Filters








2,569 Hits in 3.3 sec

Deep learning enabled real time speckle recognition and hyperspectral imaging using a multimode fiber array

Ulas Kürüm, Peter R. Wiecha, Rebecca French, Otto L. Muskens
2019 Optics Express  
Optimized neural networks trained on these datasets achieve reliable reconstruction of both discrete and continuous spectra from a monochromatic camera image.  ...  The artificial neural network can be effectively trained using numerically constructed multispectral datasets taken from a measured spectral transmission matrix.  ...  Acknowledgments We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Quadro P6000 GPU used for this research. La Linea © CAVA/QUIPOS.  ... 
doi:10.1364/oe.27.020965 fatcat:iodlzqw7cvcqdjpjsiqxisoksa

Deep Learning Enabled Real Time Speckle Recognition and Hyperspectral Imaging using a Multimode Fiber Array [article]

Ulas Kürüm, P. R. Wiecha, Rebecca French, Otto L. Muskens
2019 arXiv   pre-print
Optimized neural networks trained on these datasets achieve reliable reconstruction of both discrete and continuous spectra from a monochromatic camera image.  ...  The artificial neural network can be effectively trained using numerically constructed multispectral datasets taken from a measured spectral transmission matrix.  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Quadro P6000 GPU used for this research. La Linea © CAVA/QUIPOS.  ... 
arXiv:1904.04673v1 fatcat:begdmuewfnetxayj6sf74chjhi

Deep Representation Learning For Multimodal Brain Networks [article]

Wen Zhang, Liang Zhan, Paul Thompson, Yalin Wang
2020 arXiv   pre-print
To address these challenges, we propose a novel end-to-end deep graph representation learning (Deep Multimodal Brain Networks - DMBN) to fuse multimodal brain networks.  ...  Due to the complex network topology, for an individual brain, mining a discriminative network representation from the multimodal brain networks is non-trivial.  ...  We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.  ... 
arXiv:2007.09777v1 fatcat:m74yqcdcerfk5ezxozqzwfjebi

Editorial for the special issue on "Research on methods of multimodal information fusion in emotion recognition"

Kaijian Xia, Tao Hu, Wen Si
2019 Personal and Ubiquitous Computing  
convolutional neural network (CNN) is proposed.  ...  The paper "Emotional computing based on cross-modal fusion and edge network data incentive" presented an emotional computing algorithm based on cross-modal fusion and edge network data incentive.  ...  convolutional neural network (CNN) is proposed.  ... 
doi:10.1007/s00779-019-01260-x fatcat:6e7btyoj7zbtlahdghv23qkrye

2020 Index IEEE Journal of Selected Topics in Signal Processing Vol. 14

2020 IEEE Journal on Selected Topics in Signal Processing  
., +, JSTSP Aug. 2020 1024-1037 Robust Detection of Image Operator Chain With Two-Stream Convolutional Neural Network.  ...  ., +, JSTSP Jan. 2020 64-77 Robust Detection of Image Operator Chain With Two-Stream Convolutional Neural Network.  ... 
doi:10.1109/jstsp.2020.3029672 fatcat:6twwzcqpwzg4ddcu2et75po77u

Multimodal Emotion Recognition Model using Physiological Signals [article]

Yuxuan Zhao, Xinyan Cao, Jinlong Lin, Dunshan Yu, Xixin Cao
2019 arXiv   pre-print
1D convolutional neural network model and a biologically inspired multimodal fusion model which integrates multimodal information on the decision level for emotion recognition.  ...  Motivated by the outstanding performance of deep learning approaches in recognition tasks, we proposed a Multimodal Emotion Recognition Model that consists of a 3D convolutional neural network model, a  ...  Methods Here we propose a Multimodal Emotion Recognition Model that consists of a 3D convolutional neural network model, a 1D convolutional neural network model and a biologically inspired multimodal fusion  ... 
arXiv:1911.12918v1 fatcat:wggkkuakifedpilhnal5osfoz4

Multimode Optical Fiber Transmission with a Deep Learning Network [article]

Babak Rahmani, Damien Loterie, Georgia Konstantinou, Demetri Psaltis, Christophe Moser
2018 arXiv   pre-print
Specifically, we demonstrate that a deep convolutional neural network (CNN) can learn the non-linear relationships between the amplitude of the speckle pattern obtained at the output of the fiber and the  ...  We show, as a proof of concept, that a deep learning neural network can learn the input-output relationship in a 0.75 m long MMF.  ...  Acknowledgments Funding: This project was partially conducted with funding from the Swiss National Science Foundation (SNSF) project MuxWave (200021_160113\1).  ... 
arXiv:1805.05134v2 fatcat:pelpudat2bekdpb3zukiqah2oi

Multimodal Emotion Recognition Method Based on Convolutional Auto-Encoder

Jian Zhou, Xianwei Wei, Chunling Cheng, Qidong Yang, Qun Li
2019 International Journal of Computational Intelligence Systems  
Secondly, a fully connected neural network classifier is constructed to achieve emotion recognition.  ...  In this paper, a multimodal emotion recognition method based on convolutional auto-encoder (CAE) is proposed.  ...  ; FCNN, fully connected neural network.  ... 
doi:10.2991/ijcis.2019.125905651 fatcat:evqmfl5ncbg4deyrcix3txt7j4

