Özgün Çiçek

TL;DR: Experiments show that the reachability prior combined with multi-hypotheses learning improves multimodal prediction of the future location of tracked objects and, for the first time, the emergence of new objects.

TL;DR: A new network architecture is introduced that enforces complementary hypotheses and provides uncertainty estimates efficiently within a single forward pass without the need for sampling or ensembles and demonstrates high-quality uncertainty estimates that clearly improve over previous confidence measures on optical flow.

TL;DR: In this paper, the authors explore how deep learning (U-Net) can automate segmentation tasks in various imaging modalities, and quantify phenotypes of altered renal, neural and craniofacial development in Xenopus embryos in comparison with normal variability.

TL;DR: This work proposes a network module for learning embeddings of the environment's dynamics in a self-supervised way to take the ambiguities and high variances in the future activities into account, using a multi-hypotheses scheme that can represent multiple futures.

TL;DR: In this paper , the authors found that the actin cytoskeleton is highly dynamic during early development of multiciliated cells and that subapical actin filaments are nucleated from the distal tip of ciliary rootlets.