Web video geolocation by geotagged social resources

Yi Cheng Song; Yong Dong Zhang; Juan Cao; Tian Xia; Wu Liu; Jin Tao Li

doi:10.1109/TMM.2011.2172937

Web video geolocation by geotagged social resources

Yi Cheng Song, Yong Dong Zhang, Juan Cao, Tian Xia, Wu Liu, Jin Tao Li

Information and Decision Sciences

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

15 Scopus citations

Abstract

This paper considers the problem of web video geolocation: we hope to determine where on the Earth a web video was taken. By analyzing a 6.5-million geotagged web video dataset, we observe that there exist inherent geography intimacies between a video with its relevant videos (related videos and same-author videos). This social relationship supplies a direct and effective cue to locate the video to a particular region on the earth. Based on this observation, we propose an effective web video geolocation algorithm by propagating geotags among the web video social relationship graph. For the video that have no geotagged relevant videos, we aim to collect those geotagged relevant images that are content similar with the video (share some visual or textual information with the video) as the cue to infer the location of the video. The experiments have demonstrated the effectiveness of both methods, with the geolocation accuracy much better than state-of-the-art approaches. Finally, an online web video geolocation system: Video2Locatoin (V2L) is developed to provide public access to our algorithm.

Original language	English (US)
Article number	6054059
Pages (from-to)	456-470
Number of pages	15
Journal	IEEE Transactions on Multimedia
Volume	14
Issue number	2
DOIs	https://doi.org/10.1109/TMM.2011.2172937
State	Published - Apr 2012

Bibliographical note

Funding Information:
Manuscript received May 19, 2011; revised August 12, 2011; accepted October 06, 2011. Date of publication October 19, 2011; date of current version March 21, 2012. This work was supported in part by the Natural Science Foundation of Beijing under Grant 4112055, the National Nature Science Foundation of China under Grant 61172153 and Grant 60902090, the Co-building Program of Beijing Municipal Education Commission, Beijing New Star Project on Science & Technology, under Grant 2007B071. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Jiangchuan (JC) Liu.

Keywords

Geolocation by geotagged relevant videos
V2L
geo location by relevant geotagged images
label propagation
video content analysis
web video geolocation

Access

10.1109/TMM.2011.2172937

OpenUrl availability

Full text

Cite this

@article{8545a6bf1eb74951980f8072eb13d6b7,

title = "Web video geolocation by geotagged social resources",

abstract = "This paper considers the problem of web video geolocation: we hope to determine where on the Earth a web video was taken. By analyzing a 6.5-million geotagged web video dataset, we observe that there exist inherent geography intimacies between a video with its relevant videos (related videos and same-author videos). This social relationship supplies a direct and effective cue to locate the video to a particular region on the earth. Based on this observation, we propose an effective web video geolocation algorithm by propagating geotags among the web video social relationship graph. For the video that have no geotagged relevant videos, we aim to collect those geotagged relevant images that are content similar with the video (share some visual or textual information with the video) as the cue to infer the location of the video. The experiments have demonstrated the effectiveness of both methods, with the geolocation accuracy much better than state-of-the-art approaches. Finally, an online web video geolocation system: Video2Locatoin (V2L) is developed to provide public access to our algorithm.",

keywords = "Geolocation by geotagged relevant videos, V2L, geo location by relevant geotagged images, label propagation, video content analysis, web video geolocation",

author = "Song, {Yi Cheng} and Zhang, {Yong Dong} and Juan Cao and Tian Xia and Wu Liu and Li, {Jin Tao}",

note = "Funding Information: Manuscript received May 19, 2011; revised August 12, 2011; accepted October 06, 2011. Date of publication October 19, 2011; date of current version March 21, 2012. This work was supported in part by the Natural Science Foundation of Beijing under Grant 4112055, the National Nature Science Foundation of China under Grant 61172153 and Grant 60902090, the Co-building Program of Beijing Municipal Education Commission, Beijing New Star Project on Science & Technology, under Grant 2007B071. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Jiangchuan (JC) Liu.",

year = "2012",

month = apr,

doi = "10.1109/TMM.2011.2172937",

language = "English (US)",

volume = "14",

pages = "456--470",

journal = "IEEE Transactions on Multimedia",

issn = "1520-9210",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Web video geolocation by geotagged social resources

AU - Song, Yi Cheng

AU - Zhang, Yong Dong

AU - Cao, Juan

AU - Xia, Tian

AU - Liu, Wu

AU - Li, Jin Tao

N1 - Funding Information: Manuscript received May 19, 2011; revised August 12, 2011; accepted October 06, 2011. Date of publication October 19, 2011; date of current version March 21, 2012. This work was supported in part by the Natural Science Foundation of Beijing under Grant 4112055, the National Nature Science Foundation of China under Grant 61172153 and Grant 60902090, the Co-building Program of Beijing Municipal Education Commission, Beijing New Star Project on Science & Technology, under Grant 2007B071. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Jiangchuan (JC) Liu.

PY - 2012/4

Y1 - 2012/4

N2 - This paper considers the problem of web video geolocation: we hope to determine where on the Earth a web video was taken. By analyzing a 6.5-million geotagged web video dataset, we observe that there exist inherent geography intimacies between a video with its relevant videos (related videos and same-author videos). This social relationship supplies a direct and effective cue to locate the video to a particular region on the earth. Based on this observation, we propose an effective web video geolocation algorithm by propagating geotags among the web video social relationship graph. For the video that have no geotagged relevant videos, we aim to collect those geotagged relevant images that are content similar with the video (share some visual or textual information with the video) as the cue to infer the location of the video. The experiments have demonstrated the effectiveness of both methods, with the geolocation accuracy much better than state-of-the-art approaches. Finally, an online web video geolocation system: Video2Locatoin (V2L) is developed to provide public access to our algorithm.

AB - This paper considers the problem of web video geolocation: we hope to determine where on the Earth a web video was taken. By analyzing a 6.5-million geotagged web video dataset, we observe that there exist inherent geography intimacies between a video with its relevant videos (related videos and same-author videos). This social relationship supplies a direct and effective cue to locate the video to a particular region on the earth. Based on this observation, we propose an effective web video geolocation algorithm by propagating geotags among the web video social relationship graph. For the video that have no geotagged relevant videos, we aim to collect those geotagged relevant images that are content similar with the video (share some visual or textual information with the video) as the cue to infer the location of the video. The experiments have demonstrated the effectiveness of both methods, with the geolocation accuracy much better than state-of-the-art approaches. Finally, an online web video geolocation system: Video2Locatoin (V2L) is developed to provide public access to our algorithm.

KW - Geolocation by geotagged relevant videos

KW - V2L

KW - geo location by relevant geotagged images

KW - label propagation

KW - video content analysis

KW - web video geolocation

UR - http://www.scopus.com/inward/record.url?scp=84859010542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859010542&partnerID=8YFLogxK

U2 - 10.1109/TMM.2011.2172937

DO - 10.1109/TMM.2011.2172937

M3 - Article

AN - SCOPUS:84859010542

SN - 1520-9210

VL - 14

SP - 456

EP - 470

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

IS - 2

M1 - 6054059

ER -

Web video geolocation by geotagged social resources

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this