16-824: Visual Learning and Recognition |
Spring 2021 |
|
Course Overview
Summary: A graduate course in Computer Vision with emphasis on representation and reasoning for large amounts of data (images, videos and associated tags, text, gps-locations etc) toward the ultimate goal of Image Understanding. We will be reading an eclectic mix of classic and recent papers on topics including: Theories of Perception, Mid-level Vision (Grouping, Segmentation, Poselets), Object and Scene Recognition, 3D Scene Understanding, Action Recognition, Contextual Reasoning, Image Parsing, Joint Language and Vision Models, etc. We will be covering a wide range of supervised, semi-supervised and unsupervised approaches for each of the topics above.
Prerequisites: While there are no formal prerequisites, this course assumes familiarity with computer vision (16-720 or similar) and machine learning (10-601 or similar). If you have not taken courses covering this material, consult with the instructor.
Course Information
Logistics
- All Zoom/Gather links are posted in Piazza
- Class meetings: Mon, Wed 12:20-1:40pm EST
- Deepak's office hours: Wednesday 1:40-2:30pm EST
- TAs' office hours: Mon 4-5pm EST (Sudeep), Wed 7-8pm EST (Sanil), Fri 4.30-5.30pm EST (Ziyan)
- Contact instructors via private post on Piazza
Workload
Students will be expected to:- Attend all classes and participate in discussion.
- Submit all homework assignments on time. Collaboration is allowed so long as final work is done independently, and all collaborators are acknowledged.
- Complete final (group) project:
- Students will complete an independent research project in groups of 2-3
- Write-up findings in blog post
- Present project in class, and publish 5 minute YouTube presentation online
Grading Policy
- 10%: Class participation
- 45%: Group Project (blog post included)
- 45%: Homework Assignments (10%, 15%, 20% respectively)
Collaboration Policy
For each assignment, TAs will not be looking over any of your code before the assignment deadline. You may discuss code with classmates. Please list collaborators whom you discussed with in the assignment write-up.
Late Policy Policy
You have 7 late days which you can use over the course of the semester. Any assignment submitted after all 7 late days are used will receive 0 credit.