Div. of Web Science and Technology
Department of Computer Science
Korea Advanced Institute of Science and Technology (KAIST)

WST665/CS770A: Topics in Computer Vision (Fall 2011) <br> Web-Scale Image Retrieval

WST665/CS770: Topics in Computer Vision (Fall 2011)
Web-Scale Image Retrieval

Instructor: Sung-eui Yoon

When and where: 11:00-12:15pm on Mon. and Wed. at Room 4448 in the CS building
First class: Sep-5 (please come to first class for more information)
Please refer to the first lecture slide for other course information
Textbook: In-class handouts (no textbooks)



  • Course overview
  • Lectures and tentative schedule
  • Student presentations
  • Additional reference materials
  • Line

    Course overview

    We extract feature points between two similar images and match them, followed by overlaying them together based on the matched points in the bottom row.

    Thanks to rapid advances of digital camera and various image processing tools, we can easily create new pictures, images, and videos for various purposes. This in turn results in a huge amount of images in the internet and even in personal computers. For example, flickr, an image hosting website, contains more than five billion images and flickr members update more than three thousands image every minute.

    These huge image databases pose numerous technical challenges in terms of image processing, searching, storing, etc. In this class we will discuss various scalable techniques for web-scale image/video databases and novel applications that can utilize such data.

    In summary, what you will get at the end of the course:

  • Broad understanding on image/video retrieval techniques
  • In-depth knowledge on recent methods that can handle web-scale data
  • Study novel applications that utilize web-data
  • What you will do:

  • Choose and present a few papers from a paper list
  • Final project: come up with your own idea related to the topic, (optionally) implement it to improve the state-of-the-art techniques
  • Mid-term exam: reviewing basic image retrieval methods
  • Line

    Lecture schedule (subject to change)

    # of lecture, date Topics and slides Related material(s)
    Sep-5 (Mon) Overview on the course and course policy Q and A for the course (frequently updated)
    Sep-7 (Wed) Keypoint localization
    No class (Chuseok)
    Sep-14 (Wed) Scale-invariant region detector
    Sep-19 (Mon) Descriptors PA1: get to know basic libraries
    Sep-21 (Wed) Intro. to object detection
    Sep-26 (Mon) Bag-of-Word approach PA2: basic image retrieval, Image database
    Sep-28 (Wed) No class (attending a robotics conf.)
    Oct-5 (Wed)
    Oct-10 (Mon)
    Oct-12 (Wed)
    Recent image retrieval systems
    Oct-17 (Mon)
    Oct-19 (Wed)
    Novel applications, Part 1, 2, 3, 4
    Oct-24 (Mon) Mid-term exam
    Oct-31 (Mon) Lin, Thanh (Student presentations 1)
    Nov-3 (Wed) Youngwoon Lee, MinHaeng Lee
    Nov-7 (Mon)
    Nov-9 (Wed)
    No class (due to attending ICCV 2011) (15 min. more extensions to other classes as make-up classes
    Nov-14 (Mon) TaeHyun Oh, SeungWook Paek, JiHae Hong
    Nov-16 (Wed) Junsu kim, JongH. Lee, DongGun Lee
    Nov-21 (Mon) HaMyung Park, OhSung Kwon, JungIn Lee
    Nov-23 (Wed) Mid-term project presentations Project Guidelines
    Nov-28 (Mon) Invited talk (schedule will be changed)
    Nov-30 (Wed) Jihae Hong, MinHaeng Lee, TaeHyun Oh
    Dec-5 (Mon) DongGun Yu, JunSu Kim, JongH. Lee
    Dec-7 (Wed) Lin, JungIn Lee, OhSung Kwon
    Dec-12 (Mon) SeungWook Paek, Thanh, HaMyung Park, YoungWoon Lee
    Dec-14 (Wed) No class
    Dec-19 (Mon) Final presentation will be held at 제2강의실 (2112호) at the CS dept.

    Student presentations and reports

    For your presentations, please use the this powerpoint template; paper presentation guideline is available.

    For your final report, please use the this latex template


    Additional reference materials and links

    Computer vision resources (papers, code, datasets, etc.):

  • CVPapers
  • VLFeat: contains popular computer vision algorithms including SIFT, MSER, k-means, hierarchical k-means, agglomerative information bottleneck, and quick shift
  • Paper search:

  • Google scholar
  • Tim Rowley's graphics paper collections
  • Ke-Sen Huang's graphics paper collections
  • Line

    Acknowledgements: The course materials are based on those of Prof. Fei-Fei Li, Stanford. Thank you so much! Line

    Copyright 2011. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the author.

    This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.