Pose-Sensitive Embedding by Nonlinear NCA Regression

By Graham W. Taylor, Rob Fergus, George Williams, Ian Spiro, C. Bregler. 2010

29 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

Pedestrian Detection with Unsupervised Multi-stage Feature Learning (2012, methodology): “Supervised ConvNets have been used by a number of authors for such applications as face, hand detection [37, 29, 15, 31, 14, 36].”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, background): “However, this work does not employ a cascade of networks.”
Deep Metric Learning via Lifted Structured Feature Embedding (2015, background): “In this regard, metric learning [13, 39, 34] and dimensionality reduction [18, 7, 29, 2] techniques aim at learning semantic distance measures and embeddings such that similar input objects are mapped to nearby points on a manifold and dissimilar objects are mapped apart from each other.”
Flowing ConvNets for Human Pose Estimation in Videos (2015, methodology): “For pose estimation, there were early examples of using ConvNets for pose comparisons [33].”
Learning Human Pose Estimation Features with Convolutional Networks (2013, background): “Taylor et al. [44] trained a convolutional neural network to learn an embedding in which images of people in similar pose lie nearby.”
Adapting Deep Visuomotor Representations with Weak Pairwise Constraints (2015, methodology): “g a multi-layer perceptron for an autonomous driving task. Many approaches to pose estimation in the recent decade were trained using rendered scenes from POSER and other human form rendering systems [10,11,12]; reliance on xed feature representations limited their performance, however, and state-of”
Towards Adapting Deep Visuomotor Representations from Simulated to Real Environments (2015, methodology): “g a multi-layer perceptron for an autonomous driving task. Many approaches to pose estimation in the recent decade were trained using rendered scenes from POSER and other human form rendering systems [10,11,12]; reliance on xed feature representations limited their performance, however, and state-of”
Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network (2014, methodology): “[23] trains a deep CNN to learn a pose-sensitive embedding with nonlinear NCA (neighbourhood components analysis) regression, and predicts the location of the head and hands by finding the nearest neighbor with the learned embedding features.”