Special Issue on Advances in Domain Adaptation for Computer Vision Call for Papers
Image and Vision Computing
CALL FOR PAPERS
Special Issue on Advances in Domain Adaptation for Computer Vision
Aim and Scope:
In daily routines, humans, not only learn and apply knowledge for
visual tasks but also have intrinsic abilities to transfer knowledge
between related vision tasks. For example, if a new vision task is
relevant to any previous learning, it is possible to transfer the
learned knowledge for handling the new vision task. In developing new
computer vision algorithms, it is desired to utilize these
capabilities to make the algorithms adaptable. Generally, traditional
computer vision methods do not adapt to a new task and have to learn
the new task from the beginning. These methods do not consider that
the two visual tasks may be related and the knowledge gained in one
may be applied to learn the other one efficiently in lesser
time. Domain adaptation for computer vision is the area of research,
which attempts to mimic this human behavior by transferring the
knowledge learned in one or more source domains and use it for
learning the related visual processing task in the target
domain. Recent advances in domain adaptation, particularly in
cotraining, transfer learning, and online learning have benefited
computer vision research significantly. For example, learning from
high-resolution source domain images and transferring the knowledge to
learning low-resolution target domain information. This special issue
will focus on the recent advances in domain adaptation for different
computer vision tasks.
Topics of interest include, but are not limited to:
· Domain adaptation for machine learning frameworks for learning deep representations
· Domain adaptation for face detection/recognition and tracking
· Domain adaptation for object detection/ recognition and tracking
· Domain adaptation and hybrid models for real-time computer vision tasks
· Domain adaptation for human pose detection/recognition and estimation
· Domain adaptation for event/action detection and recognition
· Domain adaptation for few-shot learning
· Domain adaptation for deep neural network optimization
Important Dates:
Paper submission due: May 31, 2020
First notification: July 31, 2020
Revision submission due: September 30, 2020
Final decision: November 30, 2020
Paper evaluation and submission:
Submitted papers should present original, unpublished work, relevant
to one of the topics of the Special Issue. All submitted papers will
be evaluated on the basis of relevance, the significance of
contribution, technical quality, and quality of presentation, by at
least two independent reviewers (the papers will be reviewed following
standard peer-review procedures of the Journal). Each paper will be
reviewed rigorously and possibly in two rounds. Prospective authors
should follow the formatting and Instructions of Image and Vision
Computing at
https://www.elsevier.com/journals/image-and-vision-computing/0262-8856/guide-for-authors,
and invited to submit their papers directly via the online submission
system at https://www.editorialmanager.com/IMAVIS/default.aspx. When
submitting your manuscript please select the article type "VSI:
Advances in Domain Adaptation for Computer Vision (ADACV)" Please
submit your manuscript before the submission
deadline.
https://www.journals.elsevier.com/image-and-vision-computing/call-for-papers/advances-in-domain-adaptation-for-computer-vision
Guest Editors:
Dr. Pourya Shamsolmoali
Institute of Image Processing & Pattern Recognition, Shanghai Jiao
Tong University, Shanghai, China.
Email: pshams@sjtu.edu.cn
Prof. Salvador Garcaí
Department of Computer Science and Artificial Intelligence, University
of Granada, Granada, Spain.
Email: salvagl@decsai.ugr.es
Dr. Huiyu Zhou
Department of Informatics, University of Leicester, Leicester, UK.
Email: hz143@leicester.ac.uk
Prof. M. Emre Celebi
Department of Computer Science, University of Central Arkansas,
Conway, Arkansas, USA.
Email: ecelebi@uca.edu