Advanced Visual Intelligence (AVI)
Advanced Visual Intelligence (AVI)
Course Code
DA5XXX
Credits
12 (4-0-0-0-8)
Lecture
Mon / Wed / Fri
TBD
TBD
Venue
TBD
Office Hours
By appointment
Prerequisites
Computer Vision, Image Processing, Linear Algebra, Probability, Python
About
This course covers fundamental and advanced topics in computer vision and visual intelligence. Students will develop a strong understanding of both classical methods and modern deep learning approaches, with emphasis on mathematical foundations and practical implementation.
Topics include feature extraction with CNNs and transformers, object detection and segmentation, generative models, video understanding, and vision-language models.
Topics include feature extraction with CNNs and transformers, object detection and segmentation, generative models, video understanding, and vision-language models.
Announcements
Jan 2027 Course website is live. Welcome to AVI! First lecture on [date].
Schedule
| # | Topic | Slides | Video | Reading | Assignment |
|---|---|---|---|---|---|
| 01 | Introduction to Computer Vision | Slides | Video | Notes | — |
| 02 | Image Formation and Cameras | Slides | Video | Ch. 2 | HW1 Out |
| 03 | Image Filtering and Edge Detection | Slides | Video | Paper | — |
| 04 | Feature Detection and Description | Slides | Video | Paper | HW1 Due |
| 05 | Deep Learning for Vision — CNNs | Slides | Video | Paper | HW2 Out |
| 06 | Object Detection | Slides | Video | Paper | — |
| 07 | Image Segmentation | Slides | Video | Paper | HW2 Due |
| 08 | ⚡ Mid-semester Exam | — | — | — | — |
| 09 | Transformers for Vision (ViT) | Slides | Video | Paper | HW3 Out |
| 10 | Generative Models — GANs, Diffusion | Slides | Video | Paper | — |
| 11 | Video Understanding | Slides | Video | Paper | HW3 Due |
| 12 | 3D Vision and Depth Estimation | Slides | Video | Paper | HW4 Out |
| 13 | Vision-Language Models | Slides | Video | Paper | — |
| 14 | Recent Topics + Guest Lecture | Slides | Video | — | HW4 Due |
| 15 | ⚡ End-semester Exam | — | — | — | — |
Teaching Assistants
| Name | Office Hours | Days | |
|---|---|---|---|
| TA Name 1 | 3:00 PM – 5:00 PM | Monday, Wednesday | |
| TA Name 2 | 2:00 PM – 4:00 PM | Tuesday, Thursday |
Grading
| Assignments (4 × 10%) | 40% |
| Mid-semester Exam | 25% |
| End-semester Exam | 35% |
Textbooks & References
- Primary Szeliski, Computer Vision: Algorithms and Applications (2nd ed., 2022) — Free PDF
- Primary Goodfellow et al., Deep Learning (2016) — Free online
- Reference Prince, Understanding Deep Learning (2023) — Free PDF
- Reference Forsyth & Ponce, Computer Vision: A Modern Approach
- Extra Hartley & Zisserman, Multiple View Geometry in Computer Vision (2nd ed.) — Website
- Extra Vidal, Ma & Sastry, Generalized Principal Component Analysis
- Extra Selected papers from CVPR, ICCV, ECCV, NeurIPS — linked in schedule above
Policies
Attendance
Not mandatory but strongly encouraged. Lecture slides and videos will be posted after each class.
Late Submissions
10% penalty per day. No submissions accepted after 3 days past the deadline.
Academic Integrity
All submitted work must be your own. Collaboration is encouraged for understanding concepts but not for writing code or answers. Use of AI tools must be explicitly disclosed.
Last updated: January 2026