Seminar on Current Works in Computer Vision

Prof. Thomas Brox

The goal of Computer Vision is to imitate the flexibility and robustness of the human visual system and has a large impact on the success of artificial intelligence in general. Research has made significant progress in recent years particularly due to deep learning. Meanwhile computer vision is interweaved with other scopes of machine learning. In this seminar we will take a detailed look at various recent papers that span a broad range of hot topics. This includes particularly the emergence of properties from self-supervised learning and their analysis.
For each paper there will be three persons, who perform a more detailed investigation of the research paper and its background, and who will give a presentation. The presentation is followed by a discussion with all participants about the merits, limitations, and perspectives of the respective paper. You will learn to read and understand contemporary research papers, to give a good oral presentation, to ask questions, and to openly discuss a research problem.

Note that the mode of the seminar changes this semester to accomodate more slots for students. Rather than one student presenting a paper, three students will cover three different aspects, typically (but not necessarily) (1) the paper's historical background, related work, and motivation, (2) the core methodology including background methodology, and (3) experimental results and their assessment. In order to provide a strong overall presentation, you will also learn to work in a team, the assembly of which is out of your control. The success of the team effort is part of the grading.

Seminar: (2 SWS) Wednesdays, 14:00-15:30, 101-00-017/019 Contact person: Karim Farid Beginning: If you want to participate, attend the mandatory introduction meeting on April 22 14:00, register in HisInOne, and submit your paper preferences by April 27. Recommended semester: 6 (Bachelor), any (Master) Requirements: Background in computer vision Remarks: The language in this course is English. There is a strongly related Blockseminar on Deep Learning offered by apl Prof. Olaf Ronneberger from Google DeepMind. The introduction meeting will be jointly for both seminars. Topics will be assigned for both seminars via a preference voting. Only students who attended the introduction meeting and sent their paper preferences in time will be considered. Within this group, we follow the assignments of the HisInOne system. We want to avoid that people grab a topic and then jump off during the semester. Thus, please have a coarse look at all available papers to make an informed decision before you commit. The listed papers are not yet sorted by the date of presentation.If you don't attend the introduction meeting (or not send a paper preference) but choose this seminar together with only other overbooked seminars in HisInOne, you may end up without a seminar place this semester. All participants must read all papers and must attend all sessions.

---

Material:

Giving a good presentation
Proper scientific behavior

Powerpoint template for your presentation (optional)

Papers:

Date	Paper	Presenting students	Slides	Advisor
S1	V-JEPA
S2	Self-Flow
S3	Block-recurrent transformers
S4	Video generation with internal memory
S5	Reasoning with mental imagary
S6	Multimodal world models
S7	In-context algebra