Improving head and body pose estimation through semi-supervised manifold alignment
dc.contributor.author | Heili, Alexandre | |
dc.contributor.author | Varadarajan, Jagannadan | |
dc.contributor.author | Ghanem, Bernard | |
dc.contributor.author | Ahuja, Narendra | |
dc.contributor.author | Odobez, Jean-Marc | |
dc.date.accessioned | 2015-06-02T14:24:24Z | |
dc.date.available | 2015-06-02T14:24:24Z | |
dc.date.issued | 2015-02-05 | |
dc.identifier.citation | Heili, Alexandre, Jagannadan Varadarajan, Bernard Ghanem, Narendra Ahuja, and Jean-Marc Odobez. "Improving Head and Body Pose Estimation through Semi-supervised Manifold Alignment." In International Conference on Image Processing, no. EPFL-CONF-200303. 2014. | |
dc.identifier.doi | 10.1109/ICIP.2014.7025383 | |
dc.identifier.uri | http://hdl.handle.net/10754/556168 | |
dc.description.abstract | In this paper, we explore the use of a semi-supervised manifold alignment method for domain adaptation in the context of human body and head pose estimation in videos. We build upon an existing state-of-the-art system that leverages on external labelled datasets for the body and head features, and on the unlabelled test data with weak velocity labels to do a coupled estimation of the body and head pose. While this previous approach showed promising results, the learning of the underlying manifold structure of the features in the train and target data and the need to align them were not explored despite the fact that the pose features between two datasets may vary according to the scene, e.g. due to different camera point of view or perspective. In this paper, we propose to use a semi-supervised manifold alignment method to bring the train and target samples closer within the resulting embedded space. To this end, we consider an adaptation set from the target data and rely on (weak) labels, given for example by the velocity direction whenever they are reliable. These labels, along with the training labels are used to bias the manifold distance within each manifold and to establish correspondences for alignment. | |
dc.description.sponsorship | IEEE TERMS Couplings Estimation Manifolds Surveillance Training Vectors Videos | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | |
dc.relation.url | http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7025383 | |
dc.relation.url | https://dl.dropboxusercontent.com/u/18955644/website_files/Heili_ICIP_2014.pdf | |
dc.rights | (c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. | |
dc.subject | domain adaptation | |
dc.subject | head and body pose | |
dc.subject | weak labels | |
dc.subject | surveillance | |
dc.subject | semi-supervised | |
dc.subject | manifold | |
dc.title | Improving head and body pose estimation through semi-supervised manifold alignment | |
dc.type | Conference Paper | |
dc.contributor.department | Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division | |
dc.contributor.department | Electrical Engineering Program | |
dc.identifier.journal | 2014 IEEE International Conference on Image Processing (ICIP) | |
dc.conference.date | 27 October 2014 through 30 October 2014 | |
dc.conference.name | 2014 IEEE International Conference on Image Processing, ICIP 2014 | |
dc.eprint.version | Post-print | |
dc.contributor.institution | University of California San Diego, USA | |
kaust.person | Ghanem, Bernard | |
refterms.dateFOA | 2018-06-14T07:58:29Z | |
dc.date.published-online | 2015-02-05 | |
dc.date.published-print | 2014-10 |
Files in this item
This item appears in the following Collection(s)
-
Conference Papers
-
Electrical Engineering Program
For more information visit: https://cemse.kaust.edu.sa/ee -
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
For more information visit: https://cemse.kaust.edu.sa/