Capturing uncertainty in object detection is indispensable for safe autonomous driving. In
recent years, deep learning has become the de-facto approach for object detection, and …

We find that across a wide range of robot policy learning scenarios, treating supervised
policy learning with an implicit model generally performs better, on average, than commonly …

Abstract The Visual Object Tracking challenge VOT2020 is the eighth annual tracker
benchmarking activity organized by the VOT initiative. Results of 58 trackers are presented; …

Energy-Based Models (EBMs), also known as non-normalized probabilistic models, specify
probability density or mass functions up to an unknown normalizing constant. Unlike most …

A novel ordinal regression algorithm, called moving window regression (MWR), is proposed
in this paper. First, we propose the notion of relative rank (rho-rank), which is a new order …

Establishing dense correspondences between a pair of images is an important and general
problem. However, dense flow estimation is often inaccurate in the case of large …

Deep learning-based edge detectors heavily rely on pixel-wise labels which are often
provided by multiple annotators. Existing methods fuse multiple annotations using a simple …

Deep learning is a topic of considerable current interest. The availability of massive data
collections and powerful software resources has led to an impressive amount of results in …

Establishing robust and accurate correspondences between a pair of images is a long-
standing computer vision problem with numerous applications. While classically dominated …

Abstract The Visual Object Tracking challenge VOT2021 is the ninth annual tracker
benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; …