Home /
Research
Showing 661 - 666 / 897
ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes
KejunLi, MaeganTucker, ErdemBiyik....
Published date-11/09/2020
ActiveLearning
Characterizing what types of exoskeleton gaits are comfortable for users, and understanding the science of walking more generally, require recovering a user's utility landscape. Learning these landscapes is challenging, as …
MinkLoc3D: Point Cloud Based Large-Scale Place Recognition
JacekKomorowski....
Published date-11/09/2020
The paper presents a learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Existing methods, such as PointNetVLAD, are based on unordered point cloud representation. …
Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
MartinGenzel, JanMacdonald, MaximilianMärz....
Published date-11/09/2020
ImageReconstruction
In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems. Before such approaches can find application in safety-critical fields, a verification of their reliability …
After All, Only The Last Neuron Matters: Comparing Multi-modal Fusion Functions for Scene Graph Generation
MohamedKarimBelaid....
Published date-11/09/2020
GraphGeneration, SceneGraphGeneration, SemanticSegmentation
From object segmentation to word vector representations, Scene Graph Generation (SGG) became a complex task built upon numerous research results. In this paper, we focus on the last module of …
Ontology-driven Event Type Classification in Images
EricMüller-Budack, MatthiasSpringstein, SherzodHakimov....
Published date-11/09/2020
ImageClassification
Event classification can add valuable information for semantic search and the increasingly important topic of fact validation in news. So far, only few approaches address image classification for newsworthy event …
Numerical Exploration of Training Loss Level-Sets in Deep Neural Networks
NaveedTahir, GarrettE.Katz....
Published date-11/09/2020
DimensionalityReduction
We present a computational method for empirically characterizing the training loss level-sets of deep neural networks. Our method numerically constructs a path in parameter space that is constrained to a …