Results 221 to 230 of about 44,491 (259)
Some of the next articles are maybe not open access.
Hyperspectral Image Few-Shot Classification Network Based on the Earth Mover’s Distance
IEEE Transactions on Geoscience and Remote Sensing, 2022Deep learning has achieved promising performance in hyperspectral image (HSI) classification. Training deep models usually requires labeling massive HSIs, which, however, is prohibitively time-consuming and expensive.
Jiaxing Sun, Xiaobo Shen, Quansen Sun
semanticscholar +1 more source
Fast Dataset Search with Earth Mover's Distance
Proceedings of the VLDB Endowment, 2022The amount of spatial data in open data portals has increased rapidly, raising the demand for spatial dataset search in large data repositories. In this paper, we tackle spatial dataset search by using the Earth Mover's Distance (EMD) to measure the ...
Wenzhe Yang +3 more
semanticscholar +1 more source
Matching Distributions Algorithms Based on the Earth Mover’s Distance for Ordinal Quantification
IEEE Transactions on Neural Networks and Learning Systems, 2022The goal of quantification learning is to induce models capable of accurately predicting the class distribution for new bags of unseen examples. These models only return the prevalence of each class in the bag because prediction of individual examples is
Alberto Castaño +3 more
semanticscholar +1 more source
DeepEMD: A Transformer-based Fast Estimation of the Earth Mover's Distance
International Conference on Pattern Recognition, 2023The Earth Mover's Distance (EMD) is the measure of choice between point clouds. However the computational cost to compute it makes it prohibitive as a training loss, and the standard approach is to use a surrogate such as the Chamfer distance. We propose
A. Sinha, F. Fleuret
semanticscholar +1 more source
Time-aware Concept Drift Detection Using the Earth Mover’s Distance
International Conference on Process Mining, 2020Modern business processes are embedded in a complex environment and, thus, subjected to continuous changes. While current approaches focus on the control flow only, additional perspectives, such as time, are neglected.
T. Brockhoff +2 more
semanticscholar +1 more source
Depth-guided NeRF Training via Earth Mover's Distance
European Conference on Computer VisionNeural Radiance Fields (NeRFs) are trained to minimize the rendering loss of predicted viewpoints. However, the photometric loss often does not provide enough information to disambiguate between different possible geometries yielding the same image ...
Anita Rau +3 more
semanticscholar +1 more source
Fine-Grained Complexity of Earth Mover's Distance under Translation
International Symposium on Computational GeometryThe Earth Mover's Distance is a popular similarity measure in several branches of computer science. It measures the minimum total edge length of a perfect matching between two point sets. The Earth Mover's Distance under Translation ($\mathrm{EMDuT}$) is
Karl Bringmann +3 more
semanticscholar +1 more source
Body-Earth Mover’s Distance: A Matching-Based Approach for Sleep Posture Recognition
IEEE Transactions on Biomedical Circuits and Systems, 2016Sleep posture is a key component in sleep quality assessment and pressure ulcer prevention. Currently, body pressure analysis has been a popular method for sleep posture recognition.
Xiaowei Xu +5 more
semanticscholar +1 more source
The Earth Mover's distance is the Mallows distance: some insights from statistics
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 2001E. Levina, P. Bickel
semanticscholar +1 more source