Mining adjacent markets from a large-scale ads video collection for image advertising

Guwen Feng; Xin-Jing Wang; Lei Zhang; Wei-Ying Ma

doi:10.1145/1835449.1835669

Mining adjacent markets from a large-scale ads video collection for image advertising

Guwen Feng
, Xin-Jing Wang
, Lei Zhang
, Wei-Ying Ma

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

The research on image advertising is still in its infancy. Most previous approaches suggest ads by directly matching an ad to a query image, which lacks the power to identify ads from adjacent market. In this paper, we tackle the problem by mining knowledge on adjacent markets from ads videos with a novel Multi-Modal Dirichlet Process Mixture Sets model, which is a unified model of (video frames) clustering and (ads) ranking. Our approach is not only capable of discovering relevant ads (e.g. car ads for a query car image), but also suggesting ads from adjacent markets (e.g. tyre ads). Experimental results show that our proposed approach is fairly effective. © 2010 ACM.

Original language	English
Title of host publication	SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
Pages	893-894
DOIs	https://doi.org/10.1145/1835449.1835669
Publication status	Published - 2010
Externally published	Yes
Event	33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2010 - Geneva, Switzerland Duration: 19 Jul 2010 → 23 Jul 2010 https://dl.acm.org/doi/proceedings/10.1145/1835449

Publication series

Name	SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference	33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2010
Place	Switzerland
City	Geneva
Period	19/07/10 → 23/07/10
Internet address	https://dl.acm.org/doi/proceedings/10.1145/1835449

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

Adjacent marketing
Image advertising
Video retrieval

Access Output

10.1145/1835449.1835669

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Feng, G., Wang, X.-J., Zhang, L., & Ma, W.-Y. (2010). Mining adjacent markets from a large-scale ads video collection for image advertising. In SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 893-894). (SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval). https://doi.org/10.1145/1835449.1835669

Feng, Guwen ; Wang, Xin-Jing ; Zhang, Lei et al. / Mining adjacent markets from a large-scale ads video collection for image advertising. SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 2010. pp. 893-894 (SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval).

@inproceedings{58ba0f42c1c14ef78af3609a6657122e,

title = "Mining adjacent markets from a large-scale ads video collection for image advertising",

abstract = "The research on image advertising is still in its infancy. Most previous approaches suggest ads by directly matching an ad to a query image, which lacks the power to identify ads from adjacent market. In this paper, we tackle the problem by mining knowledge on adjacent markets from ads videos with a novel Multi-Modal Dirichlet Process Mixture Sets model, which is a unified model of (video frames) clustering and (ads) ranking. Our approach is not only capable of discovering relevant ads (e.g. car ads for a query car image), but also suggesting ads from adjacent markets (e.g. tyre ads). Experimental results show that our proposed approach is fairly effective. {\textcopyright} 2010 ACM.",

keywords = "Adjacent marketing, Image advertising, Video retrieval",

author = "Guwen Feng and Xin-Jing Wang and Lei Zhang and Wei-Ying Ma",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2010 ; Conference date: 19-07-2010 Through 23-07-2010",

year = "2010",

doi = "10.1145/1835449.1835669",

language = "English",

isbn = "9781605588964",

series = "SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval",

pages = "893--894",

booktitle = "SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval",

url = "https://dl.acm.org/doi/proceedings/10.1145/1835449",

}

Feng, G, Wang, X-J, Zhang, L & Ma, W-Y 2010, Mining adjacent markets from a large-scale ads video collection for image advertising. in SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 893-894, 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2010, Geneva, Switzerland, 19/07/10. https://doi.org/10.1145/1835449.1835669

Mining adjacent markets from a large-scale ads video collection for image advertising. / Feng, Guwen; Wang, Xin-Jing; Zhang, Lei et al.
SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 2010. p. 893-894 (SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Mining adjacent markets from a large-scale ads video collection for image advertising

AU - Feng, Guwen

AU - Wang, Xin-Jing

AU - Zhang, Lei

AU - Ma, Wei-Ying

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2010

Y1 - 2010

N2 - The research on image advertising is still in its infancy. Most previous approaches suggest ads by directly matching an ad to a query image, which lacks the power to identify ads from adjacent market. In this paper, we tackle the problem by mining knowledge on adjacent markets from ads videos with a novel Multi-Modal Dirichlet Process Mixture Sets model, which is a unified model of (video frames) clustering and (ads) ranking. Our approach is not only capable of discovering relevant ads (e.g. car ads for a query car image), but also suggesting ads from adjacent markets (e.g. tyre ads). Experimental results show that our proposed approach is fairly effective. © 2010 ACM.

AB - The research on image advertising is still in its infancy. Most previous approaches suggest ads by directly matching an ad to a query image, which lacks the power to identify ads from adjacent market. In this paper, we tackle the problem by mining knowledge on adjacent markets from ads videos with a novel Multi-Modal Dirichlet Process Mixture Sets model, which is a unified model of (video frames) clustering and (ads) ranking. Our approach is not only capable of discovering relevant ads (e.g. car ads for a query car image), but also suggesting ads from adjacent markets (e.g. tyre ads). Experimental results show that our proposed approach is fairly effective. © 2010 ACM.

KW - Adjacent marketing

KW - Image advertising

KW - Video retrieval

UR - https://www.scopus.com/pages/publications/77956016050

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-77956016050&origin=recordpage

U2 - 10.1145/1835449.1835669

DO - 10.1145/1835449.1835669

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781605588964

T3 - SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

SP - 893

EP - 894

BT - SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

T2 - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2010

Y2 - 19 July 2010 through 23 July 2010

ER -

Feng G, Wang XJ, Zhang L, Ma WY. Mining adjacent markets from a large-scale ads video collection for image advertising. In SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 2010. p. 893-894. (SIGIR 2010 Proceedings - 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval). doi: 10.1145/1835449.1835669

Mining adjacent markets from a large-scale ads video collection for image advertising

Abstract

Publication series

Conference

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this