Mathematics, 2023 Non-negative matrix factorization (NMF) is widely used as a powerful matrix factorization tool in data representation. However, the traditional NMF, measured by Euclidean distance or Kullback–Leibler distance, does not take into account the internal ...
Shunli Li +3 more
doaj +2 more sources
Pediatric Sarcoma Data Forms a Unique Cluster Measured via the Earth Mover’s Distance [PDF]
Scientific Reports, 2017 In this note, we combined pediatric sarcoma data from Columbia University with adult sarcoma data collected from TCGA, in order to see if one can automatically discern a unique pediatric cluster in the combined data set. Using a novel clustering pipeline
Yongxin Chen +6 more
doaj +2 more sources
Modelling saliency attention to predict eye direction by topological structure and earth mover's distance. [PDF]
PLoS ONE, 2017 A saliency attention model for predicting eye direction is proposed in this paper. This work is inspired by the success of the topological structure and Earth Mover's Distance (EMD) approach.
Longsheng Wei +4 more
doaj +2 more sources
Advanced 3D Face Reconstruction from Single 2D Images Using Enhanced Adversarial Neural Networks and Graph Neural Networks [PDF]
SensorsThis paper presents a novel framework for 3D face reconstruction from single 2D images and addresses critical limitations in existing methods. Our approach integrates modified adversarial neural networks with graph neural networks to achieve state-of-the-
Mohamed Fathallah +4 more
doaj +2 more sources
Clustering Cu-S based compounds using periodic table representation and compositional Wasserstein distance [PDF]
Scientific ReportsCrystal structure similarity is useful for the chemical analysis of nowadays big materials databases and data mining new materials. Here we propose to use two-dimensional Wasserstein distance (earth mover’s distance) to measure the compositional ...
Shuyan Hao +3 more
doaj +2 more sources
Interpreting CNN models for musical instrument recognition using multi-spectrogram heatmap analysis: a preliminary study [PDF]
Frontiers in Artificial IntelligenceIntroductionMusical instrument recognition is a critical component of music information retrieval (MIR), aimed at identifying and classifying instruments from audio recordings.
Rujia Chen +2 more
doaj +2 more sources
The earth mover's distance and Bayesian linear discriminant analysis for epileptic seizure detection in scalp EEG. [PDF]
Biomed Eng Lett, 2018 Yuan S +5 more
europepmc +2 more sources
Learning quantum data with the quantum earth mover’s distance [PDF]
Quantum Science and Technology, 2021 Quantifying how far the output of a learning algorithm is from its target is an essential task in machine learning. However, in quantum settings, the loss landscapes of commonly used distance metrics often produce undesirable outcomes such as poor local ...
B. Kiani +4 more
semanticscholar +1 more source
Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification [PDF]
AAAI Conference on Artificial Intelligence, 2022 Visible thermal person re-identification (VT-ReID) suffers from inter-modality discrepancy and intra-identity variations. Distribution alignment is a popular solution for VT-ReID, however, it is usually restricted to the influence of the intra-identity ...
Yongguo Ling +6 more
semanticscholar +1 more source
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020 In this work, we develop methods for few-shot image classification from a new perspective of optimal matching between image regions. We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image ...
Chi Zhang +3 more
semanticscholar +1 more source