IIIT Hyderabad Publications |
|||||||||
|
Human Pose Search using Deep PoseletsAuthors: Nataraj Jammalamadaka,Andrew Zisserman, C V Jawahar Conference: International Conference on Automatic Face and Gesture Recognition (FG 2015 2015) Date: 2015-05-04 Report no: IIIT/TR/2015/42 AbstractHuman pose as a query modality is an alternative and rich experience for image and video retrieval. We present a novel approach for the task of human pose retrieval, and make the following contributions: first, we introduce ‘deep poselets’ for pose-sensitive detection of various body parts, that are built on convolutional neural network (CNN) features. These deep poselets significantly outperform previous instantiations of Berkeley poselets [2]. Second, using these detector responses, we construct a pose representation that is suitable for pose search, and show that pose retrieval performance exceeds previous methods by a factor of two. The compared methods include Bag of visual words [24], Berkeley poselets [2] and Human pose estimation algorithms [28]. All the methods are quantitatively evaluated on a large dataset of images built from a number of standard benchmarks together with frames from Hollywood movies. Full paper: pdf Centre for Visual Information Technology |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |