Authors:
Haruki Fujii
1
;
Naoki Minamino
2
;
Takashi Ueda
2
;
3
;
Yohei Kondo
4
;
2
;
3
and
Kazuhiro Hotta
1
Affiliations:
1
Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan
;
2
National Institute for Basic Biology, 38 Nishigounaka, Myoudaiji-cho, Okazaki 444-0867, Japan
;
3
The Graduate University for Advanced Studies, 1560-35 Syonankokusai-mura, Hayama-machi, Miura-gun, Japan
;
4
Exploratory Research Center on Life and Living Systems (ExCELLS), 5-1 Higashiyama, Myodaiji-cho, Okazaki, 444-8787, Japan
Keyword(s):
Video Recognition, 3DCNN, Visualization, Liverwort.
Abstract:
In this paper, we propose a method to classify the videos of wild-type and mutant sperm of liverwort using deep learning and discover the differences between them. In traditional video classification, 3D-Convolution was often used. However, when 3D CNN is used, the information of multiple frames is mixed. Therefore, it is difficult to detect important frames and locations in a video. To solve this problem, we proposed a network that retains video frame information using Depthwise Convolution and Skip Connection, and used gradient-based visualization to analyze the difference between wild type and mutant sperm. In experiments, we compared the proposed method with conventional 3DCNN and show the effectiveness of the proposed method.