Luc Van Gool

TL;DR: An approach to anthropometry based on a random regression forest trained from local depth cues, whose objective function directly relies on both the image-level prediction, as well as on the local predictions' reliability, has the advantage of being both computationally highly efficient and accurate.

TL;DR: VarCity - the Video is a short documentary-style CGI movie explaining the main outcomes of the 5-year Computer Vision research project VarCity, driven by some ad-hoc technical developments but more importantly of detailed and abundant communication and agreement on common best practices.

TL;DR: This paper introduces a problem of online domain adaptation for semantic segmentation, which involves producing predictions for and, at the same time, continuously adapting a model to new frames of target domain videos, and proposes a novel method which utilizes unsupervised structure-from-motion cues as the primary source of domain adaptation.

TL;DR: A new evaluation metric proposed by Zhang 2020rethinking, i.e., IoU curve, is introduced to measure the quality of the generated object localization maps, to find the state-of-the-art approaches in the weakly supervised learning setting for object detection, semantic segmentation, and scene parsing.

TL;DR: In this paper, a domain flow generation (DLOW) model is proposed to bridge two different domains by generating a continuous sequence of intermediate domains flowing from one domain to the other.