KAIST Logo

School of Computing
Korea Advanced Institute of Science and Technology (KAIST)

CS688: Web-Scale Image Retrieval (Fall 2016)


CS688: Web-Scale Image Retrieval (Fall 2016)

Instructor: Sung-eui Yoon


When and where: 4:00-5:15pm on Tue. and Thur. at Room 2445 in the CS building
First class: Sep-1
Textbook: In-class handouts and ongoing draft on image search
Board: Noah board
Previous Board(Fall 2014): Noah board(2014)
Question Page: Question Submission
Paper Submission Page: Paper Summary Submission


Line

Outline

  • 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 recent conferences.
  • 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)
    A photo at the end of the class.
    Sep-1 (Th)
    Overview on the course and course policy
    Sep-6 (T)
    Sep-8 (Th)
    Keypoint localization
    Scale Invariant Region Selection and SIFT
    Code of Harris detector
    Code of Blob Laplacian
    Programming Assignment1
    Sep-13 (T)
    Intro to Object Recognition
    Sep-15 (Th)
    No class due to Chuseok Holiday
    Sep-20 (T)
    Sep-22 (Th)
    Bag-of-Words (BoW) Models for Local Descriptors Programming Assignment2
    PA2 dataset
    Pre-trained VGG16 model
    Sep-27 (T)
    Oct-29 (Th)
    Basic Classification and Learning Methods
    Deep Neural Nets and Features
    Programming Assignment3
    Spherical hashing
    Oct-4 (T)
    Oct-6 (Th)
    Image Search with Deep Learning Spatial Localization and Detection
    Oct-11 (T)
    Oct-13 (Th)
    No class due to the conference attendance
    Oct-18 (T)
    Hashing Techniques
    Web-Scale Imane Search and Their Application
    Oct-20 (Th)
    No calss (midterm week)
    Oct-25 (T)
    Mid-term exam
    Oct-27 (Th)
    Á¶ÀçÇü   °­¹Î±¸
    Nov-1 (T)
    ±Ç¿µ±â   ¾ÈÀÎ±Ô   Kent Sommer
    Nov-3 (Th)
    °­¹Îö   ÁÖ¼¼Çö
    Nov-8 (Th)
    ¹ÚÁß¾ð ÀÓ¿ìºó ÇÏÅ¿í
    Nov-10 (Th)
    Midterm presentation:
    1. Kent Sommer
    2. °­¹Î±¸
    3. ¹ÚÁß¾ð
    4. ÀÓ¿ìºó
    Nov-15 (T)
    Midterm presentation:
    1. ÇÏÅ¿í, ÁÖ¼¼Çö
    2. Á¶ÀçÇü, °­¹Îö
    3. ¾ÈÀαÔ, ±Ç¿µ±â
    Nov-17 (Th)
    No class due to the invided talk at KSA
    Nov-22 (T)
    Á¶ÀçÇü   ¹ÚÁß¾ð
    Nov-24 (Th)
    ±Ç¿µ±â   °­¹Îö
    Nov-29 (T)
    °­¹Î±¸   ÁÖ¼¼Çö
    Dec-1 (Th)
    ÀÓ¿ìºó   Kent Sommer
    Dec-6 (T)
    ÇÏÅÂ¿í   ¾ÈÀαÔ
    Dec-8 (Th)
    No class
    Dec-13 (T)
    Final presentation:
    1. Kent Sommer
    2. °­¹Î±¸
    3. ¹ÚÁß¾ð
    4. ÀÓ¿ìºó
    Dec-15 (Th)
    Final presentation:
    1. ÇÏÅ¿í, ÁÖ¼¼Çö
    2. Á¶ÀçÇü, °­¹Îö
    3. ¾ÈÀαÔ, ±Ç¿µ±â
    Line

    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

    Line

    Additional reference materials and links

  • WST665/CS770 homepage at fall of 2011
  • WST665/CS688 homepage at fall of 2012

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

  • CVPapers, Vision talk vidoes
  • Video lectures:
  • CNN for Visual Recognition, 2017
  • Basic machine learning, 2017
  • Digital photography, 2017
  • Recognitions, 2014
  • Image processing, 2014
  • Multimedia Information Retrieval
  • 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 2012. 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.