received Honorable Mention recognizing their excellent theoretical foundations and development of algorithms with outstanding performance gains and impact in highly relevant applications. Among them Martin
Robert Strzodka, graduated 2013 - thesis: Cache based Optimization of Stencil Computations An Algorithmic Approach), now at IBM Andreas Baak (co-advised wth Meinard Mueller, graduated 2012 - thesis: R
forms of supervision, which are easier and cheaper to collect. In this thesis, we aim to develop algorithms for learning to segment in images and videos with different levels of supervision. First, we develop [...] forms<br>of supervision, which are easier and cheaper to collect. In this thesis,<br>we aim to develop algorithms for learning to segment in images and videos<br>with different levels of supervision.<br>First
Therefore we ask how we can precisely define such challenges and how we can evaluate different algorithms on this open tasks? In this paper, we summarize and discuss such challenges as well as try to give [...] Therefore we ask how we can precisely define such challenges and how we can evaluate different algorithms on this open tasks? In this paper, we summarize and discuss such challenges as well as try to give [...] Therefore we ask how we can precisely define such challenges and how we can evaluate different algorithms on this open tasks? In this paper, we summarize and discuss such challenges as well as try to give
scans. Lastly, we evaluated different new address candidate sources, including target generation algorithms to improve the coverage of the current IPv6 Hitlist. We showed that a combination of different
evolution of this community over the last decade and understanding whether YouTube's recommendation algorithm steers users towards Incel-related videos. We collect videos shared on Incel-related communities [...] probability that a user will encounter an Incel-related video by virtue of YouTube's recommendation algorithm. Within five hops when starting from a non-Incel-related video, this probability is 1 in 5, which [...] evolution of this community over the last decade and<br>understanding whether YouTube's recommendation algorithm steers users towards<br>Incel-related videos. We collect videos shared on Incel-related communi
human gaze information into an attention-based long short-term memory architecture, and allows the algorithm to allocate attention selectively to both fixated and non-fixated image regions. Through evaluation [...] human gaze information into an attention-based long short-term memory architecture, and allows the algorithm to allocate attention selectively to both fixated and non-fixated image regions. Through evaluation [...] human gaze information into an attention-based long short-term memory architecture, and allows the algorithm to allocate attention selectively to both fixated and non-fixated image regions. Through evaluation
