A single unexpected object on the road can cause an accident or may lead...
Most state-of-the-art instance segmentation methods rely on large amount...
Recently, the self-supervised learning framework data2vec has shown insp...
The general domain of video segmentation is currently fragmented into
di...
Deep learning-based 3D human pose estimation performs best when trained ...
Modern 3D semantic instance segmentation approaches predominantly rely o...
We propose a new attention mechanism, called Global Hierarchical Attenti...
Transformers have become prevalent in computer vision due to their
perfo...
Existing state-of-the-art methods for Video Object Segmentation (VOS) le...
Person detection is a crucial task for mobile robots navigating in
human...
Deep learning is the essential building block of state-of-the-art person...
Detecting persons using a 2D LiDAR is a challenging task due to the low
...
We address the problem of learning a single model for person
re-identifi...
Detecting humans is a key skill for mobile robots and intelligent vehicl...
Deep learning approaches have made tremendous progress in the field of
s...
In this work, we tackle the problem of instance segmentation, the task o...
In the past few years, the field of computer vision has gone through a
r...
Superpixels group perceptually similar pixels to create visually meaning...
Semantic image segmentation is an essential component of modern autonomo...
We introduce the DROW detector, a deep learning based detector for 2D ra...