Presentation 2022-07-29
A Comparison Study on Image Captioning by VGG and YOLO
Yan LYU, Qiangfu Zhao, Yong Liu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Image captioning is a task for generating a descriptive statement automatically for a given image by combining image processing and natural language processing together. The existing approaches divided the whole process into two parts, encoding process and decoding process. Our research proposed an image captioning method based on the existed encoder-decoder architecture with the YOLO as encoder and the LSTM as decoder. The encoder is used to encode images into feature vectors while the decoder is to generate natural language sentences based on the feature vectors to describe the image. The proposed method was compared with other existed models.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Caption GenerationEnd-to-endYOLOLSTM
Paper # R2022-10
Date of Issue 2022-07-22 (R)

Conference Information
Committee R
Conference Date 2022/7/29(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English) Reliability Theory, Communication Network Reliability, Reliability General
Chair Tadashi Dohi(Hiroshima Univ.)
Vice Chair Yasushi Kadota(Ricoh)
Secretary Yasushi Kadota(Hiroshima Univ.)
Assistant Shinji Yokogawa(Univ. of Electro-Comm.) / Takahide Yoshikawa(Fujitsu Lab.) / Takenori Sakumura(Housei Univ.)

Paper Information
Registration To Technical Committee on Reliability
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Comparison Study on Image Captioning by VGG and YOLO
Sub Title (in English)
Keyword(1) Image Caption GenerationEnd-to-endYOLOLSTM
1st Author's Name Yan LYU
1st Author's Affiliation University of Aizu(UoA)
2nd Author's Name Qiangfu Zhao
2nd Author's Affiliation University of Aizu(UoA)
3rd Author's Name Yong Liu
3rd Author's Affiliation University of Aizu(UoA)
Date 2022-07-29
Paper # R2022-10
Volume (vol) vol.122
Number (no) R-140
Page pp.pp.7-12(R),
#Pages 6
Date of Issue 2022-07-22 (R)