Overview
There will be two tracks for course projects: (1) graduate and (2) undergraduate (see details below). Projects should be completed in groups of two or three. If you want to pursue a project individually, please talk to me beforehand. If you do not have access to GPUs, please also contact me.
Graduate Track: The graduate track is aimed toward graduate students pursuing research requiring video understanding. For this project track, students can propose any project that involves video recognition in any area of interest. Undergraduate students interested in video recognition research who have concrete ideas of what they want to pursue are also welcome to pursue this track but should talk to me before doing so.
Undergraduate Track: The undergraduate track is aimed toward undergraduate students who want to gain more experience with the existing video recognition tools. Projects in this track will require students to apply existing video recognition tools to 5 of their selected video-related applications (e.g., action recognition, optical flow, object tracking, video object segmentation, video generation, etc.). Specifically, for each of the 5 applications, the students will select several videos (e.g., personal or from the Internet) and apply a model of their choice to investigate its effectiveness at a particular task (e.g., action recognition, tracking, etc.). For each application, the students will be asked to provide 3 success instances (i.e., the model did what it was expected to do) and 3 failure instances (i.e., the model failed). This will amount to 15 success and 15 failure instances across 5 applications. Afterward, the students will document their experiences and provide a detailed analysis and insights about the results. Graduate students who think that the undergraduate track fits their background and interests better are welcome to pursue this track. Below are a few potentially relevant pointers to the existing video analysis tools/demos:
Project Proposal (10%) (Presentations on 10/2/23 & 10/4/23, Report Due 10/8/23)
You can use the following templates (graduate and undergraduate) to generate your proposal reports. Your initial proposal should cover the following items:
Graduate Track:
-
The problem that you are trying to solve.
-
The motivation behind the problem.
-
Your proposed approach, and how it relates to prior work.
-
The experiments that you plan to conduct.
-
The datasets that you plan to use.
Undergraduate Track:
-
The 5 applications that you selected.
-
The 5 video tools you will experiment with and a brief technical description of each tool.
-
The data that you plan to use.
-
What you expect to discover.
Project Milestone (10%) (Presentations on 10/30/23 & 11/1/23, Report Due 11/5/23)
You should extend your project proposal to include the following:
Graduate Track:
-
A preliminary set of results.
-
Your analysis of those results.
-
Additional experiments that you plan to run.
Undergraduate Track:
-
A preliminary set of results (i.e., success and instance cases).
-
Your analysis of those results.
Final Presentation (20%) (Presentations on 12/4/23 & 12/6/23, Report Due 12/10/23)
You should extend your project milestone to include:
Graduate Track:
-
The final set of results.
-
Your analysis of those results.
-
Your overall conclusions and findings from the project.
Undergraduate Track:
-
The final set of results (15 success and failure instances for 5 applications).
-
Your analysis of those results.
-
Your overall conclusions and findings from the project.