Advances in Multimedia Modeling

1. Front Matter

   PDF

2. Media Understanding

   1. A Novel Approach for Filtering Junk Images from Google Search Results

      • Yuli Gao, Jianping Fan, Hangzai Luo, Shin’ichi Satoh

      Pages 1-12

   2. Object-Based Image Retrieval Beyond Visual Appearances

      • Yan-Tao Zheng, Shi-Yong Neo, Tat-Seng Chua, Qi Tian

      Pages 13-23

   3. MILC2: A Multi-Layer Multi-Instance Learning Approach to Video Concept Detection

      • Zhiwei Gu, Tao Mei, Jinhui Tang, Xiuqing Wu, Xian-Sheng Hua

      Pages 24-34

3. Poster I

   1. An Implicit Active Contour Model for Feature Regions and Lines

      • Ho-Ryong Jung, Moon-Ryul Jung

      Pages 35-44

   2. New Approach for Hierarchical Classifier Training and Multi-level Image Annotation

      • Jianping Fan, Yuli Gao, Hangzai Luo, Shin’ichi Satoh

      Pages 45-57

   3. Extracting Text Information for Content-Based Video Retrieval

      • Lei Xu, Kongqiao Wang

      Pages 58-69

   4. Real-Time Video Surveillance Based on Combining Foreground Extraction and Human Detection

      • Hui-Chi Zeng, Szu-Hao Huang, Shang-Hong Lai

      Pages 70-79

   5. Detecting and Clustering Multiple Takes of One Scene

      • Werner Bailer, Felix Lee, Georg Thallinger

      Pages 80-89

   6. An Images-Based 3D Model Retrieval Approach

      • Yuehong Wang, Rujie Liu, Takayuki Baba, Yusuke Uehara, Daiki Masumoto, Shigemi Nagata

      Pages 90-100

   7. ‘Oh Web Image, Where Art Thou?’

      • Dirk Ahlers, Susanne Boll

      Pages 101-112

   8. Complementary Variance Energy for Fingerprint Segmentation

      • Z. Hou, W. Y. Yau, N. L. Than, W. Tang

      Pages 113-122

   9. Similarity Search in Multimedia Time Series Data Using Amplitude-Level Features

      • Johannes Aßfalg, Hans-Peter Kriegel, Peer Kröger, Peter Kunath, Alexey Pryakhin, Matthias Renz

      Pages 123-133

   10. Sound Source Localization with Non-calibrated Microphones

       • Tomoyuki Kobayashi, Yoshinari Kameda, Yuichi Ohta

       Pages 134-143

   11. PriSurv: Privacy Protected Video Surveillance System Using Adaptive Visual Abstraction

       • Kenta Chinomi, Naoko Nitta, Yoshimichi Ito, Noboru Babaguchi

       Pages 144-154

   12. Distribution-Based Similarity for Multi-represented Multimedia Objects

       • Hans-Peter Kriegel, Peter Kunath, Alexey Pryakhin, Matthias Schubert

       Pages 155-164

   13. Creative Media

       1. A Multimodal Input Device for Music Authoring for Children

          • Yasushi Akiyama, Sageev Oore

          Pages 165-174

       2. Free-Shaped Video Collage

          • Bo Yang, Tao Mei, Li-Feng Sun, Shi-Qiang Yang, Xian-Sheng Hua

          Pages 175-185

       3. Aesthetics-Based Automatic Home Video Skimming System

          • Wei-Ting Peng, Yueh-Hsuan Chiang, Wei-Ta Chu, Wei-Jia Huang, Wei-Lun Chang, Po-Chung Huang et al.

          Pages 186-197

       4. Using Fuzzy Lists for Playlist Management

          • François Deliège, Torben Bach Pedersen

          Pages 198-209

Welcometothe14thInternationalMultimediaModelingConference(MMM2008), held January 9–11, 2008 at Kyoto University, Kyoto, Japan. MMM is a leading international conference for researchersand industry practitioners to share their new ideas, original research results and practical development experiences from all multimedia related areas. It was a great honor to have MMM2008, one of the most long-standing m- timedia conferences, at one of the most beautiful and historically important Japanese cities. Kyoto was an ancient capital of Japan, and was and still is at the heartofJapanesecultureandhistory. Kyotoinwintermaydistinctivelyo?er the sober atmosphere of an ink painting. You can enjoy old shrines and temples which are designated as World Heritage Sites. The conference venue was the Clock Tower Centennial Hall in Kyoto University, which is one of the oldest universities in Japan. MMM2008 featured a comprehensive program including three keynote talks, six oral presentation sessions, and two poster and demo sessions. The 133 s- missions included a large number of high-quality papers in multimedia content analysis, multimedia signal processing and communications, and multimedia applications and services. We thank our 137 Technical Program Committee members and reviewers who spent many hours reviewing papers and prov- ing valuable feedback to the authors. Based on the 3 or 4 reviews per paper the Program Chairs decided to accept only 23 as oral papers and 24 as poster papers, where each type of presentation could in addition present the work as a demo. The acceptance rate of 36% follows the MMM tradition of ful?lling fruitful discussions throughout the conference.

• 3D modeling
• 3D retrieval
• HCI
• active learning
• concept ontology
• content analysis
• data compression
• digital cinema
• digital music creation
• distributed video coding
• emotion detection
• image annotation
• image compression
• modeling
• multimedia

Policies and ethics