Adversarial patches are still a simple yet powerful white box attack tha...
To cope with the high requirements during the computation of semantic
se...
We present READMem (Robust Embedding Association for a Diverse Memory), ...
This paper proposes a novel method for vision-based metric cross-view
ge...
Probabilistic models for sequential data are the basis for a variety of
...
This paper proposes a novel method for geo-tracking, i.e. continuous met...
While current methods for interactive Video Object Segmentation (iVOS) r...
Models for semantic segmentation require a large amount of hand-labeled
...
Deep neural networks, especially convolutional deep neural networks, are...
Deep learning-based models, such as recurrent neural networks (RNNs), ha...
In applications such as object tracking, time-series data inevitably car...
We present the current state of development of the sensor-equipped car
M...
In tasks such as tracking, time-series data inevitably carry missing
obs...
The reconstruction of accurate three-dimensional environment models is o...
We propose a framework that extends Blender to exploit Structure from Mo...
Visual tracking from an unmanned aerial vehicle (UAV) poses challenges s...
Methods to quantify the complexity of trajectory datasets are still a mi...
The analysis and quantification of sequence complexity is an open proble...
Living in a complex world like ours makes it unacceptable that a practic...
Deep Learning is a state-of-the-art technique to make inference on exten...
Representations of sequential data are commonly based on the assumption ...
In this paper, a novel two-stream architecture for the task of temporal
...
The problem of varying dynamics of tracked objects, such as pedestrians,...
Statistical models of the human body surface are generally learned from
...
We present a method to reconstruct the three-dimensional trajectory of a...
In recent years, there is a shift from modeling the tracking problem bas...
Recurrent neural networks are able to learn complex long-term relationsh...
We present a method to reconstruct the three-dimensional trajectory of a...
We present a method to perform online Multiple Object Tracking (MOT) of ...