Video retrieval by feature learning in key frames

M J  Pickering; S M  Ruger; D  Sinclair

Video retrieval by feature learning in key frames

M J Pickering, S M Ruger, D Sinclair

School of Philosophy, Psychology and Language Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

We evaluate the application of feature-vector based image retrieval methods to the problem of video retrieval. A vast number of primitive features is. calculated for each of the key frames generated by a segmentation process, and we examine the use of three methods for retrieving video segments using the features - a vector space model, a learning method using the AdaBoost algorithm, and a k-nearest neighbour approach.

Original language	English
Title of host publication	Image and Video Retrieval
Editors	MS Lew, N Sebe, JP Eakins
Place of Publication	Berlin
Publisher	Springer
Pages	309-317
Number of pages	9
ISBN (Print)	3-540-43899-8
Publication status	Published - 2002

Cite this

@inproceedings{a01b5df52d0a48308273de09dfcc3388,

title = "Video retrieval by feature learning in key frames",

abstract = "We evaluate the application of feature-vector based image retrieval methods to the problem of video retrieval. A vast number of primitive features is. calculated for each of the key frames generated by a segmentation process, and we examine the use of three methods for retrieving video segments using the features - a vector space model, a learning method using the AdaBoost algorithm, and a k-nearest neighbour approach.",

author = "Pickering, {M J} and Ruger, {S M} and D Sinclair",

year = "2002",

language = "English",

isbn = "3-540-43899-8",

pages = "309--317",

editor = "MS Lew and N Sebe and JP Eakins",

booktitle = "Image and Video Retrieval",

publisher = "Springer",

address = "United Kingdom",

}

TY - GEN

T1 - Video retrieval by feature learning in key frames

AU - Pickering, M J

AU - Ruger, S M

AU - Sinclair, D

PY - 2002

Y1 - 2002

N2 - We evaluate the application of feature-vector based image retrieval methods to the problem of video retrieval. A vast number of primitive features is. calculated for each of the key frames generated by a segmentation process, and we examine the use of three methods for retrieving video segments using the features - a vector space model, a learning method using the AdaBoost algorithm, and a k-nearest neighbour approach.

AB - We evaluate the application of feature-vector based image retrieval methods to the problem of video retrieval. A vast number of primitive features is. calculated for each of the key frames generated by a segmentation process, and we examine the use of three methods for retrieving video segments using the features - a vector space model, a learning method using the AdaBoost algorithm, and a k-nearest neighbour approach.

M3 - Conference contribution

SN - 3-540-43899-8

SP - 309

EP - 317

BT - Image and Video Retrieval

A2 - Lew, MS

A2 - Sebe, N

A2 - Eakins, JP

PB - Springer

CY - Berlin

ER -

Video retrieval by feature learning in key frames

Abstract / Description of output

Fingerprint

Cite this