Results 21 to 30 of about 198,293 (212)
Research on OpenCL optimization for FPGA deep learning application.
PLoS ONE, 2019 In recent years, with the development of computer science, deep learning is held as competent enough to solve the problem of inference and learning in high dimensional space.
Shuo Zhang +4 more
doaj +1 more source
Speech Processing in Computer Vision Applications [PDF]
, 2020 Deep learning has been recently proven to be a viable asset in determining features in the field of Speech Analysis. Deep learning methods like Convolutional Neural Networks facilitate the expansion of specific feature information in waveforms, allowing ...
Waterworth, Nicholas
core +2 more sources
Uncertain Flow Visualization using LIC [PDF]
, 2009 In this paper we look at the Line Integral Convolution method for flow visualization and ways in which this can be applied to the visualization of two dimensional, steady flow fields in the presence of uncertainty. To achieve this, we start by studying
Allendes Osorio, RS, Brodlie, KW
core +1 more source
Adversarial Spatio-Temporal Learning for Video Deblurring
, 2018 Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal ...
Li, Hongdong +5 more
core +1 more source
DUNet: A deformable network for retinal vessel segmentation
, 2018 Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension. In this paper, we propose Deformable U-Net (DUNet), which exploits the retinal vessels' local features
Chen, Qi +5 more
core +1 more source
FEBS Letters, EarlyView.This study reveals how the mitochondrial protein Slm35 is regulated in Saccharomyces cerevisiae. The authors identify stress‐responsive DNA elements and two upstream open reading frames (uORFs) in the 5′ untranslated region of SLM35. One uORF restricts translation, and its mutation increases Slm35 protein levels and mitophagy.
Hernán Romo‐Casanueva +5 more
wiley +1 more source
Object tracking method based on edge detection and morphology
EURASIP Journal on Advances in Signal ProcessingWith the continuous development of science and technology, intelligent surveillance technology using image processing and computer vision is also progressing. To improve the performance of target detection and tracking, an improved target tracking method
Jie Xu, Sijie Niu, Zhifeng Wang
doaj +1 more source
Efficient Remote Sensing in Agriculture via Active Learning and Opt-HRDNet
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingAs the foundation of human survival, the development of agriculture has always played an important role in social development. The quality of agricultural development determines the speed of social progress.
Desheng Chen +4 more
doaj +1 more source
A Theory for Integer Only Numerical Analysis (Draft ) [PDF]
, 2016 This draft is to be presented at the 14 th International Conference on p−adic Analysis, in Aurillac, France, July 2016. The final version of this draft is to be submitted soon afterwards.
Esbelin, Henri-Alex, Malgouyres, Rémy
core +1 more source
Improving Efficiency in Convolutional Neural Network with Multilinear Filters
, 2017 The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require billions of ...
Gabbouj, Moncef +2 more
core +1 more source