Automatic paper summary generation from visual and textual information

Shintaro Yamamoto, Yoshihiro Fukuhara, Ryota Suzuki, Shigeo Morishima, Hirokatsu Kataoka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the exponentially increasing number of manuscripts. In response to this situation, this paper proposes the paper summary generation (PSG) task using a simple but effective method to automatically generate an academic paper summary from raw PDF data. We realized PSG by combination of vision-based supervised components detector and language-based unsupervised important sentence extractor, which is applicable for a trained format of manuscripts. We show the quantitative evaluation of ability of simple vision-based components extraction, and the qualitative evaluation that our system can extract both visual item and sentence that are helpful for understanding. After processing via our PSG, the 979 manuscripts accepted by the Conference on Computer Vision and Pattern Recognition (CVPR) 2018 are available1. It is believed that the proposed method will provide a better way for researchers to stay caught with important academic papers.

Original languageEnglish
Title of host publicationEleventh International Conference on Machine Vision, ICMV 2018
EditorsAntanas Verikas, Dmitry P. Nikolaev, Petia Radeva, Jianhong Zhou
PublisherSPIE
ISBN (Electronic)9781510627482
DOIs
Publication statusPublished - 2019 Jan 1
Event11th International Conference on Machine Vision, ICMV 2018 - Munich, Germany
Duration: 2018 Nov 12018 Nov 3

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11041
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference11th International Conference on Machine Vision, ICMV 2018
CountryGermany
CityMunich
Period18/11/118/11/3

Fingerprint

Computer vision
Computer Vision
sentences
computer vision
Pattern recognition
Artificial intelligence
Extractor
Quantitative Evaluation
Detectors
boom
artificial intelligence
Pattern Recognition
evaluation
Artificial Intelligence
Processing
guy wires
Detector
pattern recognition
format
Evaluation

Keywords

  • Document Analysis
  • Paper Summarization
  • Vision and Language

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Yamamoto, S., Fukuhara, Y., Suzuki, R., Morishima, S., & Kataoka, H. (2019). Automatic paper summary generation from visual and textual information. In A. Verikas, D. P. Nikolaev, P. Radeva, & J. Zhou (Eds.), Eleventh International Conference on Machine Vision, ICMV 2018 [110410U] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11041). SPIE. https://doi.org/10.1117/12.2522789

Automatic paper summary generation from visual and textual information. / Yamamoto, Shintaro; Fukuhara, Yoshihiro; Suzuki, Ryota; Morishima, Shigeo; Kataoka, Hirokatsu.

Eleventh International Conference on Machine Vision, ICMV 2018. ed. / Antanas Verikas; Dmitry P. Nikolaev; Petia Radeva; Jianhong Zhou. SPIE, 2019. 110410U (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11041).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yamamoto, S, Fukuhara, Y, Suzuki, R, Morishima, S & Kataoka, H 2019, Automatic paper summary generation from visual and textual information. in A Verikas, DP Nikolaev, P Radeva & J Zhou (eds), Eleventh International Conference on Machine Vision, ICMV 2018., 110410U, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11041, SPIE, 11th International Conference on Machine Vision, ICMV 2018, Munich, Germany, 18/11/1. https://doi.org/10.1117/12.2522789
Yamamoto S, Fukuhara Y, Suzuki R, Morishima S, Kataoka H. Automatic paper summary generation from visual and textual information. In Verikas A, Nikolaev DP, Radeva P, Zhou J, editors, Eleventh International Conference on Machine Vision, ICMV 2018. SPIE. 2019. 110410U. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2522789
Yamamoto, Shintaro ; Fukuhara, Yoshihiro ; Suzuki, Ryota ; Morishima, Shigeo ; Kataoka, Hirokatsu. / Automatic paper summary generation from visual and textual information. Eleventh International Conference on Machine Vision, ICMV 2018. editor / Antanas Verikas ; Dmitry P. Nikolaev ; Petia Radeva ; Jianhong Zhou. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{36a36195a5fc4c1fa16d73f0d1bf7425,
title = "Automatic paper summary generation from visual and textual information",
abstract = "Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the exponentially increasing number of manuscripts. In response to this situation, this paper proposes the paper summary generation (PSG) task using a simple but effective method to automatically generate an academic paper summary from raw PDF data. We realized PSG by combination of vision-based supervised components detector and language-based unsupervised important sentence extractor, which is applicable for a trained format of manuscripts. We show the quantitative evaluation of ability of simple vision-based components extraction, and the qualitative evaluation that our system can extract both visual item and sentence that are helpful for understanding. After processing via our PSG, the 979 manuscripts accepted by the Conference on Computer Vision and Pattern Recognition (CVPR) 2018 are available1. It is believed that the proposed method will provide a better way for researchers to stay caught with important academic papers.",
keywords = "Document Analysis, Paper Summarization, Vision and Language",
author = "Shintaro Yamamoto and Yoshihiro Fukuhara and Ryota Suzuki and Shigeo Morishima and Hirokatsu Kataoka",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2522789",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Antanas Verikas and Nikolaev, {Dmitry P.} and Petia Radeva and Jianhong Zhou",
booktitle = "Eleventh International Conference on Machine Vision, ICMV 2018",

}

TY - GEN

T1 - Automatic paper summary generation from visual and textual information

AU - Yamamoto, Shintaro

AU - Fukuhara, Yoshihiro

AU - Suzuki, Ryota

AU - Morishima, Shigeo

AU - Kataoka, Hirokatsu

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the exponentially increasing number of manuscripts. In response to this situation, this paper proposes the paper summary generation (PSG) task using a simple but effective method to automatically generate an academic paper summary from raw PDF data. We realized PSG by combination of vision-based supervised components detector and language-based unsupervised important sentence extractor, which is applicable for a trained format of manuscripts. We show the quantitative evaluation of ability of simple vision-based components extraction, and the qualitative evaluation that our system can extract both visual item and sentence that are helpful for understanding. After processing via our PSG, the 979 manuscripts accepted by the Conference on Computer Vision and Pattern Recognition (CVPR) 2018 are available1. It is believed that the proposed method will provide a better way for researchers to stay caught with important academic papers.

AB - Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the exponentially increasing number of manuscripts. In response to this situation, this paper proposes the paper summary generation (PSG) task using a simple but effective method to automatically generate an academic paper summary from raw PDF data. We realized PSG by combination of vision-based supervised components detector and language-based unsupervised important sentence extractor, which is applicable for a trained format of manuscripts. We show the quantitative evaluation of ability of simple vision-based components extraction, and the qualitative evaluation that our system can extract both visual item and sentence that are helpful for understanding. After processing via our PSG, the 979 manuscripts accepted by the Conference on Computer Vision and Pattern Recognition (CVPR) 2018 are available1. It is believed that the proposed method will provide a better way for researchers to stay caught with important academic papers.

KW - Document Analysis

KW - Paper Summarization

KW - Vision and Language

UR - http://www.scopus.com/inward/record.url?scp=85063441351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063441351&partnerID=8YFLogxK

U2 - 10.1117/12.2522789

DO - 10.1117/12.2522789

M3 - Conference contribution

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Eleventh International Conference on Machine Vision, ICMV 2018

A2 - Verikas, Antanas

A2 - Nikolaev, Dmitry P.

A2 - Radeva, Petia

A2 - Zhou, Jianhong

PB - SPIE

ER -