Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08

Jinchang Ren, J. Jiang , Christian Eckes

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

5 Citations (Scopus)

Abstract

In this paper, our techniques used in TRECVID'08 on BBC rush summarization are described. Firstly, rush videos are hierarchical modeled using formal language description. Then, shot detection and V-unit determination are applied for video structuring; junk frames within the model are also effectively removed. Thirdly, adaptive clustering is employed to group shots into clusters to remove retakes. Then, each selected shot is ranked according to its length and sum of activity level for summarization. Competitive results have proved the effectiveness and efficiency of our techniques fully implemented in compressed-domain.
LanguageEnglish
Title of host publicationTVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop
Pages26-30
Number of pages5
DOIs
Publication statusPublished - 2008
EventTRECVid 2008 - , United Kingdom
Duration: 1 Feb 2008 → …

Conference

ConferenceTRECVid 2008
CountryUnited Kingdom
Period1/02/08 → …

Fingerprint

Formal languages

Keywords

  • adaptive clustering
  • hierarchical modelling

Cite this

Ren, J., Jiang , J., & Eckes, C. (2008). Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08. In TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop (pp. 26-30) https://doi.org/10.1145/1463563.1463566
Ren, Jinchang ; Jiang , J. ; Eckes, Christian. / Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08. TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop. 2008. pp. 26-30
@inproceedings{bb4ec7f668ae4c4c87baef04e0f50cc4,
title = "Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08",
abstract = "In this paper, our techniques used in TRECVID'08 on BBC rush summarization are described. Firstly, rush videos are hierarchical modeled using formal language description. Then, shot detection and V-unit determination are applied for video structuring; junk frames within the model are also effectively removed. Thirdly, adaptive clustering is employed to group shots into clusters to remove retakes. Then, each selected shot is ranked according to its length and sum of activity level for summarization. Competitive results have proved the effectiveness and efficiency of our techniques fully implemented in compressed-domain.",
keywords = "adaptive clustering, hierarchical modelling",
author = "Jinchang Ren and J. Jiang and Christian Eckes",
year = "2008",
doi = "10.1145/1463563.1463566",
language = "English",
isbn = "978-1-60558-309-9",
pages = "26--30",
booktitle = "TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop",

}

Ren, J, Jiang , J & Eckes, C 2008, Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08. in TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop. pp. 26-30, TRECVid 2008, United Kingdom, 1/02/08. https://doi.org/10.1145/1463563.1463566

Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08. / Ren, Jinchang; Jiang , J.; Eckes, Christian.

TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop. 2008. p. 26-30.

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

TY - GEN

T1 - Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08

AU - Ren, Jinchang

AU - Jiang , J.

AU - Eckes, Christian

PY - 2008

Y1 - 2008

N2 - In this paper, our techniques used in TRECVID'08 on BBC rush summarization are described. Firstly, rush videos are hierarchical modeled using formal language description. Then, shot detection and V-unit determination are applied for video structuring; junk frames within the model are also effectively removed. Thirdly, adaptive clustering is employed to group shots into clusters to remove retakes. Then, each selected shot is ranked according to its length and sum of activity level for summarization. Competitive results have proved the effectiveness and efficiency of our techniques fully implemented in compressed-domain.

AB - In this paper, our techniques used in TRECVID'08 on BBC rush summarization are described. Firstly, rush videos are hierarchical modeled using formal language description. Then, shot detection and V-unit determination are applied for video structuring; junk frames within the model are also effectively removed. Thirdly, adaptive clustering is employed to group shots into clusters to remove retakes. Then, each selected shot is ranked according to its length and sum of activity level for summarization. Competitive results have proved the effectiveness and efficiency of our techniques fully implemented in compressed-domain.

KW - adaptive clustering

KW - hierarchical modelling

U2 - 10.1145/1463563.1463566

DO - 10.1145/1463563.1463566

M3 - Conference contribution book

SN - 978-1-60558-309-9

SP - 26

EP - 30

BT - TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop

ER -

Ren J, Jiang J, Eckes C. Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08. In TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop. 2008. p. 26-30 https://doi.org/10.1145/1463563.1463566