Transfer Learning for Multimedia Applications

A Special Issue on Multimedia Tools and Applications (MTAP SI 1140T)

Important Dates (tentative):

Final Manuscript Due: May 15th, 2019

Scope [ CFP.pdf ]

Multimedia applications naturally involve heterogeneous domain data, e.g., text, image, audio and video. Data from heterogeneous domains tend to have different marginal and conditional distributions. However, conventional machine learning approaches assume that the training data and the test data are from the same data distribution. Thus, there is an unavoidable obstacle in the multimedia applications–how to mitigate the domain shifts in cross-modal algorithms? Unfortunately, a majority of existing approaches in the multimedia community ignored the problem or just left it for the future research. Recently, transfer learning has been proven to be effective to handle the domain shift problem and transfer knowledge from one domain to the other related domains. Now it is the time to face the problem in multimedia and investigate it with transfer learning!

This special issue is devoted to the publication of high-quality research papers on transfer learning for various multimedia applications, such as, multimedia retrieval, classification, recommendation, multi-modal data mining, etc. The special issue will seek for original contribution of works, which address the key challenges and problems.

Guest Editors

Dr. Jingjing Li, University of Electronic Science and Technology of China, China, Email:
Dr. Zhengming Ding, Indiana University-Purdue University Indianapolis (IUPUI), USA, Email:
Dr. Weiqing Wang, School of Information Technology, Monash University, Australia, Email:


Transfer learning for multimedia retrieval / indexing

Transfer learning for image/video/music/audio retrieval.

Recommendation and Security

Transfer learning methods for multimedia recommendation.

Transfer learning for multimedia security.

Survey, New ideas and Multimedia tools.

Survey papers with regards of transfer learning for multimedia applications.

New multimedia datasets for transfer learning.

New transfer learning tools for multimedia analysis.

Domain Adaptation, Multi-view learning, Zero-shot Learning

Deep / traditional, homogeneous / heterogeneous domain adaptation for multimedia.

Multi-view learning algorithms for multimedia.

Zero-shot learning algorithms for multimedia.