Unsupervised Video Object Segmentation (UVOS) aims at discovering object...
We propose a methodology that systematically applies deep explanation
al...
We introduce PointConvFormer, a novel building block for point cloud bas...
Video Object Segmentation (VOS) is fundamental to video understanding.
T...
CounterFactual (CF) visual explanations try to find images similar to th...
This paper summarizes our endeavors in the past few years in terms of
ex...
In this paper, we propose Stochastic Block-ADMM as an approach to train ...
We consider the problem of modeling the dynamics of continuous
spatial-t...
In the segmentation of fine-scale structures from natural and biomedical...
Recently, particle-based variational inference (ParVI) methods have gain...
In multi-object tracking, the tracker maintains in its memory the appear...
Recently, there has been a significant interest in performing convolutio...
Instance Segmentation, which seeks to obtain both class and instance lab...
Strictly enforcing orthonormality constraints on parameter matrices has ...
We propose a novel end-to-end deep scene flow model, called PointPWC-Net...
Recently, several networks that operate directly on point clouds have be...
Efficient exploration remains a challenging problem in reinforcement
lea...
Segmentation algorithms are prone to make topological errors on fine-sca...
Understanding and interpreting the decisions made by deep learning model...
Heatmap regression has became one of the mainstream approaches to locali...
We introduce HyperGAN, a generative network that learns to generate all ...
Unlike images which are represented in regular dense grids, 3D point clo...