@inproceedings{ushiku-etal-2017-procedural,
title = "Procedural Text Generation from an Execution Video",
author = "Ushiku, Atsushi and
Hashimoto, Hayato and
Hashimoto, Atsushi and
Mori, Shinsuke",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-1033",
pages = "326--335",
abstract = "In recent years, there has been a surge of interest in automatically describing images or videos in a natural language. These descriptions are useful for image/video search, etc. In this paper, we focus on procedure execution videos, in which a human makes or repairs something and propose a method for generating procedural texts from them. Since video/text pairs available are limited in size, the direct application of end-to-end deep learning is not feasible. Thus we propose to train Faster R-CNN network for object recognition and LSTM for text generation and combine them at run time. We took pairs of recipe and cooking video, generated a recipe from a video, and compared it with the original recipe. The experimental results showed that our method can produce a recipe as accurate as the state-of-the-art scene descriptions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ushiku-etal-2017-procedural">
<titleInfo>
<title>Procedural Text Generation from an Execution Video</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Ushiku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hayato</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinsuke</namePart>
<namePart type="family">Mori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, there has been a surge of interest in automatically describing images or videos in a natural language. These descriptions are useful for image/video search, etc. In this paper, we focus on procedure execution videos, in which a human makes or repairs something and propose a method for generating procedural texts from them. Since video/text pairs available are limited in size, the direct application of end-to-end deep learning is not feasible. Thus we propose to train Faster R-CNN network for object recognition and LSTM for text generation and combine them at run time. We took pairs of recipe and cooking video, generated a recipe from a video, and compared it with the original recipe. The experimental results showed that our method can produce a recipe as accurate as the state-of-the-art scene descriptions.</abstract>
<identifier type="citekey">ushiku-etal-2017-procedural</identifier>
<location>
<url>https://aclanthology.org/I17-1033</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>326</start>
<end>335</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Procedural Text Generation from an Execution Video
%A Ushiku, Atsushi
%A Hashimoto, Hayato
%A Hashimoto, Atsushi
%A Mori, Shinsuke
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F ushiku-etal-2017-procedural
%X In recent years, there has been a surge of interest in automatically describing images or videos in a natural language. These descriptions are useful for image/video search, etc. In this paper, we focus on procedure execution videos, in which a human makes or repairs something and propose a method for generating procedural texts from them. Since video/text pairs available are limited in size, the direct application of end-to-end deep learning is not feasible. Thus we propose to train Faster R-CNN network for object recognition and LSTM for text generation and combine them at run time. We took pairs of recipe and cooking video, generated a recipe from a video, and compared it with the original recipe. The experimental results showed that our method can produce a recipe as accurate as the state-of-the-art scene descriptions.
%U https://aclanthology.org/I17-1033
%P 326-335
Markdown (Informal)
[Procedural Text Generation from an Execution Video](https://aclanthology.org/I17-1033) (Ushiku et al., IJCNLP 2017)
ACL
- Atsushi Ushiku, Hayato Hashimoto, Atsushi Hashimoto, and Shinsuke Mori. 2017. Procedural Text Generation from an Execution Video. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 326–335, Taipei, Taiwan. Asian Federation of Natural Language Processing.