CS97 - Fall 2009 - Computer PerceptionProject GuidelinesProf. Doug [email protected] this course, you will experience the life cycle of an academic research project in the fieldof computer perception: brainstorming an idea, doing a literature review, conducting activeresearch, preparing a paper, and defending your work.You may work by yourself or with one other student.Deliverables1) Proposal (9/29)2) Proposal Update with Literature Review (10/8)3) Literature Review Presentation (30 minutes) (10/20-11/5)4) Full Manuscripts Due (8-pages) (11/10)5) Review Period (11/12-11/17) - Peer Reviews, Writing Center Review6) Conference Presentation (15 minutes) (12/3-12/5)7) Camera-Ready Conference Paper (8-pages) (12/10)(Bonus) Submit Paper to a Top-Tier Peer-Reviewed ConferenceAll documents must be prepared using Latex and be submitted as a PDF. The final paper willbe formatted using a standard latex stylesheet. Make sure there are no page numbers onyou pdf.Getting Started (Today)"If I've seen further, it is standing on the shoulders of giants" - Sir Isaac NewtonTwo ways to start your project are to:1)identify the problem you are interested in, explore existing solutions, propose asolution, and go...2)explore existing research, re-implement existing algorithms, re-run existingexperiments, play with existing data sets, and expand...You may also want to see last year's course proceedings. Please plan to meet with meearly and often to bounce your ideas.Proposal (9/29)"Only fools rush in" - ElvisPlanning what you are going to do takes some mental restraint since we often want to diveright in, but some good planning will give you direction and save you time and energy in theend.Format:A) Title, Authors, and Contact InfoB) Introduction: 1-2 paragraph summary of the problem you are solving, why it isinteresting, how you are solving it, and what conclusions you expect to draw from yourwork.C) 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 putyour solution in context and to support your solution.D) Proposed Solution: 3-4 paragraphs describing what you plan to do, how you plan todo it, how it solves the problem, and what types of conclusions you expect to draw fromyour work.E) Experiments: 1-3 paragraphs describing how you plan to evaluate your work. List theexperiments you will perform. For each experiment, explain how you will perform it andwhat you hope to conclude from the results.F) Requirements: software, data, test subjects, etc.G) Schedule: list the specific steps that you will take to complete your project, includedates and milestones. This is particularly important to help keep you on track, and to ensurethat if you run into difficulties completing your entire project, you have at leastimplemented steps along the way. Also, this is a great way to get specific feedback fromme.Proposal Update with Related Work Review (10/8)Refine you proposal based feedback, early experiments, and current progress. Your"Introduction" and "Related Work" should turn into the first two sections of your finalmanuscript.Also add an annotated bibliography of no less than 4 papers, where 2 are papers wehave not covered in class. You should both turn in theA) 1-page paper summaries for each referenced paperB) 2-3 paragraph summary of all the "Related Work" written in prose.Literature Review Presentation (45 minutes per person) (10/20-11/5)You will briefly present the results of your literature review to the class. Stated anotherway, you should give an informative talk on a specific topic. You should motivate the talkwith a quick introduction to your project, but focus on the research of others, and how itrelates to your work.Full Manuscripts Due (8-pages) (11/10)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 submittingto a conference. Your paper should have seven sections:A) Abstract: a 200-300 word summary of paper that stress the highlights. It is stronglyadvised that you write this section last!B) Introduction: the motivation for your work.C) Related Work: a summary of related work and specifically how it is similar to ordissimilar from your work.D) Methods: a description of your proposed solution. You should give enough detail thatsomeone could replicate your work. You may also want to include a figure to provide avisual representation of you work.E) Experimental Setup: a description of how you evaluate your work.F) Results: a thorough analysis of your results, including tables and graphs.G) Conclusions/Discussion: an explicit statement of what you can conclude from yourwork. What do you want the reader of your paper to walk away remembering? You may alsowant to describe some future directions for your work.H) Bibliography/ReferencesConference Presentation (15 minutes) (12/3-12/5)A concise description of you work that follows the same format as you manuscript. Your goalis to entice others to want to read you paper because it is interesting and useful.Camera-Ready Conference Paper (8-pages) (12/10)A polished and updated version of your manuscript based on the feedback from yourreviewers. You may also want to re-run experiments and improve your figures, tables andgraphs to maximize comprehensibility. This will be the verison that is include in the courseproceedings.BONUS: Submission to a (top-tiered, peer-reviewed) conferenceIf you submit you manuscript to a peer-reviewed conference and either (a) it is acceptedand published, or (b) I and another faculty member think that it should have been accepted,then you will get an A for the class.(If you are interested in graduate school, this might be your golden ticket