Title:
APPARATUS AND METHOD FOR DYNAMIC QUADRUPLE CONVOLUTION IN 3D CNN
Document Type and Number:
WIPO Patent Application WO/2023/097423
Kind Code:
A1
Abstract:
An apparatus, method, device and medium for dynamic quadruple convolution in a 3-dimensional (3D) convolutional neural network (CNN) are provided. The method includes: a multi-dimensional attention block configured to: receive an input feature map of a video data sample; and dynamically generate convolutional kernel scalars along four dimensions of a 3-dimensional convolution kernel space based on the input feature map, the four dimensions comprising an output channel number, an input channel number, a temporal size and a spatial size; and a convolution block configured to sequentially multiply the generated convolutional kernel scalars with a static 3D convolution kernel in a matrix-vector product way to obtain a dynamic kernel of dynamic quadruple convolution.
Inventors:
CAI DONGQI (CN)
YAO ANBANG (CN)
CHEN YURONG (CN)
LI CHAO (CN)
YAO ANBANG (CN)
CHEN YURONG (CN)
LI CHAO (CN)
Application Number:
PCT/CN2021/134283
Publication Date:
June 08, 2023
Filing Date:
November 30, 2021
Export Citation:
Assignee:
INTEL CORP (US)
CAI DONGQI (CN)
YAO ANBANG (CN)
CHEN YURONG (CN)
LI CHAO (CN)
CAI DONGQI (CN)
YAO ANBANG (CN)
CHEN YURONG (CN)
LI CHAO (CN)
International Classes:
G06K9/00
Foreign References:
CN113326748A | 2021-08-31 | |||
CN111368850A | 2020-07-03 | |||
CN112001479A | 2020-11-27 | |||
CN112016522A | 2020-12-01 | |||
US20210209339A1 | 2021-07-08 |
Attorney, Agent or Firm:
BEIJING EAST IP LTD. (CN)
Download PDF: