CS688: Large-Scale Image & Video Retrieval (Spring 2021)
Instructor: Sung-eui Yoon
- When: 4:00-5:30 pm on Tue. and Thu.
- Where: Lecture room 3445, Information Science and Electronics Bldg (E3)
- First class: March 2
- Textbook: In-class handouts and ongoing draft (pdf), ongoing draft (web) on image search
- Board: KLMS
- Question Page: Question Submission
- Paper Submission Page: Paper Summary Submission (before every Tue. class)
- Student Talk Evaluation Page: Student Talk Evaluation Submission
- Project Evaluation Page: Project Evaluation Submission
- Course video page: youtube list
Outline
- Course overview
- Lectures and tentative schedule
- Student presentations
- Additional reference materials
Course overview
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
Lecture schedule (subject to change)
| Date | Topics and slides | Related material(s) |
|---|---|---|
|
Overview on the course and course policy | |
|
Classical keypoint localization | |
|
Scale Invariant Region Selection and SIFT | |
|
||
|
Deep Neural Nets and Features | |
|
Convolutional Neural Networks |
|
|
Presentation Schedule | |
|
Bag-of-Words (BoW) Models for Local Descriptors | |
|
Inverted Index Presentation Schedule (Updated) |
|
|
||
|
Hashing Techniques | |
|
CNN based Image Search | Programming Assignment 2 |
|
||
|
||
|
Mid-term exam | |
|
||
|
Students Presentation I: 1. Seebin Lee 2. Woojae Kim |
|
|
reserved | |
|
Students Presentation I: 1. Mincheol Kim 2. Yoonki Cho |
|
|
reserved | |
|
Students Presentation I: 1. Dongjun Kim |
|
|
reserved | |
|
Mid-term presentation: 1. Woojae Kim 2. Mincheol Kim |
|
|
Mid-term presentation: 1. Sebin Lee 2. Dongjun Kim/Yoonki Cho |
|
|
Students Presentation II: 1. Yoonki Cho 2. Woojae Kim |
|
|
Students Presentation II: 1. Sebin Lee 2. Dongjun Kim |
|
|
Students Presentation II: 1. Mincheol Kim |
|
|
reserved | |
|
Final presentation: 1. Woojae Kim 2. Mincheol Kim |
|
|
Final presentation: 1. Sebin Lee 2. Dongjun Kim/Yoonki Cho |
|
|
Final exam period |
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
- CS688 homepage at spring of 2020
- CS688 homepage at fall of 2018
- CS688 homepage at fall of 2016
- WST665/CS688 homepage at fall of 2014
- WST665/CS688 homepage at fall of 2012
- WST665/CS770 homepage at fall of 2011
Computer vision resources (papers, videos, code, datasets, etc.):
- CVPapers, Vision talk videos
- Video lectures:
- 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:
Acknowledgements: The course materials are based on those of Prof. Fei-Fei Li, Stanford. Thank you so much!