922 U3570: MULTIMEDIA ANALYSIS AND INDEXING (多媒體資訊分析與檢索)
Fall 2011 (14:20 ~ 17:20, Tuesday, CSIE RM#111)
Brief Introduction
With recent advances in communications, computers, and storage capacities, multimedia streams (i.e., videos, photos, music) are becoming increasingly important information sources. To deal with such enormous and diverse information, there arise challenging theoretical problems and strong industrial needs. We will preliminarily address such issues in this course. Students in the course will gain practical experiences through intensive hand-on homeworks. The topics include the following:
- Machine learning techniques such as graphical models, discriminative models, clustering approaches, etc.
- Multimedia (video/photo/music) feature representations
- Construction of high-level indices
- Content analysis and object recognition
- Multimedia indexing and retrieval
- Multimedia data mining
- Information exploitation in social media
- Summarization, personalization, and visualization of large-scale multimedia databases
- Standards and applications in video, photo, and medical image databases
- Benchmarks and evaluation metrics
Prerequisites: Background in image processing (or signal processing related courses), probability, and linear algebra. Experience with machine learning or statistical pattern recognition will be useful but not required.
Lecturer: Winston Hsu (office: R512, CSIE Building)
PAST Course Projects
Purpose: posting student projects in the course and recruiting project members
[Fall 2010]
[Fall 2009]
[Fall 2008]
- 朱慶瑜、洪韻蕙、陳怡伶 - NTU Walker
- 陳怡君、祁恆昱、龔建瑞 - Automatic Classification for Social Albums
- 呂鈺達、陳晉暉、呂哲安 - Visual Art - Peeping Montage
- 王政堯 - CBIR System For Clothes in Yahoo Auction
- 陳祺文、林芳而、黃彥傑 - Music Changes Your BORING film
- 謝良奇 - Annotation by Search
- 吳瑞欣、劉維倫 - Love Home
- 陳怡伶 、陳思佑、帥宏翰 - Google @ home
- 邱孟傑、李世強 - Funny Face
- 李文瑜、王聖媛、曾柏儂 - http://smilelibby.blogspot.com/
- 郭盈希、江建興 - Query expansion by applying hierarchical k-means and LSH
- 陳志帆 - Object detector by using shape information
- 白育姍、林志宏 - http://g.csie.org/~meconin/mmai/doku.php?id=start
- 劉峻瑋、鄭玨玉民- dress.com
- 鄭安容、黃琦雅 - http://lenaqueen.blogspot.com/
- 林晏慶、黃鴻昇、李長曄 - http://orz4mmai.pixnet.net/blog
- 曾賢舜、柯佳伶 - Tour Recorder
- 程瀚平、胡傳甡、邱柏叡 - http://dspgg.blogspot.com/
- 葉容瑜、林敬棋 - Cast Indexing for Talk Show Videos by Face, Cloth, and Background
- 黃柏瑜、賴韻芊 - http://lovelyzoo.blogspot.com/
- 林彥良、邱子軒、莊舒婷 - http://mmai08.blogspot.com/
- 陳俊瑋、何星翰、陳俊勳 - http://jstfunny.blogspot.com/
[Fall 2007]
- Wen-Kwang Tsao, Ying-Ho Liu, "Video Matching for video duplication protection"
- Jen-Wei Huang, Peter Chen, Chi-Yao Tseng, "Progressive Image eXtraction And Recommendation"
- Photo Kao, "Analysis of photo composition - lines and shapes"
- Chun-Chao Yen, Cheng-Te Li, Chun-Min Chang, "Painting Style"
- Tse-Wei Chen, "Image segmentation and Region-based Image Retrieval"
- Tien-Jung Chuang, roastfish, "Semantic Photo Synthesis"
- 郭姿玲, "Detecting and Tracking Moving Objects in Seguences of Color Images"
- 徐兆良, Intersection of Image-Music Searching System (交錯式圖片-音樂搜尋系統)
- Kai-Wei Chang, Cho-Jui Hsieh, "Hotter or Notte- Hot Ranker"
- Tyng-Ger Li, Chui-Chiu Kung, "P2P Recommendation System."
- Carson Liao, "video advertising."
- Chia-Ping Chen, Yen-Yu Lin, "Multi-modal Feature Fusion for Retrieval."
- 吳映嫻, 鄭逸廷, "music semantic query."
- 張銘修, 陳鴻銘, 張炳傑, "Sheep Dog."
- 林厚達, 張瀠文, "face recognition in personal albums."
- Chia-yu Wan, "Clustering and Organization for personal digital album."
- 李勁葦, 袁國訓, 陳鵬仁, "Dressing matcher."
[Spring 2007]
- Pei-yu (Peggy) Chi, "Cooking Video Indexing,"
"..I'd like to make use of video analysis and indexing techniques to improve [cooking] activity recognition..." 
- Terry Wu and Ming-Fang (Alpha) Weng, "Emotion-based Media Player Show,"
"..A novel method is exhibited here to show a fancy media player show, integrating auditory and visual perception..." 
- Yi-Hsuan (Eric) Yang and 馬智釗, "What are you looking at!,"
"..knowledge about where a person is looking provides important clues which enable a better understanding of the scene..." 
- Ting-ting Hu, "Environment Adaptive Picture Frame,"
"..做出ㄧ個虛擬畫框,由一個display + 1~2 個camera組成,當它進入某個環境時,會對攝影到的環境畫面做分析,可能包括顏色、線條、空間複雜度、object recognition等等,透過這些分析,去找一或多幅適合這個環境的畫,當使用者掛上牆壁時,適合的畫就顯示在display上..." 
- Hsin-Chien Huang, "2007 IPPR Contest,"
"..Face Detection in Video..." 
- Su-Chen Lin, 陳泓稜, 林與絜, 宋品頡, "Personalized Beauty Detection System,"
"..build a personalized model for beauty detection...by analyzing photos of persons who are recognized as beauties by a user" 
- Ya-Fan Su, Yu-Ching Lin, "Who's Singing?,"
"..we're interested in is the analysis of music video (or opera) structure..." 
- Chun F. Hsu, "People Detection based Embedded Cameras,"
"..Detect strangers at the front door or the entrance lane in the office..." 
- Janet Huang, Emily Chen, Evelyn Hung, "Photo Social Network Visualization,"
"We use the photo's metadata to build a personal social network, and use a novel way to visualize the information of the photos." 
- 謝其璋, 謝秉諺, 謝逵繹, "Singer Retrieval,"

- Chun-Kang Chen, Victor Hsieh, "Visual Layers for Semantic Concept Detection,"
"...we want to separate every key-frame into foreground and background to decrease the noise [for concept detection]."
- 周辰威, 葉仰庭, 王奕棠, "Billiards Video Analysis,"
"Since there are lots of research for Sports Analysis, we think that billiards analysis might be a interesting topic."