Paper Presentation
In a group of 1/2 people
20/40 minutes presentation + 5/10 minutes discussion. Cover 2/3 - 3/5 papers.
Template:
Clear statement of the topic. Why is it important?
Backgrounds and previous literature;
Technical ideas and experiments of each paper;
Key contributions, strengths, and weaknesses of each paper (in your understanding);
Open research questions, future work, and/or potential applications
Slides are expected to be mostly visual (figures, animations, videos). Students are encouraged to search for relevant material, e.g., from the authors' webpage, project pages, etc. It's fine to use slides from the authors, but each slide that is not your own must be clearly cited.
Due dates: Send slides to instructor two days before your presentation to receive feedback.
Paper Review
At most one page in length. The selected papers should be related to your final project. It should include the following contents:
A summary of the paper;
Main contributions;
Strengths and weaknesses;
Experiments;
Future work, open research questions;
(Optional) Unclear points;
(Optional) Potential applications.
Ethics: According to university policy, using materials generated by AI (e.g., ChatGPT) without attribution is considered plagiarism.
Assignment
For each assignment, you need to fill in all the missing lines of codes, and succesfully run codes to get satiesfying running results. Keep the running results in *.ipynb and submit it to canvas.
Deadline: See course schedule for deadline of each assignment. You will be allowed a total of five late days per course. Each additional late day will incur a 10% penalty.
Ethics: Please do assignments individually. You can search the Internet resources to help you write, debug, and run the codes.
Points: You will get 10/10 points if your submission shows good running results. Otherwise, you will get fewer points depending on your written codes and running results.
Final Project
In a group of 1 - 2 people (2 is preferred, but higher workload for the project is expected)
Submit a project paper (4 pages), a project website (4 pages), and presentation slides (in pdf) to canvas.
Give a presentation of 10-15 minutes at the end of the semester
Topics are flexible, but should be related to this course, such as:
Proposing and addressing a new task/application;
Design and evaluation of a novel approach;
An extension of an approach studied in class;
In-depth analysis of an existing technique;
In-depth comparison of two related existing techniques.
Final project proposal presentation (5 points): You have 5 minutes to describe the following: (1) Problem statement: describe the problem; (2) Related work: briefly describe related papers. What will be unique about your project that previous work has not done? (3) Approach: describe your planned algorithm(s); (4) Experiments: Describe your planned experiments to evaluate the approach. (5) Others: Summarize any preliminary results.
Project website (15 points): A website that shows the idea, results, demos of the project. You can use any website platform that we can access, such as GitHub Page, Google Site, etc. Please include the following essentials on your website:
Project title
Your name(s)
Institution
A link to your PDF
Course name
An abstract and/or method overview
Experimental results and/or demos
Any other details that seem important
Below are some excellent website templates.
Example-1: https://cat3d.github.io/ source code: https://github.com/cat3d/cat3d.github.io
Example-2: https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/
Final project paper (10 points): A 4-page PDF that describes the following: (1) Introduction: summarize the problem, main idea, and results. Please include a link to your project website; (2) Related work: provide a detailed description of related papers. If you're proposing a new idea or extending an existing approach, what will be unique about your project that previous work has not done? If you're analyzing one or two related techniques, describe how they relate to other relevant work; (3) Approach: Describe in detail the algorithm(s) you employed. Clearly state the method's input and output, and any assumptions or design choices; (4) Experiments: describe the experiments you conducted to evaluate the approach. For each experiment, describe what you did, what was the main purpose of the experiment, and what you learned from the results. Provide figures, tables, and qualitative examples, as appropriate. (5) Conclusions: briefly summarize the main idea and results, discuss limitations and possible future work.
Template: CVPR2024 author kit
Final project presentation (10 points): A 10 minute presentation describing the contents above.