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 driver assistance systems. The ultimate goal of Computer Vision is to imitate the great 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 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) Wednesday, 10:15-11:45, Room: 52-2-17 Contact person: Özgün Cicek Beginning: Wednesday, April 24, 2019, 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 based on the first meeting. If there are more interested students than places, places will be assigned based on your presence and motivation in the first meeting and priority suggestions of the HisInOne system. The date of registration is irrelevant. In particular, we want to avoid that people grab a topic and then jump off during the semester. 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 with instructions for a good presentation
Powerpoint template (optional)

Papers:

Date	Paper	Questions	Presenting student	Slides	Advisor
29.05	Video segmentation with language based detection	Questions	Ben Bausch	Slides	Maxim Tatarchenko
19.06	Self-supervised feature learning for future prediction	Questions	Stefan Moehrle	Slides	Jan Bechtold
26.06	Few-shot learning	Questions	Constantin Wittig	Slides	Tonmoy Saikia
03.07	Camera pose estimation	Questions	Lal Jose	Slides	Philipp Schroeppel
10.07	Future person activities and locations	Questions	Naya Baslan	Slides	Osama Makansi
17.07	Unsupervised learning of correspondence	Questions	Mohamed Feras Shaheen	Slides	Nikolaus Mayer
24.07	Cross-modal learning of video and text	Questions	Simon Ging	Slides	Mohammadreza Zolfaghari