DFP-ALC: Automatic video summarization using Distinct Frame Patch index and Appearance based Linear Clustering

Sivapriyaa Kannappan; Yonghuai Liu; Bernie Tiddeman

doi:10.1016/j.patrec.2018.12.017

DFP-ALC: Automatic video summarization using Distinct Frame Patch index and Appearance based Linear Clustering

Sivapriyaa Kannappan, Yonghuai Liu, Bernie Tiddeman

Cyfrifiadureg

Allbwn ymchwil: Cyfraniad at gyfnodolyn › Erthygl › adolygiad gan gymheiriaid

9 Dyfyniadau(SciVal)

123 Wedi eu Llwytho i Lawr (Pure)

Crynodeb

Video summarization aims to create a succinct representation of videos for efficient browsing and retrieval. We propose an innovative method for the task. It includes two main steps: (i) the first step proposes a Distinct Frame Patch (DFP) index for selecting a set of good candidate frames, and (ii) the second step proposes a novel Appearance based Linear Clustering (ALC) to refine them for distinct ones. While the first step measures the content of frames, the second step considers to what extent one frame is different from another in both the spatial and temporal spaces. The experiments are performed over two publicly accessible datasets. The results show the effectiveness and efficiency of the proposed method when compared with other state-of-the-art techniques.

Iaith wreiddiol	Saesneg
Tudalennau (o-i)	8-16
Nifer y tudalennau	9
Cyfnodolyn	Pattern Recognition Letters
Cyfrol	120
Dyddiad ar-lein cynnar	23 Rhag 2018
Dynodwyr Gwrthrych Digidol (DOIs)	https://doi.org/10.1016/j.patrec.2018.12.017
Statws	Cyhoeddwyd - 01 Ebr 2019

Mynediad at Ddogfen

10.1016/j.patrec.2018.12.017

DFP-ALC: Automatic Video Summarization Using Distinct Frame Patch Index and Appearance based Linear ClusteringLlawysgrif awdur wedi’i dderbyn, 5.17 MBTrwydded: CC BY-NC-ND

Cysylltiad parhaol

Dolen barhaus

Ffeiliau eraill a chysylltiadau

Dolen i’r cyhoeddiad yn Scopus

Bernie Tiddeman
- bptaber.acuk
- Cyfadran Busnes a’r Gwyddorau Ffisegol, Cyfrifiadureg - Professor in Computer Science
Unigolyn: Dysgu ac Ymchwil

Dyfynnu hyn

@article{be87291e00a64e2390b90090d4c63dbd,

title = "DFP-ALC: Automatic video summarization using Distinct Frame Patch index and Appearance based Linear Clustering",

abstract = "Video summarization aims to create a succinct representation of videos for efficient browsing and retrieval. We propose an innovative method for the task. It includes two main steps: (i) the first step proposes a Distinct Frame Patch (DFP) index for selecting a set of good candidate frames, and (ii) the second step proposes a novel Appearance based Linear Clustering (ALC) to refine them for distinct ones. While the first step measures the content of frames, the second step considers to what extent one frame is different from another in both the spatial and temporal spaces. The experiments are performed over two publicly accessible datasets. The results show the effectiveness and efficiency of the proposed method when compared with other state-of-the-art techniques.",

keywords = "Appearance based Linear clustering, Bayesian information criterion, Candidate frame selection, Distinct frame patch index, Keyframe extraction, Video summarization",

author = "Sivapriyaa Kannappan and Yonghuai Liu and Bernie Tiddeman",

note = "Funding Information: The first author is grateful for the award given by Aberystwyth University under the Departmental Overseas Scholarship (DOS) and partly funding by Object Matrix, Ltd on the project. We are also grateful to the anonymous reviewers for their insightful comments that have improved the clarity and the readability of the paper. Publisher Copyright: {\textcopyright} 2018",

year = "2019",

month = apr,

day = "1",

doi = "10.1016/j.patrec.2018.12.017",

language = "English",

volume = "120",

pages = "8--16",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier",

}

TY - JOUR

T1 - DFP-ALC

T2 - Automatic video summarization using Distinct Frame Patch index and Appearance based Linear Clustering

AU - Kannappan, Sivapriyaa

AU - Liu, Yonghuai

AU - Tiddeman, Bernie

N1 - Funding Information: The first author is grateful for the award given by Aberystwyth University under the Departmental Overseas Scholarship (DOS) and partly funding by Object Matrix, Ltd on the project. We are also grateful to the anonymous reviewers for their insightful comments that have improved the clarity and the readability of the paper. Publisher Copyright: © 2018

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Video summarization aims to create a succinct representation of videos for efficient browsing and retrieval. We propose an innovative method for the task. It includes two main steps: (i) the first step proposes a Distinct Frame Patch (DFP) index for selecting a set of good candidate frames, and (ii) the second step proposes a novel Appearance based Linear Clustering (ALC) to refine them for distinct ones. While the first step measures the content of frames, the second step considers to what extent one frame is different from another in both the spatial and temporal spaces. The experiments are performed over two publicly accessible datasets. The results show the effectiveness and efficiency of the proposed method when compared with other state-of-the-art techniques.

AB - Video summarization aims to create a succinct representation of videos for efficient browsing and retrieval. We propose an innovative method for the task. It includes two main steps: (i) the first step proposes a Distinct Frame Patch (DFP) index for selecting a set of good candidate frames, and (ii) the second step proposes a novel Appearance based Linear Clustering (ALC) to refine them for distinct ones. While the first step measures the content of frames, the second step considers to what extent one frame is different from another in both the spatial and temporal spaces. The experiments are performed over two publicly accessible datasets. The results show the effectiveness and efficiency of the proposed method when compared with other state-of-the-art techniques.

KW - Appearance based Linear clustering

KW - Bayesian information criterion

KW - Candidate frame selection

KW - Distinct frame patch index

KW - Keyframe extraction

KW - Video summarization

UR - http://www.scopus.com/inward/record.url?scp=85059165365&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2018.12.017

DO - 10.1016/j.patrec.2018.12.017

M3 - Article

SN - 0167-8655

VL - 120

SP - 8

EP - 16

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

ER -

DFP-ALC: Automatic video summarization using Distinct Frame Patch index and Appearance based Linear Clustering

Crynodeb

Mynediad at Ddogfen

Cysylltiad parhaol

Ffeiliau eraill a chysylltiadau

Ôl bys

Proffiliau

Bernie Tiddeman

Dyfynnu hyn