Seminar on Current Works in Computer Vision

Prof. Thomas Brox

Computer Vision is a very active research field with many practical applications, for instance in quality control, robotics, or driving assistance systems. The ultimate goal of Computer Vision is to imitate the capabilies of the human visual system, allowing the computer not only to record images but also to interpret them. Research has made significant progress in recent years and particularly deep learning has helped improve on many tasks and approach new ones.
In this seminar we will take a detailed look at some of the most interesting recent works. For each paper there will be one person, who performs a more detailed investigation of a research paper and its background and who will give a presentation. The presentation is followed by a discussion with all participants about the merits and limitations 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.

Seminar: (2 SWS) Thursday, 10-12 (hct), Room: 52-2-17 Contact person: Özgün Cicek Beginning: Thursday, October 18, 2018, 10:15 Allocation of seminar topics ECTS Credits: 4 Recommended semester: 6 (Bachelor), any (Master) Requirements: Background in computer vision Remarks: The language in this course is English. There is a related Blockseminar on Biomedical Image Analysis offered by apl Prof. Olaf Ronneberger from Google DeepMind. Topics will be assigned for both seminars in the first meeting. Please register for one of the seminars online before the first meeting. Places will be assigned based on presence and interest in the first session. The date of registration is not of relevance. Be aware that 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 in the first meeting. The listed papers are not yet sorted by the date of presentation. Important! Please get in contact with your advisor as soon as possible, and at least 4 weeks before your presentation Submit your presentation outline to your advisor at least 2 weeks before your presentation and meet with your advisor. Submit your presentation slides to your advisor at least 1 week before your presentation and meet again. All participants must read all papers and answer a few questions. The questions will be available in the 'Questions' column of the table below at least one week before the corresponding presentation. The answers must be sent to the advisor of the paper before the paper is presented.

---

Slides of first session with instructions for a good presentation
Powerpoint template (optional)

Papers:

Date	Paper	Questions	Presenting student	Slides	Advisor
13.12.2018	Deep network architectures	Questions	Lukas Boschert	Slides	Tonmoy Saikia
10.01.2019	Bilevel learning	Questions	Anushe Glushik	Slides	Yassine Marrakchi
17.01.2019	Learned 6D pose estimation	Questions	Hanna Siemund	Slides	Nikolaus Mayer
24.01.2019	Facial animation from a single image	Questions	Simon Ging	Slides	Mohammedreza Zolfaghari
31.01.2019	Semi-supervised learning	Questions	Mariana Ferrandon	Slides	Sudhanshu Mittal
07.02.2019	Visual meta-learning for planning and control	Questions	Samuel Roth	Slides	Artemij Amiranashvili