Mixed ranking scheme for video retrieval

Y. Feng; Jinchang Ren; J. Jiang

doi:10.1049/el.2010.8621

Mixed ranking scheme for video retrieval

Y. Feng
, Jinchang Ren
, J. Jiang

Electronic And Electrical Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

A unified ranking scheme for effective video retrieval is proposed, in which low-level visual feature terms and high-level image category features are combined organically to inspire effective retrieval in the manner of semantics. By taking these features as a joint fact of document relevance, the BM25 model, popular in text retrieval, is employed to determine a mixed similarity rank of video documents. Experiments using the well-known TRECVID retrieval dataset have validated the superiority of the methodology.

Original language	English
Pages (from-to)	1600-1601
Number of pages	2
Journal	Electronics Letters
Volume	46
Issue number	24
DOIs	https://doi.org/10.1049/el.2010.8621
Publication status	Published - 25 Nov 2010

Keywords

video retrieval
feature extraction
content-based retrieval
mixed ranking scheme
video document ranking

Access to Document

10.1049/el.2010.8621

Cite this

@article{6bbcff418fde4bd9a122a82cca0ec562,

title = "Mixed ranking scheme for video retrieval",

abstract = "A unified ranking scheme for effective video retrieval is proposed, in which low-level visual feature terms and high-level image category features are combined organically to inspire effective retrieval in the manner of semantics. By taking these features as a joint fact of document relevance, the BM25 model, popular in text retrieval, is employed to determine a mixed similarity rank of video documents. Experiments using the well-known TRECVID retrieval dataset have validated the superiority of the methodology.",

keywords = "video retrieval, feature extraction, content-based retrieval, mixed ranking scheme , video document ranking",

author = "Y. Feng and Jinchang Ren and J. Jiang",

year = "2010",

month = nov,

day = "25",

doi = "10.1049/el.2010.8621",

language = "English",

volume = "46",

pages = "1600--1601",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "John Wiley \& Sons Inc.",

number = "24",

}

TY - JOUR

T1 - Mixed ranking scheme for video retrieval

AU - Feng, Y.

AU - Ren, Jinchang

AU - Jiang , J.

PY - 2010/11/25

Y1 - 2010/11/25

N2 - A unified ranking scheme for effective video retrieval is proposed, in which low-level visual feature terms and high-level image category features are combined organically to inspire effective retrieval in the manner of semantics. By taking these features as a joint fact of document relevance, the BM25 model, popular in text retrieval, is employed to determine a mixed similarity rank of video documents. Experiments using the well-known TRECVID retrieval dataset have validated the superiority of the methodology.

AB - A unified ranking scheme for effective video retrieval is proposed, in which low-level visual feature terms and high-level image category features are combined organically to inspire effective retrieval in the manner of semantics. By taking these features as a joint fact of document relevance, the BM25 model, popular in text retrieval, is employed to determine a mixed similarity rank of video documents. Experiments using the well-known TRECVID retrieval dataset have validated the superiority of the methodology.

KW - video retrieval

KW - feature extraction

KW - content-based retrieval

KW - mixed ranking scheme

KW - video document ranking

U2 - 10.1049/el.2010.8621

DO - 10.1049/el.2010.8621

M3 - Article

SN - 0013-5194

VL - 46

SP - 1600

EP - 1601

JO - Electronics Letters

JF - Electronics Letters

IS - 24

ER -

Mixed ranking scheme for video retrieval

Abstract

Keywords

Access to Document

Fingerprint

Cite this