Results 41 to 50 of about 148,198 (270)

Pointwise Convolutional Neural Networks

open access: yes, 2018
Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently. However, the capability of using point clouds with convolutional neural network has been so far not fully explored. In this paper,
Hua, Binh-Son   +2 more
core   +1 more source

A Bridge Structure 3D Representation for Deep Neural Network and Its Application in Frequency Estimation

open access: yesAdvances in Civil Engineering, 2022
Currently, most predictions related to bridge geometry use shallow neural networks, which limit the network’s ability to fit since the input form limits the depth of the neural network.
Kejian Hu, Xiaoguang Wu
doaj   +1 more source

ON SELECTING IMAGES FROM AN UNAIMED VIDEO STREAM FOR PHOTOGRAMMETRIC MODELLING [PDF]

open access: yesISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020
In this paper, we illustrate how convolutional neural networks and voxel-based processing together with voxel visualizations can be utilized for the selection of unaimed images for a photogrammetric image block.
P. Rönnholm   +3 more
doaj   +1 more source

Projection-Based 2.5D U-net Architecture for Fast Volumetric Segmentation

open access: yes, 2019
Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and require long training time.
Angermann, Christoph   +4 more
core   +1 more source

CBIR system using Capsule Networks and 3D CNN for Alzheimer's disease diagnosis

open access: yesInformatics in Medicine Unlocked, 2019
Alzheimer’s disease (AD) is an irreversible disorder of the brain related to loss of memory, commonly seen in the elderly and aging population. Implementation of revolutionary computer aided diagnosis techniques with Content Based Image Retrieval (CBIR ...
K.R. Kruthika   +2 more
doaj   +1 more source

A Convolutional Neural Network for Point Cloud Instance Segmentation in Cluttered Scene Trained by Synthetic Data Without Color

open access: yesIEEE Access, 2020
3D Instance segmentation is a fundamental task in computer vision. Effective segmentation plays an important role in robotic tasks, augmented reality, autonomous driving, etc.
Yajun Xu   +3 more
doaj   +1 more source

DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding

open access: yes, 2017
While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding.
Bai, Mingru   +4 more
core   +1 more source

Hierarchical Graph Attention Based Multi-View Convolutional Neural Network for 3D Object Recognition

open access: yesIEEE Access, 2021
For multi-view convolutional neural network based 3D object recognition, how to fuse the information of multiple views is a key factor affecting the recognition performance. Most traditional methods use max-pooling algorithm to obtain the final 3D object
Hui Zeng   +4 more
doaj   +1 more source

NIRExpNet: Three-Stream 3D Convolutional Neural Network for Near Infrared Facial Expression Recognition

open access: yesApplied Sciences, 2017
Facial expression recognition (FER) under active near-infrared (NIR) illumination has the advantages of illumination invariance. In this paper, we propose a three-stream 3D convolutional neural network, named as NIRExpNet for NIR FER. The 3D structure of
Zhan Wu   +4 more
doaj   +1 more source

A Multi-Scale and Multi-Level Spectral-Spatial Feature Fusion Network for Hyperspectral Image Classification

open access: yesRemote Sensing, 2020
Extracting spatial and spectral features through deep neural networks has become an effective means of classification of hyperspectral images. However, most networks rarely consider the extraction of multi-scale spatial features and cannot fully ...
Caihong Mu, Zhen Guo, Yi Liu
doaj   +1 more source

Home - About - Disclaimer - Privacy