Bridging the semantic gap in sports

Baoxin Li, James Errico, Hao Pan, Ibrahim Sezan

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

13 Citations (Scopus)

Abstract

One of the major challenges facing current media management systems and the related applications is the so-called "semantic gap" between the rich meaning that a user desires and the shallowness of the content descriptions that are automatically extracted from the media. In this paper, we address the problem of bridging this gap in the sports domain. We propose a general framework for indexing and summarizing sports broadcast programs. The framework is based on a high-level model of sports broadcast video using the concept of an event, defined according to domain-specific knowledge for different types of sports. Within this general framework, we develop automatic event detection algorithms that are based on automatic analysis of the visual and aural signals in the media. We have successfully applied the event detection algorithms to different types of sports including American football, baseball, Japanese sumo wrestling, and soccer. Event modeling and detection contribute to the reduction of the semantic gap by providing rudimentary semantic information obtained through media analysis. We further propose a novel approach, which makes use of independently generated rich textual metadata, to fill the gap completely through synchronization of the information-laden textual data with the basic event segments. An MPEG-7 compliant prototype browsing system has been implemented to demonstrate semantic retrieval and summarization of sports video.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsM.M. Yeung, R.W. Lienhart, C.S. Li
Pages314-326
Number of pages13
Volume5021
DOIs
StatePublished - 2003
Externally publishedYes
EventStorage and Retrieval for Media Databases 2003 - Santa Clara, CA, United States
Duration: Jan 22 2003Jan 23 2003

Other

OtherStorage and Retrieval for Media Databases 2003
CountryUnited States
CitySanta Clara, CA
Period1/22/031/23/03

Fingerprint

semantics
Sports
Semantics
visual signals
metadata
management systems
retrieval
Metadata
synchronism
prototypes
Synchronization

Keywords

  • Event detection
  • Metadata synchronization
  • Video summarization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Li, B., Errico, J., Pan, H., & Sezan, I. (2003). Bridging the semantic gap in sports. In M. M. Yeung, R. W. Lienhart, & C. S. Li (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5021, pp. 314-326) https://doi.org/10.1117/12.476261

Bridging the semantic gap in sports. / Li, Baoxin; Errico, James; Pan, Hao; Sezan, Ibrahim.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / M.M. Yeung; R.W. Lienhart; C.S. Li. Vol. 5021 2003. p. 314-326.

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

Li, B, Errico, J, Pan, H & Sezan, I 2003, Bridging the semantic gap in sports. in MM Yeung, RW Lienhart & CS Li (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5021, pp. 314-326, Storage and Retrieval for Media Databases 2003, Santa Clara, CA, United States, 1/22/03. https://doi.org/10.1117/12.476261
Li B, Errico J, Pan H, Sezan I. Bridging the semantic gap in sports. In Yeung MM, Lienhart RW, Li CS, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 5021. 2003. p. 314-326 https://doi.org/10.1117/12.476261
Li, Baoxin ; Errico, James ; Pan, Hao ; Sezan, Ibrahim. / Bridging the semantic gap in sports. Proceedings of SPIE - The International Society for Optical Engineering. editor / M.M. Yeung ; R.W. Lienhart ; C.S. Li. Vol. 5021 2003. pp. 314-326
@inproceedings{eb83d9a5436944ebbd7bfdb6d2235297,
title = "Bridging the semantic gap in sports",
abstract = "One of the major challenges facing current media management systems and the related applications is the so-called {"}semantic gap{"} between the rich meaning that a user desires and the shallowness of the content descriptions that are automatically extracted from the media. In this paper, we address the problem of bridging this gap in the sports domain. We propose a general framework for indexing and summarizing sports broadcast programs. The framework is based on a high-level model of sports broadcast video using the concept of an event, defined according to domain-specific knowledge for different types of sports. Within this general framework, we develop automatic event detection algorithms that are based on automatic analysis of the visual and aural signals in the media. We have successfully applied the event detection algorithms to different types of sports including American football, baseball, Japanese sumo wrestling, and soccer. Event modeling and detection contribute to the reduction of the semantic gap by providing rudimentary semantic information obtained through media analysis. We further propose a novel approach, which makes use of independently generated rich textual metadata, to fill the gap completely through synchronization of the information-laden textual data with the basic event segments. An MPEG-7 compliant prototype browsing system has been implemented to demonstrate semantic retrieval and summarization of sports video.",
keywords = "Event detection, Metadata synchronization, Video summarization",
author = "Baoxin Li and James Errico and Hao Pan and Ibrahim Sezan",
year = "2003",
doi = "10.1117/12.476261",
language = "English (US)",
volume = "5021",
pages = "314--326",
editor = "M.M. Yeung and R.W. Lienhart and C.S. Li",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Bridging the semantic gap in sports

AU - Li, Baoxin

AU - Errico, James

AU - Pan, Hao

AU - Sezan, Ibrahim

PY - 2003

Y1 - 2003

N2 - One of the major challenges facing current media management systems and the related applications is the so-called "semantic gap" between the rich meaning that a user desires and the shallowness of the content descriptions that are automatically extracted from the media. In this paper, we address the problem of bridging this gap in the sports domain. We propose a general framework for indexing and summarizing sports broadcast programs. The framework is based on a high-level model of sports broadcast video using the concept of an event, defined according to domain-specific knowledge for different types of sports. Within this general framework, we develop automatic event detection algorithms that are based on automatic analysis of the visual and aural signals in the media. We have successfully applied the event detection algorithms to different types of sports including American football, baseball, Japanese sumo wrestling, and soccer. Event modeling and detection contribute to the reduction of the semantic gap by providing rudimentary semantic information obtained through media analysis. We further propose a novel approach, which makes use of independently generated rich textual metadata, to fill the gap completely through synchronization of the information-laden textual data with the basic event segments. An MPEG-7 compliant prototype browsing system has been implemented to demonstrate semantic retrieval and summarization of sports video.

AB - One of the major challenges facing current media management systems and the related applications is the so-called "semantic gap" between the rich meaning that a user desires and the shallowness of the content descriptions that are automatically extracted from the media. In this paper, we address the problem of bridging this gap in the sports domain. We propose a general framework for indexing and summarizing sports broadcast programs. The framework is based on a high-level model of sports broadcast video using the concept of an event, defined according to domain-specific knowledge for different types of sports. Within this general framework, we develop automatic event detection algorithms that are based on automatic analysis of the visual and aural signals in the media. We have successfully applied the event detection algorithms to different types of sports including American football, baseball, Japanese sumo wrestling, and soccer. Event modeling and detection contribute to the reduction of the semantic gap by providing rudimentary semantic information obtained through media analysis. We further propose a novel approach, which makes use of independently generated rich textual metadata, to fill the gap completely through synchronization of the information-laden textual data with the basic event segments. An MPEG-7 compliant prototype browsing system has been implemented to demonstrate semantic retrieval and summarization of sports video.

KW - Event detection

KW - Metadata synchronization

KW - Video summarization

UR - http://www.scopus.com/inward/record.url?scp=0037718460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037718460&partnerID=8YFLogxK

U2 - 10.1117/12.476261

DO - 10.1117/12.476261

M3 - Conference contribution

VL - 5021

SP - 314

EP - 326

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

A2 - Yeung, M.M.

A2 - Lienhart, R.W.

A2 - Li, C.S.

ER -