Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation
Authors:
- Suha KwakSKSuha Kwak
- Minsu ChoMCMinsu Cho
- Ivan LaptevILIvan Laptev
- 12 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4938-4947
Abstract
We address the problem of learning a pose-aware, compact embedding that projects images with similar human poses to be placed close-by in the embedding space. The embedding function is built on a deep convolutional network, and trained with triplet-based rank constraints on real image data. This architecture allows us to learn a robust representation that captures differences in human poses by effectively factoring out variations in clothing, background, and imaging conditions in the wild. For a variety of pose-related tasks, the proposed pose embedding provides a cost-efficient and natural alternative to explicit pose estimation, circumventing challenges of localizing body joints. We demonstrate the efficacy of the embedding on pose-based image retrieval and action recognition problems.Keywords
This publication has 43 references indexed in Scilit:
- Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks2014
- Posebits for Monocular Human Pose Estimation2014
- Towards Understanding Action Recognition2013
- Multi-agent Event Detection: Localization and Role Assignment2013
- Articulated pose estimation with flexible mixtures-of-parts2011
- Grouplet: A structured image representation for recognizing human and object interactions2010
- Recognizing human actions from still images with latent poses2010
- Modeling View and Posture Manifolds for Tracking2007
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989