • 12
  • 2
  • PDF
Slim DensePose: Thrifty Learning From Sparse Annotations and Motion Cues
TLDR
DensePose supersedes traditional landmark detectors by densely mapping image pixels to body surface coordinates. Expand
  • 10
  • 2
  • PDF
Fully-trainable deep matching
TLDR
We rewrite the complete DM algorithm as a convolutional neural network that can be trained end-to-end via backpropagation. Expand
  • 33
  • 1
  • PDF
Cross Pixel Optical Flow Similarity for Self-Supervised Learning
TLDR
We propose a novel method for learning convolutional neural image representations without manual supervision. Expand
  • 22
  • 1
  • PDF
Unsupervised object learning from dense equivariant image labelling
TLDR
We propose a new approach that, given a large number of images of an object and no other supervision, can extract a dense object-centric coordinate frame that can map image pixels to their corresponding object coordinates. Expand
  • 12
  • 1
  • PDF
Modelling and unsupervised learning of symmetric deformable object categories
TLDR
We propose a new approach to model and learn, without manual supervision, the symmetries of natural objects, such as faces or flowers, given only images as input. Expand
  • 4
  • PDF
Self-supervised Segmentation by Grouping Optical-Flow
TLDR
We propose to self-supervise a convolutional neural network operating on images by learning to group image pixels in such a way that their collective motion is “coherent”. Expand
  • 1
  • PDF
Objects from motion