Multi-modal query expansion for video object instances retrieval

Andrei Bursuc; Titus Zaharia

Multi-modal query expansion for video object instances retrieval

Andrei Bursuc
, Titus Zaharia

Institut Mines-Télécom

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

Abstract

In this paper we tackle the issue of object instances retrieval in video repositories using minimum information from the user (e.g., textual description/tags). Starting for a set of tags, images containing the object of interest are crawled from popular image search engines and repositories (e.g., Bing¹, Fickr², Google³) and the positive and most representative instances of the object are automatically identified. These positive images are then used to generate a visual query descriptor and to retrieve videos containing the object of the interest. This multi-modal approach makes it possible to retrieve video content through images obtained from textual queries, without the use of any advanced learning technique. We test out method on the Flickr corpus of the TRECVID 2012 Instance Search Task.

Original language	English
Title of host publication	Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013
Publisher	MVA Organization
Pages	214-217
Number of pages	4
ISBN (Print)	9784901122139
Publication status	Published - 1 Jan 2013
Externally published	Yes
Event	13th IAPR International Conference on Machine Vision Applications, MVA 2013 - Kyoto, Japan Duration: 20 May 2013 → 23 May 2013

Publication series

Name	Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013

Conference

Conference	13th IAPR International Conference on Machine Vision Applications, MVA 2013
Country/Territory	Japan
City	Kyoto
Period	20/05/13 → 23/05/13

Cite this

@inproceedings{3580f89997b444c8803890092ec86137,

title = "Multi-modal query expansion for video object instances retrieval",

abstract = "In this paper we tackle the issue of object instances retrieval in video repositories using minimum information from the user (e.g., textual description/tags). Starting for a set of tags, images containing the object of interest are crawled from popular image search engines and repositories (e.g., Bing1, Fickr2, Google3) and the positive and most representative instances of the object are automatically identified. These positive images are then used to generate a visual query descriptor and to retrieve videos containing the object of the interest. This multi-modal approach makes it possible to retrieve video content through images obtained from textual queries, without the use of any advanced learning technique. We test out method on the Flickr corpus of the TRECVID 2012 Instance Search Task.",

author = "Andrei Bursuc and Titus Zaharia",

note = "Publisher Copyright: {\textcopyright} 2013; MVA Organization. All rights reserved.; 13th IAPR International Conference on Machine Vision Applications, MVA 2013 ; Conference date: 20-05-2013 Through 23-05-2013",

year = "2013",

month = jan,

day = "1",

language = "English",

isbn = "9784901122139",

series = "Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013",

publisher = "MVA Organization",

pages = "214--217",

booktitle = "Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013",

}

Bursuc, A & Zaharia, T 2013, Multi-modal query expansion for video object instances retrieval. in Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013. Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013, MVA Organization, pp. 214-217, 13th IAPR International Conference on Machine Vision Applications, MVA 2013, Kyoto, Japan, 20/05/13.

Multi-modal query expansion for video object instances retrieval. / Bursuc, Andrei; Zaharia, Titus.
Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013. MVA Organization, 2013. p. 214-217 (Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013).

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

TY - GEN

T1 - Multi-modal query expansion for video object instances retrieval

AU - Bursuc, Andrei

AU - Zaharia, Titus

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this paper we tackle the issue of object instances retrieval in video repositories using minimum information from the user (e.g., textual description/tags). Starting for a set of tags, images containing the object of interest are crawled from popular image search engines and repositories (e.g., Bing1, Fickr2, Google3) and the positive and most representative instances of the object are automatically identified. These positive images are then used to generate a visual query descriptor and to retrieve videos containing the object of the interest. This multi-modal approach makes it possible to retrieve video content through images obtained from textual queries, without the use of any advanced learning technique. We test out method on the Flickr corpus of the TRECVID 2012 Instance Search Task.

AB - In this paper we tackle the issue of object instances retrieval in video repositories using minimum information from the user (e.g., textual description/tags). Starting for a set of tags, images containing the object of interest are crawled from popular image search engines and repositories (e.g., Bing1, Fickr2, Google3) and the positive and most representative instances of the object are automatically identified. These positive images are then used to generate a visual query descriptor and to retrieve videos containing the object of the interest. This multi-modal approach makes it possible to retrieve video content through images obtained from textual queries, without the use of any advanced learning technique. We test out method on the Flickr corpus of the TRECVID 2012 Instance Search Task.

M3 - Conference contribution

AN - SCOPUS:85083072912

SN - 9784901122139

T3 - Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013

SP - 214

EP - 217

BT - Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013

PB - MVA Organization

T2 - 13th IAPR International Conference on Machine Vision Applications, MVA 2013

Y2 - 20 May 2013 through 23 May 2013

ER -

Multi-modal query expansion for video object instances retrieval

Abstract

Publication series

Conference

Fingerprint

Cite this