Dynamic subtitle placement considering the region of interest and speaker location

Wataru Akahori, Tatsunori Hirai, Shigeo Morishima

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

1 Citation (Scopus)

Abstract

This paper presents a subtitle placement method that reduces unnecessary eye movements. Although methods that vary the position of subtitles have been discussed in a previous study, subtitles may overlap the region of interest (ROI). Therefore, we propose a dynamic subtitling method that utilizes eye-Tracking data to avoid the subtitles from overlapping with important regions. The proposed method calculates the ROI based on the eye-Tracking data of multiple viewers. By positioning subtitles immediately under the ROI, the subtitles do not overlap the ROI. Furthermore, we detect speakers in a scene based on audio and visual information to help viewers recognize the speaker by positioning subtitles near the speaker. Experimental results show that the proposed method enables viewers to watch the ROI and the subtitle in longer duration than traditional subtitles, and is effective in terms of enhancing the comfort and utility of the viewing experience.

Original languageEnglish
Title of host publicationVISAPP
PublisherSciTePress
Pages102-109
Number of pages8
Volume6
ISBN (Electronic)9789897582271
Publication statusPublished - 2017 Jan 1
Externally publishedYes
Event12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017 - Porto, Portugal
Duration: 2017 Feb 272017 Mar 1

Other

Other12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017
CountryPortugal
CityPorto
Period17/2/2717/3/1

Fingerprint

Eye movements

Keywords

  • Dynamic Subtitles
  • Eye-Tracking
  • Region of Interest
  • Speaker Detection
  • User Experience.

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Akahori, W., Hirai, T., & Morishima, S. (2017). Dynamic subtitle placement considering the region of interest and speaker location. In VISAPP (Vol. 6, pp. 102-109). SciTePress.

Dynamic subtitle placement considering the region of interest and speaker location. / Akahori, Wataru; Hirai, Tatsunori; Morishima, Shigeo.

VISAPP. Vol. 6 SciTePress, 2017. p. 102-109.

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

Akahori, W, Hirai, T & Morishima, S 2017, Dynamic subtitle placement considering the region of interest and speaker location. in VISAPP. vol. 6, SciTePress, pp. 102-109, 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017, Porto, Portugal, 17/2/27.
Akahori W, Hirai T, Morishima S. Dynamic subtitle placement considering the region of interest and speaker location. In VISAPP. Vol. 6. SciTePress. 2017. p. 102-109
Akahori, Wataru ; Hirai, Tatsunori ; Morishima, Shigeo. / Dynamic subtitle placement considering the region of interest and speaker location. VISAPP. Vol. 6 SciTePress, 2017. pp. 102-109
@inproceedings{ea462f516abd4b6eb3e1a2adf328a244,
title = "Dynamic subtitle placement considering the region of interest and speaker location",
abstract = "This paper presents a subtitle placement method that reduces unnecessary eye movements. Although methods that vary the position of subtitles have been discussed in a previous study, subtitles may overlap the region of interest (ROI). Therefore, we propose a dynamic subtitling method that utilizes eye-Tracking data to avoid the subtitles from overlapping with important regions. The proposed method calculates the ROI based on the eye-Tracking data of multiple viewers. By positioning subtitles immediately under the ROI, the subtitles do not overlap the ROI. Furthermore, we detect speakers in a scene based on audio and visual information to help viewers recognize the speaker by positioning subtitles near the speaker. Experimental results show that the proposed method enables viewers to watch the ROI and the subtitle in longer duration than traditional subtitles, and is effective in terms of enhancing the comfort and utility of the viewing experience.",
keywords = "Dynamic Subtitles, Eye-Tracking, Region of Interest, Speaker Detection, User Experience.",
author = "Wataru Akahori and Tatsunori Hirai and Shigeo Morishima",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "6",
pages = "102--109",
booktitle = "VISAPP",
publisher = "SciTePress",

}

TY - GEN

T1 - Dynamic subtitle placement considering the region of interest and speaker location

AU - Akahori, Wataru

AU - Hirai, Tatsunori

AU - Morishima, Shigeo

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This paper presents a subtitle placement method that reduces unnecessary eye movements. Although methods that vary the position of subtitles have been discussed in a previous study, subtitles may overlap the region of interest (ROI). Therefore, we propose a dynamic subtitling method that utilizes eye-Tracking data to avoid the subtitles from overlapping with important regions. The proposed method calculates the ROI based on the eye-Tracking data of multiple viewers. By positioning subtitles immediately under the ROI, the subtitles do not overlap the ROI. Furthermore, we detect speakers in a scene based on audio and visual information to help viewers recognize the speaker by positioning subtitles near the speaker. Experimental results show that the proposed method enables viewers to watch the ROI and the subtitle in longer duration than traditional subtitles, and is effective in terms of enhancing the comfort and utility of the viewing experience.

AB - This paper presents a subtitle placement method that reduces unnecessary eye movements. Although methods that vary the position of subtitles have been discussed in a previous study, subtitles may overlap the region of interest (ROI). Therefore, we propose a dynamic subtitling method that utilizes eye-Tracking data to avoid the subtitles from overlapping with important regions. The proposed method calculates the ROI based on the eye-Tracking data of multiple viewers. By positioning subtitles immediately under the ROI, the subtitles do not overlap the ROI. Furthermore, we detect speakers in a scene based on audio and visual information to help viewers recognize the speaker by positioning subtitles near the speaker. Experimental results show that the proposed method enables viewers to watch the ROI and the subtitle in longer duration than traditional subtitles, and is effective in terms of enhancing the comfort and utility of the viewing experience.

KW - Dynamic Subtitles

KW - Eye-Tracking

KW - Region of Interest

KW - Speaker Detection

KW - User Experience.

UR - http://www.scopus.com/inward/record.url?scp=85047855063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047855063&partnerID=8YFLogxK

M3 - Conference contribution

VL - 6

SP - 102

EP - 109

BT - VISAPP

PB - SciTePress

ER -