摘要：It is our great pleasure to organize a joint special issue in the Journal of Multimedia on selected outstanding papers from The Fourth IEEE International Workshop on Multimedia Information Processing and Retrieval (MIPR2008) and The First IEEE International Workshop on Data Semantics for Multimedia Systems and Applications (DSMSA2008), held in conjunction with The IEEE International Symposium on Multimedia (ISM2008) from December 15-17, 2008 in Berkeley, California, USA. The goal of MIPR2008 is to provide a forum for original research contributions and practical system design, implementation, and applications of multimedia information processing and retrieval. The goal of DSMSA2008 is to bring the semantic web community and multimedia computing community together and provide a forum for multidisciplinary research opportunities, with a focus on how to apply the Semantic Web technologies to the acquisition, generation, transmission, storage, and processing of multimedia information. These two workshops share the common goal of seeking high quality research contributions on multimedia information representation, analysis, retrieval and delivery, as well as practical solutions for the design and implementation of multimedia information management system. Among the papers presented in MIPR2008 and DSMSA2008, six papers were selected for inclusion in this special issue. The authors were asked to extend and revise their original workshop articles, and then each paper was reviewed by three referees. We are in great honor to accept the following papers: · "A Multimedia Data Management Approach with GeM-Tree" by Kasturi Chatterjee and Shu-Ching Chen · "A Multiple Instance Learning and Relevance Feedback Framework for Retrieving Abnormal Incidents in Surveillance Videos" by Chengcui Zhang, Wei-Bang Chen, Xin Chen, Lin Yang, and John Johnstone · "Multimodal speaker segmentation and identification in presence of overlapped speech segments" by Viktor Rozgic, Kyu Jeong Han, Panayiotis G. Georgiou and Shrikanth Narayanan · "A Mechanism for Propagation of Semantic Annotations of Multimedia Content" by Gilberto Zonta Pastorello Jr, Jaudete Daltio, and Claudia Bauzer Medeiros · "Baseball Digest Production System using Inductive Logic Programming" by Masaru Miyazaki, Masahiro Shibata, and Nobuyuki Yagi · "A Semantics and Data-Driven Biomedical Multimedia Software System" by Shih-Hsi Liu, Yu Cao, Ming Li, Pranay Kilaru, Thell Smith, and Shaen Toner The paper “A Multimedia Data Management Approach with GeM-Tree” by Kasturi Chatterjee and Shu-Ching Chen introduces a multimedia data management framework using a multidimensional tree-based index structure, which provides a generalized framework to organize and retrieve images and videos seamlessly. In the paper entitled “A Multiple Instance Learning and Relevance Feedback Framework for Retrieving Abnormal Incidents in Surveillance Videos”, the authors Chengcui Zhang, Wei-Bang Chen, Xin Chen, Lin Yang, and John Johnstone describe a method to incorporate coupled hidden Markov models (CHMM) with relevance feedback (RF) and multiple-instance learning (MIL) for retrieving various abnormal events in surveillance videos. Viktor Rozgic, Kyu Jeong Han, Panayiotis G. Georgiou and Shrikanth Narayanan describe a multimodal algorithm for speaker segmentation and identification in their paper “Multimodal Speaker Segmentation and Identification in Presence of Overlapped Speech Segments”. In the paper entitled “A Mechanism for Propagation of Semantic Annotations of Multimedia Content”, Gilberto Zonta Pastorello Jr, Jaudete Daltio, and Claudia Bauzer Medeiros introduce techniques for structuring and propagating semantic multimedia annotations, in parallel to the data transformation processes, to alleviate the overhead and decrease the errors introduced by manual annotation. The paper “Baseball Digest Production System using Inductive Logic Programming” by Masaru Miyazaki, Masahiro Shibata, and Nobuyuki Yagi propose a technique to acquire knowledge for baseball digest video production using an inductive inference approach. Shih-Hsi Liu, Yu Cao, Ming Li, Pranay Kilaru, Thell Smith, and Shaen Toner investigate the problem of how to develop a large-scale biomedical multimedia software system under Service-Oriented Architecture (SOA). We greatly appreciate the support from the Editor-in-Chief of the Journal of Multimedia (JMM) for giving us the opportunity to publish these high-quality articles in this special issue. We also thank the efforts of the authors, reviewers, and program committees who ensure the success and high quality of the programs of both workshops. We hope that you will enjoy reading this special issue.
关键词：Special Issue;Data Semantics;Multimedia Information Management
