Department of Information Technology

Course on Classical and Modern Papers in Image Analysis

Once a month, according to the per-session selected 2h time-slot, we will discuss a paper within any of the interest fields of the PhD students at CBA. We will aim at (each month) alternating between a classic and a modern paper (from the last ~5 years, but established enough to have generated sufficient attention from the community). The lists of "articles that have stood the test of time" in the field of computer vision and pattern recognition and in the field of artificial intelligence
could provide inspiration.


See here!


Each session, one PhD student will be the discussion leader. Everybody is expected to read the paper, and submit a commentary (one paragraph) to the discussion leader. The commentary can be about anything in the paper: positive or negative criticism about the paper as a whole, or about something that is poorly explained, an interesting detail, a surprising solution, etc. During the discussion session, these points will be discussed in further detail, as well as other points that the discussion leader finds. The discussion leader is expected to give an overview of the paper; this overview can be two slides or a more in-depth explanation of the paper, this is up to the discussion leader.

0.3 ECTS will be awarded to all students who are actively present and submitted a commentary. 1 ECTS will be awarded to the discussion leader. Credits will be registered when needed, and only if 3 or more ECTS have been collected. Other researchers or students may participate in the seminars but will not be given course credits unless special arrangements are made in advance by their supervisors.


The discussion leader is responsible for all aspects of the organization of the discussion session. Please use this checklist when preparing for the session:

  • Choose a paper together with your supervisor.
  • Send an email to the it-vi2 (at) list stating when the session will be held, and which paper you chose. (Optionally, make a Doodle to find a time when as many as possible can participate and use the course Glip group to facilitate communication.) Attach a PDF copy of the paper to the email.
  • Reserve the seminar room (or schedule the session in some other way, e.g. via Zoom).
  • Update the schedule page with the relevant information. You can update the page by clicking on the "Edit this page" link in the rightmost column in the black bar at the bottom of the page.
  • Study the paper carefully and prepare a (very short or longer) presentation of the paper. Note that everybody is expected to study the paper, not just the discussion leader! Do not only look at the selected paper, but also take a look at earlier and/or later significant papers that are strongly related.
  • Collect the commentaries that other students should be sending you, and organize them in some way on your slides. These should be the basis for a discussion of the paper.
  • Print out this form and give it to your supervisor before the start of the session. Mark the names of the students that sent a commentary. Your supervisor is responsible for assigning credits to active students, signing the form and giving it to Natasa for archival. Electronic version of this document is also accepted.
  • Try to get a discussion going!
  • Pass the virtual baton on to the next person on the list. If this person cannot organize the session, it is their responsibility to find a replacement, and by swap with a course participant who did not already present during the ongoing academic year.

Discussion points

Possible topics for commentary and discussion:

  • Impact
    • What were the main pre-existing methods that the authors based their work on?
    • What later methods have been based on these results?
    • What have the authors accomplished with their results?
    • What have others accomplished with these results?
    • Have other people come up with the same ideas?
    • What would our field look like today without this paper?
  • Scientific content
    • How this content is presented
    • How the methods are described
    • How the methods are evaluated
    • How the results are described
    • How the results are discussed
  • Writing style
    • Does the abstract correctly represent the contents?
    • What is the reader assumed to know?
    • Overstatement/understatement of results
    • References
Updated  2020-06-21 22:47:00 by Natasa Sladoje.