Presentation 2019-10-26
Procedural Text Generation from a Photo Sequence
Taichi Nishimura, Atsushi Hashimoto, Shinsuke Mori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we tackle a problem to generate a procedural text from a photo sequence, which aims to help users create a multimedia procedural text only by taking photographs. For this goal, the output texts should include important words that make sense as an instructions. However, traditional methods do not consider these words. To select the important words to describe a photo, the proposed method incorporates a retrieval method into a generation model. From various experimental results, we confirmed that the method outperforms standard baselines.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Procedural text / Photo sequence / Cross modal embedding / Sentence generation
Paper # HCS2019-47
Date of Issue 2019-10-19 (HCS)

Conference Information
Committee HCS
Conference Date 2019/10/26(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Nihon Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Masafumi Matsuda(NTT)
Vice Chair Tomoo Inoue(Univ. of Tsukuba) / Yugo Hayashi(Ritsumeikan Univ.)
Secretary Tomoo Inoue(Kanazawa Inst. of Tech.) / Yugo Hayashi(Osaka Electro-Comm. Univ.)
Assistant Tomoko Kanda(Osaka Inst. of Tech.) / Kazuki Takashima(Tohoku Univ.) / Ken Fujiwara(Osaka Univ. of Economic) / Kazunori Terada(Gifu Univ.) / Atsushi Kimura(Nihon Univ.) / HUANG HUNGHSUAN(Riken)

Paper Information
Registration To Technical Committee on Human Communication Science
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Procedural Text Generation from a Photo Sequence
Sub Title (in English)
Keyword(1) Procedural text
Keyword(2) Photo sequence
Keyword(3) Cross modal embedding
Keyword(4) Sentence generation
1st Author's Name Taichi Nishimura
1st Author's Affiliation Kyoto University(Kyoto Univ.)
2nd Author's Name Atsushi Hashimoto
2nd Author's Affiliation OMRON SINICX Corporation(OSX)
3rd Author's Name Shinsuke Mori
3rd Author's Affiliation Academic Center for Computing and Media Studies, Kyoto University(Kyoto Univ.)
Date 2019-10-26
Paper # HCS2019-47
Volume (vol) vol.119
Number (no) HCS-252
Page pp.pp.41-46(HCS),
#Pages 6
Date of Issue 2019-10-19 (HCS)