Home /
Research
Showing 595 - 600 / 897
Invertible CNN-Based Super Resolution with Downsampling Awareness
AndrewGeiss, JosephC.Hardin....
Published date-11/11/2020
ImageSuper-Resolution, SuperResolution, Super-Resolution
Single image super resolution involves artificially increasing the resolution of an image. Recently, convolutional neural networks have been demonstrated as very powerful tools for this problem. These networks are typically …
Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion
ZhanqiuZhang, JianyuCai, JieWang....
Published date-11/11/2020
KnowledgeGraphCompletion, LinkPrediction
Tensor factorization based models have shown great power in knowledge graph completion (KGC). However, their performance usually suffers from the overfitting problem seriously. This motivates various regularizers---such as the squared …
Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures
Ying-TaoLuo, Peng-QiLi, Dong-TingLi....
Published date-11/11/2020
In quantum mechanics, a norm squared wave function can be interpreted as the probability density that describes the likelihood of a particle to be measured in a given position or …
Text Augmentation for Language Models in High Error Recognition Scenario
KarelBeneš, LukášBurget....
Published date-11/11/2020
DataAugmentation, SpeechRecognition, TextAugmentation
We examine the effect of data augmentation for training of language models for speech recognition. We compare augmentation based on global error statistics with one based on per-word unigram statistics …
Clustering of Big Data with Mixed Features
JoshuaTobin, MimiZhang....
Published date-11/11/2020
Clustering
Clustering large, mixed data is a central problem in data mining. Many approaches adopt the idea of k-means, and hence are sensitive to initialisation, detect only spherical clusters, and require …
End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks
AliceXue....
Published date-11/11/2020
ChineseLandscapePaintingGeneration
Current GAN-based art generation methods produce unoriginal artwork due to their dependence on conditional input. Here, we propose Sketch-And-Paint GAN (SAPGAN), the first model which generates Chinese landscape paintings from …