Search Results - "Fadel, Samuel G."
-
1
Visualizing the Hidden Activity of Artificial Neural Networks
Published in IEEE transactions on visualization and computer graphics (01-01-2017)“…In machine learning, pattern classification assigns high-dimensional vectors (observations) to classes based on generalization from examples. Artificial neural…”
Get full text
Journal Article -
2
Contextual movement models based on normalizing flows
Published in Advances in statistical analysis : AStA : a journal of the German Statistical Society (01-03-2023)“…Movement models predict positions of players (or objects in general) over time and are thus key to analyzing spatiotemporal data as it is often used in sports…”
Get full text
Journal Article -
3
Exploiting ConvNet Diversity for Flooding Identification
Published in IEEE geoscience and remote sensing letters (01-09-2018)“…Flooding is the world's most costly type of natural disaster in terms of both economic losses and human causalities. A first and essential procedure toward…”
Get full text
Journal Article -
4
Neural relational inference for disaster multimedia retrieval
Published in Multimedia tools and applications (01-09-2020)“…Events around the world are increasingly documented on social media, especially by the people experiencing them, as these platforms become more popular over…”
Get full text
Journal Article -
5
LoCH: A neighborhood-based multidimensional projection technique for high-dimensional sparse spaces
Published in Neurocomputing (Amsterdam) (20-02-2015)“…On the last few years multidimensional projection techniques have advanced towards defining faster and user-centered approaches. However, most of existing…”
Get full text
Journal Article -
6
UPDis: A user-assisted projection technique for distance information
Published in Information Visualization (01-10-2018)“…Multidimensional projection techniques have become essential analytical tools. Typically, they map data from a high-dimensional space into a low-dimensional…”
Get full text
Book Review Journal Article -
7
Nmap: A Novel Neighborhood Preservation Space-filling Algorithm
Published in IEEE transactions on visualization and computer graphics (01-12-2014)“…Space-filling techniques seek to use as much as possible the visual space to represent a dataset, splitting it into regions that represent the data elements…”
Get full text
Journal Article -
8
Leveraging Activations for Superpixel Explanations
Published 07-06-2024“…Saliency methods have become standard in the explanation toolkit of deep neural networks. Recent developments specific to image classifiers have investigated…”
Get full text
Journal Article -
9
Graph-Based Early-Fusion for Flood Detection
Published in 2018 25th IEEE International Conference on Image Processing (ICIP) (01-10-2018)“…Flooding is one of the most harmful natural disasters, as it poses danger to both buildings and human lives. Therefore, it is fundamental to monitor these…”
Get full text
Conference Proceeding -
10
Self-Supervised Siamese Autoencoders
Published 05-04-2023“…Fully supervised models often require large amounts of labeled training data, which tends to be costly and hard to acquire. In contrast, self-supervised…”
Get full text
Journal Article -
11
Link Prediction in Dynamic Graphs for Recommendation
Published 17-11-2018“…Recent advances in employing neural networks on graph domains helped push the state of the art in link prediction tasks, particularly in recommendation…”
Get full text
Journal Article -
12
Principled Interpolation in Normalizing Flows
Published 22-10-2020“…Generative models based on normalizing flows are very successful in modeling complex data distributions using simpler ones. However, straightforward linear…”
Get full text
Journal Article -
13
Exploiting ConvNet Diversity for Flooding Identification
Published 05-06-2018“…Flooding is the world's most costly type of natural disaster in terms of both economic losses and human causalities. A first and essential procedure towards…”
Get full text
Journal Article