In this paper, we investigate properties and limitations of invariance
l...
Video summarization aims at choosing parts of a video that narrate a sto...
Symmetries built into a neural network have appeared to be very benefici...
The standard approach to contrastive learning is to maximize the agreeme...
The goal of this paper is Human-object Interaction (HO-I) detection. HO-...
Robustness against unwanted perturbations is an important aspect of depl...
We consider the problem of information compression from high dimensional...
Tracking multiple objects individually differs from tracking groups of
r...
We focus on building robustness in the convolutions of neural visual
cla...
Scale is often seen as a given, disturbing factor in many vision tasks. ...
We focus on the robustness of neural networks for classification. To per...
Human-object interaction recognition aims for identifying the relationsh...
In this paper we aim to explore the general robustness of neural network...
Siamese trackers turn tracking into similarity estimation between a temp...
Human-object interaction (HOI) detection is a core task in computer visi...
In this paper, we aim to explain the decisions of neural networks by
uti...
In this paper, we aim to understand and explain the decisions of deep ne...
With the transformative technologies and the rapidly changing global R ...
Deep computer vision systems being vulnerable to imperceptible and caref...
We introduce a new video dataset and benchmark to assess single-object
t...
It is widely believed that the success of deep convolutional networks is...