MULTIMEDIA TOOLS AND APPLICATIONS

Special Issue on Ad Hoc Web Multimedia Analysis with Limited Supervision


1. Scope:

With the advance of Web 2.0 era, there is an explosive growth of user generated multimedia data shared in social network websites such as Flickr, YouTube, and Facebook. These real world multimedia data turn out a great challenge in the semantic understanding and retrieval of web multimedia. On one hand, the users’ comments and tagging can be well exploited to provide more semantic cues for the web multimedia analysis. On the other hand, the annotations of these data contain a lot of noisy tags and are always weakly tagging. Furthermore, for web multimedia analysis, the negative examples come from an infinite semantic space and we have no clue about the semantics these negative examples include. The constructed specific method or model may be unreliable for the analysis of ad hoc test multimedia data. Thus, we need to develop generic model for analysis tasks of the ad hoc test multimedia data (a.k.a. Ad Hoc Web Multimedia Analysis). Different from the traditional learning based multimedia analysis methods, it is impossible to have adequate precisely labeled training data in the ad hoc multimedia analysis. More importantly, we have no knowledge of the ad hoc test data. For example, because the test instances are still considered to come from the same semantic space as that of the labeled training data, semi-supervised learning needs to be augmented for the task of ad hoc multimedia analysis. As the research of ad hoc web multimedia analysis with limited supervision is still in its infancy, we see a timely opportunity for organizing a special issue to bring together active researchers to share recent progress in this exciting area. This special issue serves as a forum for researchers all over the world to discuss their works and recent advances in ad hoc web multimedia analysis with limited supervision. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Especially, to provide readers of the special issue with a state-of-the-art background on the topic, we will invite one survey paper, which will undergo peer review. This special issue seeks to present and highlight the latest developments on large scale web multimedia analysis. Papers addressing interesting real-world applications are especially encouraged. Topics of interest include, but are not limited to,

• Ad hoc web multimedia event detection
• Describing ad hoc web multimedia with contextual information
• Integration and ensemble of multimedia classifiers with limited supervision
• Context and content fusion in social multimedia tagging
• Multiple source domain adaptation for ad hoc multimedia analysis
• Cross-media data mining for social media analysis
• Heterogeneous knowledge discovery with few multimedia examplars
• Real-world applications of ad hoc multimedia recommendation, sharing, and context-based browsing etc.

2. Submission Guideline：

Authors should prepare their manuscript according to the Instructions for Authors available from the online submission page of the Multimedia Tools and Applications at springer.com. All the papers will be peer-reviewed following the Multimedia Tools and Applications reviewing procedures.

Notes: when submitting your manuscript (https://www.editorialmanager.com/mtap/), at the step of “Select Article Type”, please indicate: “Ad Hoc Web Multimedia Analysis with Limited Supervision”.

Important Dates:

• Paper Submission: November 1, 2013
• First Notification: January 15, 2014
• Revised Manuscript: February 15, 2014
• Notification of Acceptance: April 1, 2014
• Final Manuscript Due: May 1, 2014


Guest Editors

 Dr. Yahong Han, Tianjin University, China, Email: yahong@tju.edu.cn
 Dr. Yi Yang, The University of Queensland, Australia, Email: yi.yang@uq.edu.au
 Dr. Jingdong Wang, Microsoft Research Asia, China, Email: jingdw@microsoft.com