| Aims |
This module lays the theoretical foundation for graduate students to do research in media computing. It covers the main theoretical issues common to various media research areas. These issues provide a general framework within which specific techniques in particular research areas can be understood.
This module focuses on the conceptual foundation common to various media computing topics. This common foundation is
|
| Mapping |
It gives rise to more sophisticated concepts including functions, fitting, transformations, registrations and structure discovery. These concepts are applied to the solving of high-level, structured media problems. For the purpose of illustration, this module will focus primarily on images, 3D models, temporal sequences of images and 3D models and music.
If you are interested in research or in solving novel high-level media computing problems, then this module is for you.
For frequently asked questions, please refer to the FAQ page. |
| |
| What this is Not |
This module is not about low-level processing at the levels of signal and features. So, it does not cover signal processing, codec, streaming, feature extraction, etc. It also does not cover classification, neural networks and deep learning, which have separate modules for them.
For frequently asked questions, please refer to the FAQ page. |
| |
| Objectives |
After taking this module, students will learn:
1. Knowledge: Mathematical models and algorithms for fitting, transformations, registrations and structure recovery.
2. Application: Apply knowledge to media problem solving, i.e., problem formulation and algorithm design. Programming is optional.
|
|
| Prerequisites |
Basic linear algebra and calculus, with a little bit of probability and statistics.
Background regarding images and 3D graphics models are useful but not absolutely necessary.
Applied linear algebra is used extensively in this module.
You need to work with algorithms in the form of linear algebra a lot.
If you do not have sufficient math background, then this module is not suitable for you.
Please download Exercise 1 and Exercise 2 from the Schedule page and try them.
If you cannot do these exercises by yourself, then this module is not suitable for you. |
| |
| Assessments |
| Assessment |
Individual
Weight |
Team
Weight |
| Online Quizzes |
10% |
|
| Assignments |
45% |
|
| Team Project |
|
35% |
| Participation |
10% |
|
| Total |
65% |
35% |
Please refer to LumiNUS CS5240 for more details. |
| |
| Lecturer |
A/Prof. Leow Wee Kheng
Email: leowwk@comp.nus.edu.sg
Office: AS6 #05-07 |
| |
|
