Convolution: Math, Graphics, and Discrete Signals
Parallel Processing
Convolution Properties II
Convolution Properties I
Deconvolution
Upsampling
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: Feb 16, 2026

Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
Qiang Lan1,2, Zelong Wang1,2, Mei Wen1,2
1College of Computer, National University of Defense Technology, Changsha 410073, China.
This study optimizes 3D convolutional neural networks for video classification using the Winograd Minimal Filtering Algorithm (WMFA). The WMFA implementation achieved a twofold speedup in 3D convolution layers compared to cuDNN, enhancing computational efficiency.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: