Results 41 to 50 of about 52,085 (312)

xUnit: Learning a Spatial Activation Function for Efficient Image Restoration

, 2018
In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of millions of ...
Kligvasser, Idan, Michaeli, Tomer, Shaham, Tamar Rott   +2 more
core   +1 more source

DeepID-Net: Deformable deep convolutional neural networks for object detection [PDF]

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and
Ouyang, Wanli, Wang, Xiaogang, Zeng, Xingyu, Qiu, Shi, Luo, Ping, Tian, Yonglong, Li, Hongsheng, Yang, Shuo, Wang, Zhe, Loy, Chen-Change, Tang, Xiaoou   +10 more
openaire   +2 more sources

End‐to‐end global to local convolutional neural network learning for hand pose recovery in depth data

IET Computer Vision, 2022
Despite recent advances in 3‐D pose estimation of human hands, thanks to the advent of convolutional neural networks (CNNs) and depth cameras, this task is still far from being solved in uncontrolled setups.
Meysam Madadi, Sergio Escalera, Xavier Baró, Jordi Gonzàlez   +3 more
doaj   +1 more source

Augmenting Paraphrase Generation with Syntax Information Using Graph Convolutional Networks

Entropy, 2021
Paraphrase generation is an important yet challenging task in natural language processing. Neural network-based approaches have achieved remarkable success in sequence-to-sequence learning.
Xiaoqiang Chi, Yang Xiang
doaj   +1 more source

Monocular Object Instance Segmentation and Depth Ordering with CNNs

, 2015
In this paper we tackle the problem of instance-level segmentation and depth ordering from a single monocular image. Towards this goal, we take advantage of convolutional neural nets and train them to directly predict instance-level segmentations where ...
Fidler, Sanja, Schwing, Alexander G., Urtasun, Raquel, Zhang, Ziyu   +3 more
core   +1 more source

Efficient Gender Classification Using a Deep LDA-Pruned Net

, 2017
Many real-time tasks, such as human-computer interaction, require fast and efficient facial gender classification. Although deep CNN nets have been very effective for a multitude of classification tasks, their high space and time demands make them ...
Arbel, Tal, Clark, James J., Tian, Qing
core   +1 more source

Diffusion Tractography Biomarker for Epilepsy Severity in Children With Drug‐Resistant Epilepsy

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective To develop a novel deep‐learning model of clinical DWI tractography that can accurately predict the general assessment of epilepsy severity (GASE) in pediatric drug‐resistant epilepsy (DRE) and test if it can screen diverse neurocognitive impairments identified through neuropsychological assessments.
Jeong‐Won Jeong, Min‐Hee Lee, Hiroshi Uda, Yoon Ho Hwang, Michael Behen, Aimee Luat, Csaba Juhász, Eishi Asano   +7 more
wiley   +1 more source

Generalizable and efficient cross‐domain person re‐identification model using deep metric learning

IET Computer Vision, 2023
Most of the successful person re‐ID models conduct supervised training and need a large number of training data. These models fail to generalise well on unseen unlabelled testing sets.
Saba Sadat Faghih Imani, Kazim Fouladi‐Ghaleh, Hossein Aghababa   +2 more
doaj   +1 more source

Improving neural networks by preventing co-adaptation of feature detectors [PDF]

, 2012
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case.
Hinton, Geoffrey E., Krizhevsky, Alex, Salakhutdinov, Ruslan R., Srivastava, Nitish, Sutskever, Ilya   +4 more
core   +1 more source

Deep Learning–Assisted Differentiation of Four Peripheral Neuropathies Using Corneal Confocal Microscopy

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Peripheral neuropathies contribute to patient disability but may be diagnosed late or missed altogether due to late referral, limitation of current diagnostic methods and lack of specialized testing facilities. To address this clinical gap, we developed NeuropathAI, an interpretable deep learning–based multiclass classification ...
Chaima Ben Rabah, Ioannis N. Petropoulos, Mark Stettner, Maryam Ferdousi, Uazman Alam, Nathan Efron, Ahmed Serag, Rayaz A. Malik   +7 more
wiley   +1 more source