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
Neural Networks (ST-CNN) 577 Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks 578 Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial  ...  radiotherapy planning 629 Multi-channel Generative Adversarial Network for Parallel Magnetic Resonance Image Reconstruction in K-space 632 Physics-based Simulation to enable Ultrasound monitoring of HIFU  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Single-Sensor Acoustic Emission Source Localization in Plate-Like Structures Using Deep Learning

Arvin Ebrahimkhanlou, Salvatore Salamone
2018 Aerospace (Basel)  
Visualizing the Inception of a Convolutional Neural Network Images that strongly activate a specific channel in a layer of a convolutional neural network represent the inception of that channel.  ...  Visualizing the Inception of a Convolutional Neural Network Images that strongly activate a specific channel in a layer of a convolutional neural network represent the inception of that channel.  ... 
doi:10.3390/aerospace5020050 fatcat:emxqd4bm2vgwjkm7hgum6uzoea

Recognizing three-dimensional phase images with deep learning [article]

Weiru Fan, Tianrun Chen, Xingqi Xu, Ziyang Chen, Huizhu Hu, Delong Zhang, Da-Wei Wang, Jixiong Pu, Shi-Yao Zhu
2021 arXiv   pre-print
To address this challenge, we developed a speckle three-dimensional reconstruction network (STRN) to recognize phase objects behind scattering media, which circumvents the limitations of memory effect.  ...  From the single-shot, reference-free and scanning-free speckle pattern input, STRN distinguishes depth-resolving quantitative phase information with high fidelity.  ...  The input single channel 256 × 256 images go through a composite layer with 5 × 5 convolution and result in a 64-channel feature map.  ... 
arXiv:2107.10584v1 fatcat:zwbzte677rcqnjl3v5rtmd4fqy

Multimode optical fiber transmission with a deep learning network

Babak Rahmani, Damien Loterie, Georgia Konstantinou, Demetri Psaltis, Christophe Moser
2018 Light: Science & Applications  
Specifically, we demonstrate that a deep convolutional neural network (CNN) can learn the nonlinear relationships between the amplitude of the speckle pattern (phase information lost) obtained at the output  ...  We show, as a proof of concept, that a deep neural network can learn the input-output relationship in a 0.75 m long MMF.  ...  Acknowledgements This project was partially conducted with funding from the Swiss National Science Foundation (SNSF) project MuxWave (200021_160113/1) and partly funded by CERAMIC X.0-High-precision micromanufacturing  ... 
doi:10.1038/s41377-018-0074-1 pmid:30302240 pmcid:PMC6168552 fatcat:3sqlsn5hcfh5hegybwxdw6tfam

MMTM: Multimodal Transfer Module for CNN Fusion [article]

Hamid Reza Vaezi Joze, Amirreza Shaban, Michael L. Iuzzolino and Kazuhito Koishida
2020 arXiv   pre-print
In this paper, we present a simple neural network module for leveraging the knowledge from multiple modalities in convolutional neural networks.  ...  In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end.  ...  Inspired by the squeeze and excitation (SE) module [19] for unimodal convolutional neural networks, we propose a multimodal transfer module to recalibrate the channel-wise fea-tures of different CNN  ... 
arXiv:1911.08670v2 fatcat:uxv6tldwrvgwbndrtbbktpvjhy

Learning the retinal anatomy from scarce annotated data using self-supervised multimodal reconstruction

Álvaro S. Hervella, José Rouco, Jorge Novo, Marcos Ortega
2020 Applied Soft Computing  
For that purpose, a neural network is pre-trained using the self-supervised multimodal reconstruction of fluorescein angiography from retinography.  ...  We propose a novel alternative that allows to apply transfer learning from unlabelled data of the same domain, which consists in the use of a multimodal reconstruction task.  ...  Specifically, U-Net is a fully convolutional neural network with output and input of the same size.  ... 
doi:10.1016/j.asoc.2020.106210 fatcat:7zr5xxza6rgald67fkcnve557y

Intensity-only Mode Decomposition on Multimode Fibers using a Densely Connected Convolutional Network

Stefan Rothe, Qian Zhang, Nektarios Koukourakis, Jurgen Czarske
2020 Journal of Lightwave Technology  
Index Terms-DenseNet, convolutional neural network, mode decomposition, multimode fiber, physical layer security, transfer learning.  ...  To overcome these drawbacks, a neural network is proposed, which performs mode decomposition with intensity-only camera recordings of the multimode fiber facet.  ...  Furthermore, it is shown that detection with the neural network also works with a multimode fiber that also carries unknown modes.  ... 
doi:10.1109/jlt.2020.3041374 fatcat:epjomsheajel7kzuwrfskekdjm
« Previous Showing results 1 — 15 out of 2,569 results