In this course, you will experience the life cycle of an academic research project in the field of computer perception: brainstorming an idea, doing a literature review, conducting active research, preparing a paper, and defending your work.

You may work by yourself or with one other student.

1. Proposal (10/7)
2. Proposal Update with Literature Review (10/30)
3. Literature Review Presentation (30 minutes) (11/6-12/2)
4. Full Manuscripts Due (8-pages) (11/19)
5. Conference Presentation (15 minutes) (12/4-12/09)
6. Camera-Ready Conference Paper (8-pages) (12/11)

All documents must be prepared using Latex and be submitted as a PDF. You should use the NIPS style files so that everyone's paper have the same look and feel.

If you are new to Latex, I highly recommend The Not So Short Introduction to Latex as a starting reference. I would also recommend that you use Bibtex to organize your list of references. "If I've seen further, it is standing on the shoulders of giants" - Sir Isaac Newton

Two ways to start your project are to:

1. identify the problem you are interested in, explore existing solutions, and propose a solution, and go...
2. explore existing research, re-implement existing algorithms, re-run existing experiments, play with existing data sets, and expand...

You may also want to see my list of computer perception tasks. Please plan to meet with me early and often to bounce your ideas. "Only fools rush in" - Elvis

Planning what you are going to do takes some mental restraint since we often want to dive right in, but some good planning will give you direction and save you time and energy in the end.

Format:

1. Title, Authors, and Contact Info
2. Introduction: 1-2 paragraph summary of the problem you are solving, why it is interesting, how you are solving it, and what conclusions you expect to draw from your work.
3. Related Work: 1-2 paragraphs describing similar approaches to the one you propose. This need not be an exhaustive summary of related literature, but should be used to put your solution in context and to support your solution.
4. Proposed Solution: 3-4 paragraphs describing what you plan to do, how you plan to do it, how it solves the problem, and what types of conclusions you expect to draw from your work.
5. Experiments: 1-3 paragraphs describing how you plan to evaluate your work. List the experiments you will perform. For each experiment, explain how you will perform it and what you hope to conclude from the results.
6. Requirements: software, data, test subjects, etc.
7. Schedule: list the specific steps that you will take to complete your project, include dates and milestones. This is particularly important to help keep you on track, and to ensure that if you run into difficulties completing your entire project, you have at least implemented steps along the way. Also, this is a great way to get specific feedback from me.

Refine you proposal based on early feedback. This will include a more detailed schedule of tasks. Each task should be broken down into subtasks that can be accomplished in a day or so. Please indicate which tasks are done and which tasks you are actively working on now. This may include results from initial experiments, a description of the data you have collected, and/or a summary of your code base.

Also please add an annotated bibliography of no less than 4 papers, where 2 are papers we have not covered in class. For each paper in the the annotated bibliography should include a 4-5 sentence summary in paragraph form that

1. Summarizes the paper
2. Discusses how the paper relates to you research.

(The goal is to have the "Related Work" section of your final manuscript in place for this proposal update.) You will briefly present the results of your literature review to the class. You should motivate the talk with a quick introduction to your project, but focus on the research of others, and how it relates to your work. To communicate all the work that you have done, you will write a paper about your work. Your paper should look and feel like a paper that you are submitting to a conference. Your paper should have seven sections:

1. Abstract: a 200-300 word summary of paper that stress the highlights. It is strongly advised that you write this section last!
2. Introduction: the motivation for your work.
3. Related Work: a summary of related work and specifically how it is similar to or dissimilar from your work.
4. Methods: a description of your proposed solution. You should give enough detail that someone could replicate your work. You may also want to include a figure to provide a visual representation of you work.
5. Experimental Setup: a description of how you evaluate your work.
6. Results: a thorough analysis of your results, including tables and graphs.
7. Conclusions/Discussion: an explicit statement of what you can conclude from your work. What do you want the reader of your paper to walk away remembering? You may also want to describe some future directions for your work.
8. Bibliography/References

A concise description of you work that follows the same format as you manuscript. Your goal is to entice others to want to read you paper because it is interesting and useful. A polished and updated version of your manuscript based on the feedback from your reviewers. You may also want to re-run experiments and improve your figures, tables and graphs to maximize comprehensibility.