Luc Van Gool

TL;DR: The proposed EnergyWGAN objective guarantees a valid symmetric divergence serving as a more rigorous and meaningful quantitative measure and is capable of searching a more faithful solution space than the original WGANs without fixing a specific $k$-Lipschitz constraint.

TL;DR: This paper describes the calibration procedure of the two omni-directional cameras present in the AWEAR 2.0 system as well as a structure-from-motion pipeline that allows for stable multi-body tracking even from rather shaky video sequences thanks to ground plane stabilization.

TL;DR: This paper model the new problem as a sparse supernet with a new continuous architecture representation using a mixture of sparsity constraints, i.e., Sparse Group Lasso, and exploits a hierarchical accelerated proximal gradient algorithm within a bi-level optimization framework to optimize the proposed sparse supernets.

TL;DR: In this paper, a spatial-temporal convolutional self-attention layer with a theoretical understanding was proposed to exploit the locality information for video super-resolution, and a bidirectional optical flow-based feed-forward layer was designed to discover the correlations across different video frames and also align features.

TL;DR: This work studies scene understanding in the form of online estimation of semantic bird's-eye-view HD-maps using the video input from a single onboard camera and proposes a novel architecture that combines image-level understanding, BEV level understanding, and the aggregation of temporal information.