An experimental evaluation (benchmarking some methods). Implement one or more existing algorithms and design an in-depth experimental evaluation and comparison that goes beyond what was described in the paper(s). Identify the relative strengths and weaknesses and include this in your report.
An interesting extension of prior work. In most cases, I'd recommend implementing the prior method yourself, rather than downloading implementations available online, as this gives you a better understanding of how the method works (and you can avoid mucking around with some one else's code). But this is not a hard and fast rule--if the extension is very significant you may use available code.
A new application of prior work. Apply a known technique to a new application domain, and evaluate its performance.
Create a new and better and maybe larger dataset for a problem and evaluate some baseline methods on it.
Develop a new solution (hopefully better!) to an existing problem.
Pose a new technical problem and solve it. Identify a new problem for which no known solution exists, devise a solution, and implement/test it.
You should turn in a one-page proposal describing your project. It should specify:
Project goals. Be specific. Describe the input and output.
Brief description of your approach. If you are implementing or extending a previous method, give the reference and web link to the paper.
Will you be using helper code (e.g., available online) or will you implement it all yourself?
Evaluation method. How will you test it? Which test cases will you use?
In case of two people on a project, mention who will do what?
Special equipment that will be needed. I may be able to help with cameras, tripods, etc.
Even if you choose one of the research ideas described in the G doc, still you need to submit a proposal.
Turn in the proposal via Webcourses by January 17 (11:59pm).
Each person will give a short (10-12 minute) PowerPoint presentation on their project to the class. I will assign a time slot to each person.
In the presentation, you should
provide motivation for your project, explaining why it is important and interesting,
explain your research questions,
provide evidence and your results,
draw conclusions.
You can use the computer projector (e.g. via powerpoint) for your talk. Try to make the presentation interesting (e.g. by including a demo).
Your presentations should be uploaded to Webcourses.
Prepare your final write up of the project according to CVPR formatting style which you can find here. Include everything in a .zip file. This .zip file should include at least your writeup (as either a PS or PDF file), the webpage (as HTML or PHP) and the source code of any programs you wrote for your project as well as collected data. Include other files if you feel they are appropriate, but obviously explain their relevance in a read file. You may submit a hard copy of these materials in person if you prefer, but online submission is preferred.
Do not be late with your submissions. This is not a homework you can turn in late at the cost of 5 points per day; I will be grading these pretty much immediately, since the final grades are due soon after the deadline. For additional guidance in structuring the report, look at the template structure of some CVPR papers. Not every project fits into this structure, and you might choose a different structure instead. It should roughly follow the format of a CVPR conference paper, including the following:
title, team members
short intro
related work, with references to papers, web pages
technical description including algorithm
experimental results
discussion of results, strengths/weaknesses, what worked, what didn't
future work and what you would do if you had more time
The projects will be graded in the same spirit as research papers are assessed (though I dont expect you to do original work at the same level). Here is a list of things that I will be looking for:
Originality
Relevance to course
Quality of arguments (are claims supported, how convincing are the arguments you bring forward)
Connection to earlier work
Clarity (how clearly are goals and achievements presented)
Scope/Size (in proportion to size of group)
Significance (are the questions you are asking interesting)
Relative to each other, the proposal will account for 15% of the grade, the presentation for 25%, and the report for 60%.
Feel free to come and talk to me about the various aspects of your project (in fact I strongly encourage you to) so that I can make sure that you are on the right track. Dont forget to have fun while doing it; its meant to be something that you are interested in doing!
Sample Projects & resources
You can find some sample projects as well as other helpful content related to this course here:
- http://cs231n.stanford.edu/project.html
- http://cvisioncentral.com/projects/
- http://www-cs.ccny.cuny.edu/~zhu/CSCI6716-2011s/ProjectTopicsSpring2011.pdf
- https://www.pinterest.com/explore/computer-vision/
- http://stackoverflow.com/questions/3080123/computer-vision-project-ideas
- http://vision.ucsd.edu/projects
- http://ci2cv.net/16623/final-project/
How should it look like:
http://cs.gmu.edu/~kosecka/cs482/lect-project.pdf [here is an example]