Prior Knowledge

  • Familiarity with computer systems and databases at an undergraduate level
  • Knowledge of AI at the application level, and systems for AI recommended but not required

Course Goals

  • Understand recent developments at the intersection of AI & visual analysis
  • Read, analyze, discuss, and present academic and industry papers
  • Propose and execute a semester-long research project
  • Present your research and write a research paper on your project

Course Structure

  • Prior to the start of each class, you will submit a paper review on Gradescope covering:
    • A summary of the paper
    • Its key strengths and weaknesses
    • An assessment of its evaluation
    • A discussion topic for the paper’s lecture
  • 1-2 students will give an overview of the assigned paper, then leading a discussion around open questions, future work, and related topics
  • Guest lectures will be followed by summary and insight reviews to be submitted on Gradescope

Feedback

Throughout the semester, we want to know what is working, and what isn’t. We have created a thread on Ed for this.

To make your comments anonymous and visible only to the teaching staff, please check the following boxes:

ed

You are also welcome to email the instructor with feedback as well.

Grading

Assignment weight breakdown

55%: Term project

  • 10%: Proposal (5% presentation, 5% report)
  • 10%: Midterm presentation
  • 35%: Final (15% presentation, 20% report/software)

20%: Research paper presentations

20%: Paper reviews and guest lecture summaries

5%: Participation (in-class questions and discussion)

Grading scale

The default grading scale is the following:

  • A: >=90%
  • B: [80%, 90%)
  • C: [70%, 80%)
  • D: [60%, 70%)

Passing grades are C or higher.

The instructor reserves the right to adjust grade thresholds downward to benefit students, based on class performance. Thresholds will not be raised under any circumstances.

Course Policies

Late submissions and extensions

Each student will be given four “late” tokens for the term

  • Paper reviews and guest lecture summaries: 1 token per late day
  • Proposal report: 2 tokens per late day
  • All else: cannot use tokens (including final report)

Academic integrity and honesty

Georgia Tech aims to cultivate a community based on trust, academic integrity, and honor. Students are expected to act according to the highest ethical standards. Review Georgia Tech’s Honor Code and the student Code of Conduct.

Any student suspected of cheating or plagiarizing on a quiz, exam, or assignment will be reported to the Office of Student Integrity, who will investigate the incident and identify the appropriate penalty for violations.

Collaboration

For paper reviews and guest lecture summaries, students are encouraged to discuss ideas and interpretations with peers but must independently write their own submissions. All written work must reflect the student’s individual understanding and analysis.

Generative AI usage

You should treat generative AI analogously to assistance or collaboration from another person. In other words, you may use generative AI tools (ChatGPT, Cursor, Claude, etc.). However, using generative AI tools to substantially complete an assignment (e.g., directly writing your paper reviews or writing your proposal/final report) is not permitted. Students are required cite/acknowledge extensive use of generative AI tools beyond incidental use, such as light editing, grammar suggestions, and programming aids. [Adopted from Mark Zhao]

Accommodations for students with disabilities

If you are a student with learning needs that require special accommodation, contact the Office of Disability Services (404-894-2563) as soon as possible to make an appointment to discuss your special needs and to obtain an accommodations letter. Please also e-mail me as soon as possible in order to set up a time to discuss your learning needs.

Inclement weather and digital learning days

For a Digital Learning Day, all class activities will be held remotely via video conferencing. The instructors will share pertinent video conferencing links via a Canvas announcement and/or through email.

Wellness resources

A list of resources for graduate students is given on the Office of Graduate and Postdoctoral Education website. Specific information for current graduate students includes:

  • Academic Resources such as the Communications Center, Language Institute, Library, Catalog, Registrar, resources for conducting research, Advocacy and Conflict Resolution resources, and how to manage unexpected situations that may impact your academic performance
  • Student Resources such as Campus Services, Child Care/Family programs, Health & Wellness, Career Services, and the Student Resource Guide
  • Professional Development such as the programming from the Career Center and other professional development resources and events

At Georgia Tech, we are concerned about your overall physical, social, and mental well-being. A comprehensive list of wellness related resources has been compiled and maintained by the Office of the Vice President for Student Engagement and Well-being.

More resources are also available through the Learning Well Initiative.