Video retrieval using relevant topics extraction from movie subtitles

Bogdan Mocanu; Ruxandra Tapu; Ermina Tapu

doi:10.1109/ISETC.2016.7781123

Video retrieval using relevant topics extraction from movie subtitles

Bogdan Mocanu, Ruxandra Tapu, Ermina Tapu

University 'Politehnica' of Bucharest

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper we propose a novel video retrieval approach based on relevant topics extraction from video subtitles using natural language processing strategies and movie temporal segmentation into scenes. The proposed method is able to identify various subjects existent in a subtitle document and deals with the polysemantic character of words. The approach has been tested on various movie genres, including documentaries, TV series, news, sports. The objective evaluation carried out on a video dataset selected from one week video archive of France Television proves the performance of our technique that returns a mean average precision score superior to 0.5.

Original language	English
Title of host publication	2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	327-330
Number of pages	4
ISBN (Electronic)	9781509037483
DOIs	https://doi.org/10.1109/ISETC.2016.7781123
Publication status	Published - 9 Dec 2016
Externally published	Yes
Event	12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Timisoara, Romania Duration: 27 Oct 2016 → 28 Oct 2016

Publication series

Name	2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings

Conference

Conference	12th International Symposium on Electronics and Telecommunications, ISETC 2016
Country/Territory	Romania
City	Timisoara
Period	27/10/16 → 28/10/16

Keywords

keywords and topic extraction
subtitle
temporal segmentation
video retrieval

Access to Document

10.1109/ISETC.2016.7781123

Cite this

Mocanu, B., Tapu, R., & Tapu, E. (2016). Video retrieval using relevant topics extraction from movie subtitles. In 2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings (pp. 327-330). Article 7781123 (2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISETC.2016.7781123

Mocanu, Bogdan ; Tapu, Ruxandra ; Tapu, Ermina. / Video retrieval using relevant topics extraction from movie subtitles. 2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 327-330 (2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings).

@inproceedings{9001c13e6bae4e99b96452d5bfa53e1b,

title = "Video retrieval using relevant topics extraction from movie subtitles",

abstract = "In this paper we propose a novel video retrieval approach based on relevant topics extraction from video subtitles using natural language processing strategies and movie temporal segmentation into scenes. The proposed method is able to identify various subjects existent in a subtitle document and deals with the polysemantic character of words. The approach has been tested on various movie genres, including documentaries, TV series, news, sports. The objective evaluation carried out on a video dataset selected from one week video archive of France Television proves the performance of our technique that returns a mean average precision score superior to 0.5.",

keywords = "keywords and topic extraction, subtitle, temporal segmentation, video retrieval",

author = "Bogdan Mocanu and Ruxandra Tapu and Ermina Tapu",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 12th International Symposium on Electronics and Telecommunications, ISETC 2016 ; Conference date: 27-10-2016 Through 28-10-2016",

year = "2016",

month = dec,

day = "9",

doi = "10.1109/ISETC.2016.7781123",

language = "English",

series = "2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "327--330",

booktitle = "2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings",

}

Mocanu, B, Tapu, R & Tapu, E 2016, Video retrieval using relevant topics extraction from movie subtitles. in 2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings., 7781123, 2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 327-330, 12th International Symposium on Electronics and Telecommunications, ISETC 2016, Timisoara, Romania, 27/10/16. https://doi.org/10.1109/ISETC.2016.7781123

Video retrieval using relevant topics extraction from movie subtitles. / Mocanu, Bogdan; Tapu, Ruxandra; Tapu, Ermina.
2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 327-330 7781123 (2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Video retrieval using relevant topics extraction from movie subtitles

AU - Mocanu, Bogdan

AU - Tapu, Ruxandra

AU - Tapu, Ermina

PY - 2016/12/9

Y1 - 2016/12/9

N2 - In this paper we propose a novel video retrieval approach based on relevant topics extraction from video subtitles using natural language processing strategies and movie temporal segmentation into scenes. The proposed method is able to identify various subjects existent in a subtitle document and deals with the polysemantic character of words. The approach has been tested on various movie genres, including documentaries, TV series, news, sports. The objective evaluation carried out on a video dataset selected from one week video archive of France Television proves the performance of our technique that returns a mean average precision score superior to 0.5.

AB - In this paper we propose a novel video retrieval approach based on relevant topics extraction from video subtitles using natural language processing strategies and movie temporal segmentation into scenes. The proposed method is able to identify various subjects existent in a subtitle document and deals with the polysemantic character of words. The approach has been tested on various movie genres, including documentaries, TV series, news, sports. The objective evaluation carried out on a video dataset selected from one week video archive of France Television proves the performance of our technique that returns a mean average precision score superior to 0.5.

KW - keywords and topic extraction

KW - subtitle

KW - temporal segmentation

KW - video retrieval

U2 - 10.1109/ISETC.2016.7781123

DO - 10.1109/ISETC.2016.7781123

M3 - Conference contribution

AN - SCOPUS:85010403006

T3 - 2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings

SP - 327

EP - 330

BT - 2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Symposium on Electronics and Telecommunications, ISETC 2016

Y2 - 27 October 2016 through 28 October 2016

ER -

Mocanu B, Tapu R, Tapu E. Video retrieval using relevant topics extraction from movie subtitles. In 2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 327-330. 7781123. (2016 12th International Symposium on Electronics and Telecommunications, ISETC 2016 - Conference Proceedings). doi: 10.1109/ISETC.2016.7781123

Video retrieval using relevant topics extraction from movie subtitles

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this