3D Densely Connected Convolutional Network for the Recognition of Human Shopping Actions
In recent years, deep convolutional neural networks (CNNs) have shown remarkable results in the image domain. However, most of the neural networks in action recognition do not have very deep layer compared with the CNN in the image domain. This thesis presents a 3D Densely Connected Convolutional Ne...
Main Author: | Gu, Dongfeng |
---|---|
Other Authors: | Laganière, Robert |
Language: | en |
Published: |
Université d'Ottawa / University of Ottawa
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/10393/36739 http://dx.doi.org/10.20381/ruor-21013 |
Similar Items
-
Multiple Feature Reweight DenseNet for Image Classification
by: Ke Zhang, et al.
Published: (2019-01-01) -
Recognition and Mapping of Landslide Using a Fully Convolutional DenseNet and Influencing Factors
by: Xiao Gao, et al.
Published: (2021-01-01) -
A New Architecture of Densely Connected Convolutional Networks for Pan-Sharpening
by: Wei Huang, et al.
Published: (2020-04-01) -
Esophageal Abnormality Detection Using DenseNet Based Faster R-CNN With Gabor Features
by: Noha Ghatwary, et al.
Published: (2019-01-01) -
A Smart Mobile Diagnosis System for Citrus Diseases Based on Densely Connected Convolutional Networks
by: Wenyan Pan, et al.
Published: (2019-01-01)