Topics in Computer Science 1 (CSCI 4440U)
Human Action Recognition
Fall 2024
Faisal Qureshi
faisal.qureshi@ontariotechu.net

News

Nov 14, 2024
Midterm 2 will take place on Wednesday, Nov. 20. It will cover everything that we have discussed thus far, including the action recognition papers that we have read in this course.
Oct 22, 2024
Exercise on image based action recognition is now available.
Oct 11, 2024
Reading week, Oct 14 to Oct 18. No classes.
Oct 2, 2024
Midterm 1 will take place on Friday, Oct 4. It will cover material that we discussed in the "Classical Papers." It will also cover material covered up to Image Pyramids.
Sep 24, 2024
We will cover Laptev 2005 and Gorelick et al. 2007 papers.
Sep 17, 2024
We will cover Shuldt et al. 2004 paper.
Sep 12, 2024
Exercise on hidden markov models is now available.
Sep 10, 2024
We will cover Yamata et al. 1992 paper.
Sep 1, 2024
Website is now online.

Course Info

Syllabus

Lectures

Communication

https://piazza.com/uoit.ca/fall2024/csci4440u/home

Office hours

Lab times and locations are available here.

Canvas (requires login)

Labs and inclass exercises will be submitted through course canvas site.

Description

This course explores the techniques and methodologies for the recognition and analysis of human actions in images and video sequences. Designed for senior-year computer science students, the course covers both classical and contemporary approaches to action recognition, integrating theory with hands-on application. This course is particularly well-suited for students who are interested in pursuing research or careers in computer vision, artificial intelligence, or related fields.

The students will be exposed to a curated selection of influential papers that cover a range of methodologies for action recognition. Each week, students will read assigned papers, critically analyze them, and participate in in-depth class discussions to explore the strengths, weaknesses, and potential applications of the proposed methods.

In addition to the discussions, students will choose one or more papers to implement. This hands-on project will allow them to reproduce key results, experiment with variations of the methods, and possibly propose and test their own improvements. Through this process, students will gain a deeper understanding of the technical challenges and considerations involved in human action recognition, as well as experience in implementing and evaluating research ideas.

By the end of the course, students will have not only gained knowledge of the latest trends and techniques in action recognition but also developed practical skills in reading, critiquing, and implementing complex research papers.

Prerequisites

A working knowledge of machine learning and deep learning (CSCI 4050, CSCI 4052, or equivalent) and familiarity with basic computer vision techniques (CSCI 3240U, preferrably CSCI 4220U, or equivalent).

Topics

Learning Outcomes

By the end of this course, students will be able to:

  1. Understand and implement key algorithms and models used for action recognition in images and videos.
  2. Analyze and critique the strengths and weaknesses of various action recognition approaches.
  3. Apply advanced machine learning and deep learning techniques to solve real-world action recognition problems.
  4. Develop and evaluate action recognition systems using state-of-the-art tools and datasets.
  5. Stay abreast of the latest research and trends in the rapidly evolving field of action recognition.

Grading

A student must get 50% in the course project to pass the course. Furthermore, a student must get 50% in the two midterms to pass the course. Class attendence is not optional.

Important dates

Ontario Tech University’s academic calendar that lists important dates (and deadlines) is available at here.

Background

Papers

How to read a paper?

The list presented below is by no means complete.

Each week, a paper will be assigned to one or more students, who will lead the discussion on that paper.

Classic Papers

Deep Learning and Modern Approaches

Emerging Trends and Reviews

Course project

The course project is an independent exploration of a specific problem within the context of this course.

The topic of the project will be decided in consultation with the instructor.

Project grade will depend on the ideas, how well you present them in the report, how well you position your work in the related literature, how thorough are your experiments and how thoughtful are your conclusions.

Teams of up to two students are allowed.

Three minutes project videos

You are required to prepare a three-minutes video that provides an overview of your project. You may frame these videos as pitch videos to investors–having broad understanding of computers science, information technology, and artificial intelligence landscape–who are considering investing in your business that is built around the technology that you have developed in your project.

Final Report

For your final project write-up you must use ACM SIG Proceedings Template (available at the ACM website). Project report is at most 12 pages long, plus extra pages for references.

Alternately, you can use the following template (from “Tech Report ala MIT AI Lab (1981):

Resources

Textbook

We will use the following textbook to cover the fundamentals needed to understand the material covered in this course.