Towards auto-documentary: Tracking the evolution of news stories

Pinar Duygulu, Jia Yu Pan, David Alexander Forsyth

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

Abstract

News videos constitute an important source of information for tracking and documenting important events. In these videos, news stories are often accompanied by short video shots that tend to be repeated during the course of the event. Automatic detection of such repetitions is essential for creating auto-documentaries, for alleviating the limitation of traditional textual topic detection methods. In this paper, we propose novel methods for detecting and tracking the evolution of news over time. The proposed method exploits both visual cues and textual information to summarize evolving news stories. Experiments are carried on the TREC-VID data set consisting of 120 hours of news videos from two different channels.

Original languageEnglish (US)
Title of host publicationACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia
Pages820-827
Number of pages8
StatePublished - Dec 1 2004
Externally publishedYes
EventACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia - New York, NY, United States
Duration: Oct 10 2004Oct 16 2004

Publication series

NameACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia

Other

OtherACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia
CountryUnited States
CityNew York, NY
Period10/10/0410/16/04

Fingerprint

Experiments

Keywords

  • Auto-documentary
  • Duplicate sequences
  • Graph-based multi-modal topic discovery
  • Matching logos
  • News video analysis

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Duygulu, P., Pan, J. Y., & Forsyth, D. A. (2004). Towards auto-documentary: Tracking the evolution of news stories. In ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia (pp. 820-827). (ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia).

Towards auto-documentary : Tracking the evolution of news stories. / Duygulu, Pinar; Pan, Jia Yu; Forsyth, David Alexander.

ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. 2004. p. 820-827 (ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia).

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

Duygulu, P, Pan, JY & Forsyth, DA 2004, Towards auto-documentary: Tracking the evolution of news stories. in ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia, pp. 820-827, ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia, New York, NY, United States, 10/10/04.
Duygulu P, Pan JY, Forsyth DA. Towards auto-documentary: Tracking the evolution of news stories. In ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. 2004. p. 820-827. (ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia).
Duygulu, Pinar ; Pan, Jia Yu ; Forsyth, David Alexander. / Towards auto-documentary : Tracking the evolution of news stories. ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. 2004. pp. 820-827 (ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia).
@inproceedings{90564b8ea1d0405cb61ad024f3c8c1cf,
title = "Towards auto-documentary: Tracking the evolution of news stories",
abstract = "News videos constitute an important source of information for tracking and documenting important events. In these videos, news stories are often accompanied by short video shots that tend to be repeated during the course of the event. Automatic detection of such repetitions is essential for creating auto-documentaries, for alleviating the limitation of traditional textual topic detection methods. In this paper, we propose novel methods for detecting and tracking the evolution of news over time. The proposed method exploits both visual cues and textual information to summarize evolving news stories. Experiments are carried on the TREC-VID data set consisting of 120 hours of news videos from two different channels.",
keywords = "Auto-documentary, Duplicate sequences, Graph-based multi-modal topic discovery, Matching logos, News video analysis",
author = "Pinar Duygulu and Pan, {Jia Yu} and Forsyth, {David Alexander}",
year = "2004",
month = "12",
day = "1",
language = "English (US)",
isbn = "1581138938",
series = "ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia",
pages = "820--827",
booktitle = "ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia",

}

TY - GEN

T1 - Towards auto-documentary

T2 - Tracking the evolution of news stories

AU - Duygulu, Pinar

AU - Pan, Jia Yu

AU - Forsyth, David Alexander

PY - 2004/12/1

Y1 - 2004/12/1

N2 - News videos constitute an important source of information for tracking and documenting important events. In these videos, news stories are often accompanied by short video shots that tend to be repeated during the course of the event. Automatic detection of such repetitions is essential for creating auto-documentaries, for alleviating the limitation of traditional textual topic detection methods. In this paper, we propose novel methods for detecting and tracking the evolution of news over time. The proposed method exploits both visual cues and textual information to summarize evolving news stories. Experiments are carried on the TREC-VID data set consisting of 120 hours of news videos from two different channels.

AB - News videos constitute an important source of information for tracking and documenting important events. In these videos, news stories are often accompanied by short video shots that tend to be repeated during the course of the event. Automatic detection of such repetitions is essential for creating auto-documentaries, for alleviating the limitation of traditional textual topic detection methods. In this paper, we propose novel methods for detecting and tracking the evolution of news over time. The proposed method exploits both visual cues and textual information to summarize evolving news stories. Experiments are carried on the TREC-VID data set consisting of 120 hours of news videos from two different channels.

KW - Auto-documentary

KW - Duplicate sequences

KW - Graph-based multi-modal topic discovery

KW - Matching logos

KW - News video analysis

UR - http://www.scopus.com/inward/record.url?scp=13444260830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13444260830&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:13444260830

SN - 1581138938

SN - 9781581138931

T3 - ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia

SP - 820

EP - 827

BT - ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia

ER -