Call for Papers
International Journal of Computer Vision
Special Issue on Domain Adaptation for Vision Applications
Domain adaptation is an emerging research topic in computer vision. In some
vision applications, the domain of interest (i.e., the target domain)
contains very few or even no labeled samples, while an existing domain
(i.e., the auxiliary domain) is often available with a large number of
labeled examples. For example, millions of loosely labeled Flickr photos or
YouTube videos can be readily obtained by using keywords (also called tags)
based search. On the other hand, users may be interested in retrieving and
organizing their own multimedia collections of images and videos at the
semantic level, but may be reluctant to put forth the effort to annotate
their photos and videos by themselves. This problem becomes furthermore
challenging because the feature distributions of training samples from the
web domain and consumer domain may differ tremendously in statistical
properties. To effectively utilize training samples from both domains,
domain adaptation techniques can be employed to learn robust classifiers
that explicitly cope with the considerable variation in feature
distributions.
This special issue seeks high quality and original research on domain
adaptation for vision applications. The goals of this special issue are
three-fold: 1) investigating fundamental theories for domain adaptation, 2)
presenting novel domain adaptation techniques applicable to at least one
existing computer vision application, and 3) exploring new challenging
vision applications for domain adaptation techniques.
Manuscripts are solicited to address a wide range of topics on domain
adaptation techniques and applications with a focus on computer vision
tasks, including but not limited to the following:
* Fundamental theory for domain adaptation
* Single source domain adaptation
* Multiple source domain adaptation
* Unsupervised domain adaptation
* Heterogeneous domain adaptation
* Online domain adaptation
* Cross-knowledge transfer
* Novel computer vision applications for domain adaptation
* Evaluation of domain adaptation algorithms and systems for specific
vision applications
Guidelines for authors can be found at
http://www.editorialmanager.com/visi/ . Prospective authors should submit
high quality, original manuscripts that have not appeared, nor are under
consideration, in any other journal or conference. Papers submitted to this
special issue should have a distinctive title using the format: SI-Domain
Adaptation<title>. All papers will be peer reviewed by experts in the field.
Important Dates
Manuscript submission: 1st March 2013
Preliminary results: 30th June 2013
Revisions due: 30th September 2013
Notification: 30th November 2013
Final manuscripts due: 30th December 2013
Anticipated publication: 1st or 2nd quarter 2014
Guest Editors
Dr. Dong Xu
Nanyang Technological University, Singapore
dongxu@ntu.edu.sg
Prof. Rama Chellappa
University of Maryland, College Park, USA
rama@umiacs.umd.edu
Prof. Trevor Darrell
University of California, Berkeley, USA
trevor@eecs.berkeley.edu
Dr. Hal Daume III
University of Maryland, College Park, USA
hal@umiacs.umd.edu
--
※ 發信站: 批踢踢實業坊(ptt.cc)
◆ From: 147.46.241.183