A decomposable Winograd method for N-D convolution acceleration in video analysis

DOI10.1007/s11263-021-01500-9zbMath1483.68431OpenAlexW3192697904MaRDI QIDQ2054386

Ling Li, Shaoli Liu, Di Huang, Rui Zhang, Fan Wu, Xianzhuo Wang, Xishan Zhang, Yunji Chen, Pengwei Jin

Publication date: 2 December 2021

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11263-021-01500-9

zbMATH Keywords

Winograd algorithmvideo analysisconvolution neural networksmodel acceleration

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Machine vision and scene understanding (68T45)

Uses Software

• NumPy
• TensorFlow
• cuDNN
• PyTorch
• DARTS
• DoReFa-Net
• ProxylessNAS
• MinkowskiEngine

Cites Work

• Unnamed Item
• Enabling Efficient Fast Convolution Algorithms on GPUs via MegaKernels

This page was built for publication: A decomposable Winograd method for N-D convolution acceleration in video analysis