We offer 3 fully funded PhD fellowships on video understanding in autonomous vision.
Autonomous vision aims to solve computer vision problems related to autonomous driving. Autonomous vision algorithms achieve impressive results on a single image for various tasks, such as object detection and semantic segmentation, however, this success has not been fully extended to video sequences yet. In computer vision, it is commonly acknowledged that video understanding falls years behind single image. This is mainly due to two reasons: processing power required for reasoning across multiple frames and the difficulty of obtaining ground truth for every frame in a sequence, especially for pixel-level tasks such as motion estimation.
Based on these observations, there are two likely directions to boost the performance of video understanding tasks in autonomous vision: unsupervised learning and object-level reasoning as opposed to pixel-level reasoning. Following these intuitions, we offer positions in the following topics:
- Learning Object-Object Relations in Video
- Video Object Detection using Temporal Cues
- Unsupervised Motion Estimation & Segmentation in Video
Funding & Details
Ph.D. positions are fully funded (4500TL/month) by The Scientific and Technological Research Council of Turkey (TÜBİTAK). Koç University provides additional benefits including housing and meal allowances. We encourage applications from diverse backgrounds, both national and international, especially from underrepresented groups. In addition, M.Sc. (max. 2 years) and research internship (min. 6 months) applications will also be considered, please get in touch for further details.
We are looking for highly motivated students with an academic background in Computer Science and Engineering. The following skills are required:
- A good understanding of mathematical and algorithmic concepts in computer science.
- Decent programming skills and flexibility to learn new languages and concepts.
- A keen interest in machine learning and computer vision problems and algorithms.
- Good communication skills in English both written and spoken.
How to Apply
For further information and applying, please send an email to Fatma Güney by attaching your CV, transcript, and a paragraph explaining why you want to be considered for which position (max. half a page).