Sparse 3D convolutional neural networks (2015-05-01T00:00:00.000000Z)

TL;DR

A convolutional neural network designed for processing sparse three-dimensional input data and experiment with CNNs on the 2D triangular-lattice and 3D tetrahedral- lattice is implemented.

Abstract

We have implemented a convolutional neural network designed for processing sparse three-dimensional input data. The world we live in is three dimensional so there are a large number of potential applications. In the quest for eciency, we experiment with CNNs on the 2D triangular-lattice and 3D tetrahedral-lattice.

Authors

Benjamin Graham

5 papers

Sparse 3D convolutional neural networks

TL;DR

Abstract

Authors

References16 items

3D Convolutional Neural Networks for landing zone detection from LiDAR

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Fractional Max-Pooling

Spatially-sparse convolutional neural networks

Large-Scale Video Classification with Convolutional Neural Networks

3D ShapeNets: A deep representation for volumetric shapes

Fast Training of Convolutional Networks through FFTs

Learning Separable Filters

UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Multi-column deep neural networks for image classification

CASIA Online and Offline Chinese Handwriting Databases

Recognizing human actions

Recognizing human actions: a local SVM approach

Convolutional networks for images, speech, and time series

Learning Multiple Layers of Features from Tiny Images

Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Convolutional Neural Networks for Human Action Recognition

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names