Unsupervised summarization of rushes videos

Yang Liu; Feng Zhou; Wei Liu; Fernando De La Torre; Yan Liu

doi:10.1145/1873951.1874069

Unsupervised summarization of rushes videos

Yang Liu^*
, Feng Zhou
, Wei Liu
, Fernando De La Torre
, Yan Liu^*

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

14 Citations (Scopus)

Abstract

This paper proposes a new framework to formulate summarization of rushes video as an unsupervised learning problem. We pose the problem of video summarization as one of time-series clustering, and proposed Constrained Aligned Cluster Analysis (CACA). CACA combines kernel k-means, Dynamic Time Alignment Kernel (DTAK), and unlike previous work, CACA jointly optimizes video segmentation and shot clustering. CACA is effciently solved via dynamic programming. Experimental results on the TRECVID 2007 and 2008 BBC rushes video summarization databases validate the accuracy and effectiveness of CACA.

Original language	English
Title of host publication	MM'10 - Proceedings of the ACM Multimedia 2010 International Conference
Publisher	Association for Computing Machinery (ACM)
Pages	751-754
Number of pages	4
ISBN (Print)	9781605589336
DOIs	https://doi.org/10.1145/1873951.1874069
Publication status	Published - 25 Oct 2010
Event	18th ACM International Conference on Multimedia ACM Multimedia 2010, MM'10 - Firenze, Italy Duration: 25 Oct 2010 → 29 Oct 2010 https://dl.acm.org/doi/proceedings/10.1145/1873951 (Conference proceeding)

Publication series

Name	Proceedings of the ACM Multimedia International Conference

Conference

Conference	18th ACM International Conference on Multimedia ACM Multimedia 2010, MM'10
Country/Territory	Italy
City	Firenze
Period	25/10/10 → 29/10/10
Internet address	https://dl.acm.org/doi/proceedings/10.1145/1873951 (Conference proceeding)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

User-Defined Keywords

constrained aligned cluster analysis
dynamic programming
dynamic time alignment kernel
rushes video summarization
trecvid
unsupervised learning

Access to Document

10.1145/1873951.1874069

Cite this

@inproceedings{0f40c2aafa4f4ea3b56628d959af4793,

title = "Unsupervised summarization of rushes videos",

abstract = "This paper proposes a new framework to formulate summarization of rushes video as an unsupervised learning problem. We pose the problem of video summarization as one of time-series clustering, and proposed Constrained Aligned Cluster Analysis (CACA). CACA combines kernel k-means, Dynamic Time Alignment Kernel (DTAK), and unlike previous work, CACA jointly optimizes video segmentation and shot clustering. CACA is effciently solved via dynamic programming. Experimental results on the TRECVID 2007 and 2008 BBC rushes video summarization databases validate the accuracy and effectiveness of CACA.",

keywords = "constrained aligned cluster analysis, dynamic programming, dynamic time alignment kernel, rushes video summarization, trecvid, unsupervised learning",

author = "Yang Liu and Feng Zhou and Wei Liu and \{De La Torre\}, Fernando and Yan Liu",

note = "Publisher Copyright: 2010 ACM; 18th ACM International Conference on Multimedia ACM Multimedia 2010, MM'10 ; Conference date: 25-10-2010 Through 29-10-2010",

year = "2010",

month = oct,

day = "25",

doi = "10.1145/1873951.1874069",

language = "English",

isbn = "9781605589336",

series = "Proceedings of the ACM Multimedia International Conference",

publisher = "Association for Computing Machinery (ACM)",

pages = "751--754",

booktitle = "MM'10 - Proceedings of the ACM Multimedia 2010 International Conference",

address = "United States",

url = "https://dl.acm.org/doi/proceedings/10.1145/1873951",

}

Liu, Y, Zhou, F, Liu, W, De La Torre, F & Liu, Y 2010, Unsupervised summarization of rushes videos. in MM'10 - Proceedings of the ACM Multimedia 2010 International Conference. Proceedings of the ACM Multimedia International Conference, Association for Computing Machinery (ACM), pp. 751-754, 18th ACM International Conference on Multimedia ACM Multimedia 2010, MM'10, Firenze, Italy, 25/10/10. https://doi.org/10.1145/1873951.1874069

Unsupervised summarization of rushes videos. / Liu, Yang; Zhou, Feng; Liu, Wei et al.
MM'10 - Proceedings of the ACM Multimedia 2010 International Conference. Association for Computing Machinery (ACM), 2010. p. 751-754 (Proceedings of the ACM Multimedia International Conference).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Unsupervised summarization of rushes videos

AU - Liu, Yang

AU - Zhou, Feng

AU - Liu, Wei

AU - De La Torre, Fernando

AU - Liu, Yan

N1 - Publisher Copyright: 2010 ACM

PY - 2010/10/25

Y1 - 2010/10/25

N2 - This paper proposes a new framework to formulate summarization of rushes video as an unsupervised learning problem. We pose the problem of video summarization as one of time-series clustering, and proposed Constrained Aligned Cluster Analysis (CACA). CACA combines kernel k-means, Dynamic Time Alignment Kernel (DTAK), and unlike previous work, CACA jointly optimizes video segmentation and shot clustering. CACA is effciently solved via dynamic programming. Experimental results on the TRECVID 2007 and 2008 BBC rushes video summarization databases validate the accuracy and effectiveness of CACA.

AB - This paper proposes a new framework to formulate summarization of rushes video as an unsupervised learning problem. We pose the problem of video summarization as one of time-series clustering, and proposed Constrained Aligned Cluster Analysis (CACA). CACA combines kernel k-means, Dynamic Time Alignment Kernel (DTAK), and unlike previous work, CACA jointly optimizes video segmentation and shot clustering. CACA is effciently solved via dynamic programming. Experimental results on the TRECVID 2007 and 2008 BBC rushes video summarization databases validate the accuracy and effectiveness of CACA.

KW - constrained aligned cluster analysis

KW - dynamic programming

KW - dynamic time alignment kernel

KW - rushes video summarization

KW - trecvid

KW - unsupervised learning

UR - https://www.scopus.com/pages/publications/78650991600

U2 - 10.1145/1873951.1874069

DO - 10.1145/1873951.1874069

M3 - Conference proceeding

AN - SCOPUS:78650991600

SN - 9781605589336

T3 - Proceedings of the ACM Multimedia International Conference

SP - 751

EP - 754

BT - MM'10 - Proceedings of the ACM Multimedia 2010 International Conference

PB - Association for Computing Machinery (ACM)

T2 - 18th ACM International Conference on Multimedia ACM Multimedia 2010, MM'10

Y2 - 25 October 2010 through 29 October 2010

ER -

Unsupervised summarization of rushes videos

Abstract

Publication series

Conference

UN SDGs

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this