DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
UNIVERSITY OF CALIFORNIA, SAN DIEGO

Following is the schedule for the projects. You are encouraged to discuss your project throughout the quarter with the instructor and TA during their office hours.

(1) On or before Monday, May 1, at 11:59 PM, you must submit a project proposal in pdf format by email to the instructor and TA.  This should explain explicitly and clearly what you will do.  In particular, the proposal should include:

• a list of four to six milestones, and deadlines to achieve the milestones
• a list of questions to be answered during the project and discussed in the report
• if the project is experimental, which existing software you will use directly or build upon
• if the project is experimental, precisely which datasets you will use and where you can obtain them quickly
• a few recent and very closely related papers that you will build on, with full bibliographic data.

(2) On or before Monday, May 8, at 11:59 PM, you must submit a revised project proposal in pdf format by email to the instructor and TA. Since you will have to use LaTeX eventually, you should start now with the revised proposal.  In the first phase of the project, some important tasks include:

• formulating clear, sensible hypotheses to test,
• finding useful training/test sets,
• surveying closely related recent papers, and
• selecting and obtaining existing software, and developing new software.

(3) On or before Monday, June 5, at 11:59 PM, you must submit a complete, polished draft of your project report in pdf format by email to the instructor and TA.  The report should resemble as closely as possible a good submission for a computer vision or pattern recognition conference.  You must follow the CVPR formatting instructions. You may find Charles Elkan's notes on machine learning projects and reports helpful.

(4) On or before Monday, June 12 at 11:59 PM, you must submit the final version of your project report in pdf format by email to the instructor and TA. You must follow the CVPR formatting instructions. Project reports will be evaluated using these grading criteria.

While doing the project, remember that winning at research is similar to winning in many other fields of endeavor.

• Build on an idea that has been successful in previous work.
• Make the description of your work understandable, attractive, and memorable; pick catchy names.
• Keep the work simple.  Let the basic ideas shine through.
• More papers = more ways to have impact and be noticed.

Last update: April 1, 2017. Content adapted from previous CSE courses by Serge Belongie and Charles Elkan.