Large scale video analytics

On-demand, iterative inquiry for moving image research

Virginia Kuhn, Alan Craig, Kevin Franklin, Michael Simeone, Ritu Arora, Dave Bock, Luigi Marini

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

2 Citations (Scopus)

Abstract

Video is exploding as a means of communication and expression, and the resultant archives are massive, disconnected datasets. Thus, scholars' ability to research this crucial aspect of contemporary culture is severely hamstrung by limitations in semantic image retrieval, incomplete metadata, and the lack of a precise understanding of the actual content of any given archive. Our aim in the Large Scale Video Analytics (LSVA) project is to address obstacles in both image-retrieval and research that uses extreme-scale archives of video data that employs a human-machine hybrid process for analyzing moving images. We propose an approach that 1) places more interpretive power in the hands of the human user through novel visualizations of video data, and 2) uses a customized on-demand configuration that enables iterative queries.

Original languageEnglish (US)
Title of host publication2012 IEEE 8th International Conference on E-Science, e-Science 2012
DOIs
StatePublished - Dec 1 2012
Externally publishedYes
Event2012 IEEE 8th International Conference on E-Science, e-Science 2012 - Chicago, IL, United States
Duration: Oct 8 2012Oct 12 2012

Other

Other2012 IEEE 8th International Conference on E-Science, e-Science 2012
CountryUnited States
CityChicago, IL
Period10/8/1210/12/12

Fingerprint

Image retrieval
Metadata
Visualization
Semantics
Communication

Keywords

  • High performance computing
  • Image edge detection
  • Image retrieval
  • Multimedia databases
  • Software
  • Visualization

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Kuhn, V., Craig, A., Franklin, K., Simeone, M., Arora, R., Bock, D., & Marini, L. (2012). Large scale video analytics: On-demand, iterative inquiry for moving image research. In 2012 IEEE 8th International Conference on E-Science, e-Science 2012 [6404446] https://doi.org/10.1109/eScience.2012.6404446

Large scale video analytics : On-demand, iterative inquiry for moving image research. / Kuhn, Virginia; Craig, Alan; Franklin, Kevin; Simeone, Michael; Arora, Ritu; Bock, Dave; Marini, Luigi.

2012 IEEE 8th International Conference on E-Science, e-Science 2012. 2012. 6404446.

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

Kuhn, V, Craig, A, Franklin, K, Simeone, M, Arora, R, Bock, D & Marini, L 2012, Large scale video analytics: On-demand, iterative inquiry for moving image research. in 2012 IEEE 8th International Conference on E-Science, e-Science 2012., 6404446, 2012 IEEE 8th International Conference on E-Science, e-Science 2012, Chicago, IL, United States, 10/8/12. https://doi.org/10.1109/eScience.2012.6404446
Kuhn V, Craig A, Franklin K, Simeone M, Arora R, Bock D et al. Large scale video analytics: On-demand, iterative inquiry for moving image research. In 2012 IEEE 8th International Conference on E-Science, e-Science 2012. 2012. 6404446 https://doi.org/10.1109/eScience.2012.6404446
Kuhn, Virginia ; Craig, Alan ; Franklin, Kevin ; Simeone, Michael ; Arora, Ritu ; Bock, Dave ; Marini, Luigi. / Large scale video analytics : On-demand, iterative inquiry for moving image research. 2012 IEEE 8th International Conference on E-Science, e-Science 2012. 2012.
@inproceedings{3340e9cbb525463583edbbbd303dcca6,
title = "Large scale video analytics: On-demand, iterative inquiry for moving image research",
abstract = "Video is exploding as a means of communication and expression, and the resultant archives are massive, disconnected datasets. Thus, scholars' ability to research this crucial aspect of contemporary culture is severely hamstrung by limitations in semantic image retrieval, incomplete metadata, and the lack of a precise understanding of the actual content of any given archive. Our aim in the Large Scale Video Analytics (LSVA) project is to address obstacles in both image-retrieval and research that uses extreme-scale archives of video data that employs a human-machine hybrid process for analyzing moving images. We propose an approach that 1) places more interpretive power in the hands of the human user through novel visualizations of video data, and 2) uses a customized on-demand configuration that enables iterative queries.",
keywords = "High performance computing, Image edge detection, Image retrieval, Multimedia databases, Software, Visualization",
author = "Virginia Kuhn and Alan Craig and Kevin Franklin and Michael Simeone and Ritu Arora and Dave Bock and Luigi Marini",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/eScience.2012.6404446",
language = "English (US)",
isbn = "9781467344678",
booktitle = "2012 IEEE 8th International Conference on E-Science, e-Science 2012",

}

TY - GEN

T1 - Large scale video analytics

T2 - On-demand, iterative inquiry for moving image research

AU - Kuhn, Virginia

AU - Craig, Alan

AU - Franklin, Kevin

AU - Simeone, Michael

AU - Arora, Ritu

AU - Bock, Dave

AU - Marini, Luigi

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Video is exploding as a means of communication and expression, and the resultant archives are massive, disconnected datasets. Thus, scholars' ability to research this crucial aspect of contemporary culture is severely hamstrung by limitations in semantic image retrieval, incomplete metadata, and the lack of a precise understanding of the actual content of any given archive. Our aim in the Large Scale Video Analytics (LSVA) project is to address obstacles in both image-retrieval and research that uses extreme-scale archives of video data that employs a human-machine hybrid process for analyzing moving images. We propose an approach that 1) places more interpretive power in the hands of the human user through novel visualizations of video data, and 2) uses a customized on-demand configuration that enables iterative queries.

AB - Video is exploding as a means of communication and expression, and the resultant archives are massive, disconnected datasets. Thus, scholars' ability to research this crucial aspect of contemporary culture is severely hamstrung by limitations in semantic image retrieval, incomplete metadata, and the lack of a precise understanding of the actual content of any given archive. Our aim in the Large Scale Video Analytics (LSVA) project is to address obstacles in both image-retrieval and research that uses extreme-scale archives of video data that employs a human-machine hybrid process for analyzing moving images. We propose an approach that 1) places more interpretive power in the hands of the human user through novel visualizations of video data, and 2) uses a customized on-demand configuration that enables iterative queries.

KW - High performance computing

KW - Image edge detection

KW - Image retrieval

KW - Multimedia databases

KW - Software

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=84873616548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873616548&partnerID=8YFLogxK

U2 - 10.1109/eScience.2012.6404446

DO - 10.1109/eScience.2012.6404446

M3 - Conference contribution

SN - 9781467344678

BT - 2012 IEEE 8th International Conference on E-Science, e-Science 2012

ER -