12 citations · 15 across the 2 of their papers we have counts for
6 papers
Unsupervised Learning of Landmarks by Descriptor Vector Exchange
James Thewlis, Samuel Albanie, Hakan Bilen +1
Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as the eyes and the nose in faces, without manual supervision. How…
Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cues
Natalia Neverova, James Thewlis, Rıza Alp Güler +2
DensePose supersedes traditional landmark detectors by densely mapping image pixels to body surface coordinates. This power, however, comes at a greatly increased annotation time,…
Cross Pixel Optical Flow Similarity for Self-Supervised Learning
Aravindh Mahendran, James Thewlis, Andrea Vedaldi
We propose a novel method for learning convolutional neural image representations without manual supervision. We use motion cues in the form of optical flow, to supervise represent…
Unsupervised learning of object frames by dense equivariant image labelling
James Thewlis, Hakan Bilen, Andrea Vedaldi
One of the key challenges of visual perception is to extract abstract models of 3D objects and object categories from visual measurements, which are affected by complex nuisance fa…
Unsupervised learning of object landmarks by factorized spatial embeddings
James Thewlis, Hakan Bilen, Andrea Vedaldi
Learning automatically the structure of object categories remains an important open problem in computer vision. In this paper, we propose a novel unsupervised approach that can dis…
Fully-Trainable Deep Matching
James Thewlis, Shuai Zheng, Philip H. S. Torr +1
Deep Matching (DM) is a popular high-quality method for quasi-dense image matching. Despite its name, however, the original DM formulation does not yield a deep neural network that…