Call for Papers: ICME 2021 Special Session at

Deep Learning for Multimedia Applications with Limited Supervision

Abstract

Deep learning technique has been widely applied in multimedia analysis applications. With sufficient annotated training data, supervised deep learning has achieved inspiring performance on various vision tasks, such as image classification, face recognition, person re-identification. However, collecting enough annotated data needed for supervised methods requires extensive human annotation efforts. Considering that most of the learning performed by animals and humans is unsupervised, their predictive learning pattern provides a good guidance for unsupervised knowledge discovery from unlabeled data. To alleviate the reliance on human annotation, unsupervised/ weakly supervised learning has become an increasingly emergent topic in multimedia applications. However, it is still challenging for unsupervised/weakly supervised deep learning, as the raw image signal is in a continuous, high-dimensional space, and it also faces various obstacles, such as uncertain noise, large domain shift, heterogenous data.

The aim of this special issue is to call for a coordinated effort to investigate the deep learning techniques with limited supervision for different multimedia applications, identify key tasks and challenges, showcase innovative ideas, introduce large scale datasets for novel applications and discuss future directions. This special issue provides a forum for researchers from multimedia, computer vision, and machine learning to present recent progress in deep learning research with limited supervision to various multimedia applications. The list of possible topics includes, but not limited to:

Unsupervised/ weakly-supervised learning for multimedia analysis
Unsupervised domain adaptation for multimedia analysis
Zero-shot learning for multimedia analysis
Transfer learning for multimedia analysis
Domain generalized learning for multimedia analysis
Deep learning from web data with limited supervision
New benchmarks/metrics/datasets for deep learning with limited supervision

Submission Guidelines and Important Dates

Submission of papers (the same with regular papers):

Regular (Special Session) Paper submission: December 13, 2020
Submission of papers to workshops and other tracks : March 13, 2021
Industry/Application track paper submission : March 22, 2021

Regular and Special Sessions:

Submission portal: https://cmt3.research.microsoft.com/ICME2021
Length: Papers must be no longer than 6 pages, including all text, figures, and references.
Abstract: The abstract should be about 100-150 words.
Submission site: All papers must indicate a Primary Subject Area to be appropriately reviewed. Papers invited to a Special Session must indicate the Special Session as the Primary Subject Area of the paper. The Special Sessions are open to all authors. All authors are invited to submit their papers to any of the Special Sessions by indicating the Special Session as the Primary Subject area of the paper.
Double blind Review: Paper submissions are reviewed by experts selected by the conference committee for their demonstrated knowledge of particular topics. Regular and Special Session papers are reviewed identically, and are subject to ICME main conference acceptance rates (15% for Oral presentations and the next 15% for Poster presentations).

Example Paper, Formatting Guidelines, and Templates. link

Organizers

Mang Ye
Inception Institute of Artificial Intelligence, UAE
mangye16 AT gmail.com

Joey Tianyi Zhou
Agency for Science, Technology, and Research (A*STAR), Singapore
joey.tianyi.zhou AT gmail.com

Jianbing Shen
Beijing Institute of Technology, China
shenjianbingcg AT gmail.com

Pong C. Yuen
Hong Kong Baptist University, Hong Kong, China
pcyuen AT comp.hkbu.edu.hk

Comments

In addition to invited papers, other potential authors will be allowed to submit papers to Special Sessions. All papers will go through the same review process as the regular papers submitted to the main conference to ensure that the contributions are of high quality. All accepted papers will be indexed the same as regular papers in the main conference proceedings. If a special session has more than 5 papers being accepted, some of the papers will be moved to the regular paper sessions of the conference.

Extended versions of the top-ranked ICME 2021 papers will be invited for submission and potential publication in the IEEE Transactions on Multimedia and IEEE Open Journal of Circuits and Systems.