Abstract
The rapid popularization of various online media services have attracted large amounts of consumers and shown us a large potential market of video advertising. In this paper, we propose interactive service recommendation based on ad concept hierarchy and contextual search. Instead of traditional ODP (Open Directory Project) based approach, we built a ad domain based concept hierarchy to make the most of the product details over the e-commerce sites. Firstly, we capture the summarization images related to the advertising product in the video content and search visually similar product images from the built product image database. Then, we aggregate the visual tags and textual tags with K-line clustering. Finally, we map them to the product concept space and make keywords suggestion, and users can interactively select keyframes or keywords to personalize their intentions by textual re-search. Experiments and comparison show that the system can accurately provide effective advertising suggestions.
Similar content being viewed by others
References
Bay H, Ess A, Tuytelaars T, Gool LV (2008) Surf: speeded up robust features. Comput Vis Image Underst 110(3):346–359
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522
Berg AC, Malik J (2001) Geometric blur for template matching. In: Proc. CVPR’01, vol 1, pp 607–614
Boiman O, Shechtman E, Irani M (2008) In defense of nearest-neighbor based image classification. In: Proc. CVPR’08, pp 1–8
Bosch A, Zisserman A, Munoz X (2007) Matching local self-similarities across images and videos. In: Proc. CVPR’07, pp 1–8
Chang CH, Hsieh KY, Chiang MC, Wu JL (2010) Virtual spotlighted advertising for tennis videos. J Vis Commun Image Represent 21:595–612
Chen Y, Xue GR, Yu Y (2008) Advertising keyword suggestion based on concept hierarchy. In: Proc. ACM WSDM’08, pp 251–260
Duan LY, Wang J, Zheng Y, Jin JS, Lu H, Xu C (2006) Segmentation, categorization, and identification of commercials from tv streams using multimodal analysis. In: Proc. ACM MM’06, pp 202–210
Fischer I, Poland J (2004) New methods for spectral clustering. Technical report, IDSIA
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proc. CVPR’06, vol 2, pp 2169–2178
Li Y, Tian Y, Duan LY, Yang Y, Huang T, Gao W (2010) Sequence multi-labeling: A unified video annotation scheme with spatial and temporal context. IEEE Trans Multimedia 12:814–828
Ling H, Soato S (2007) Proximity distribution kernels for geometric context in category recognition. In: Proc. ICCV’07, pp 1–8
Liu H, Qiu X, Huang Q, Jiang S, Xu C (2009) Advertise gently - in-image advertising with low intrusiveness. In: Proc. ICIP’09, pp 3105–3108
Ma Z, Pant G, Sheng ORL (2007) Interest-based personalized search. ACM Trans Inf Syst 25(1):5
Manning CD, Raghavan P, Schütze H (2008) Introduction to information retrieval. Cambridge University Press, Cambridge
Marszałek M, Schmid C, Harzallah H, J Weijer (2007) Learning object representations for visual object class recognition. In: Proc. the visual recognition challengeworkshop, in conjunction with ICCV, vol 19, pp 696–710
Mei T, Hua XS, Yang L, Li S (2007) Videosense: towards effective online video advertising. In: Proc. ACM multimedia’07, pp 1075–1084
Mei T, Hua XS, Li S (2008) Contextual in-image advertising. In: Proc. ACM multimedia’08, pp 439–448
Open directory project. http://www.dmoz.org
Shechtman E, Irani M (2007) Matching local self-similarities across images and videos. In: IEEE conference on computer vision and pattern recognition 2007 (CVPR’07), pp 1–8
Sweney M (2009) Internet overtakes television to become biggest advertising sector in the UK. http://www.guardian.co.uk/media/2009/sep/30/internet-biggest-ukadvertising-sector
Sweney M (2010) Interactive media—the new golden goose of branding? http://www.articlesnatch.com/Article/Interactive-Media—The-New-Golden-Goose-Of-Branding-/479306
Wang J, Fang Y, Lu H (2008) Online video advertising based on user’s attention relavancy computing. In: Proc. ICME’08, pp 1161–1164
Wang B, Wang J, Chen S, Duan LY, Lu H (2009) Semantic linking between ad video and web service with progressive search. In: Proc. ICDM workshop on internet multimedia mining, pp 196–201
Wang J, Duan LY, Wang B, Chen S, Ouyang Y, Liu J, Lu H, Gao W (2009) Linking video ads with product or service information by web search. In: Proc. ICME’09, pp 274–277
Wang B, Wang J, Duan LY, Tian Q, Lu H (2010) Interactive service recommendation based on ad concept hierarchy. In: Proc. ICIMCS’10, pp 87–90
Wang B, Wang J, Duan LY, Tian Q, Lu H, Gao W (2010) Interactive web video advertising with context analysis and search. In: Proc. ICPR’10, pp 3252–3255
Wang XJ, Yu M, Zhang L, Cai R, Ma WY (2009) Argo: intelligent advertising by mining a user’s interest from his photo collections. In: KDD Workshop on Data Mining and Audience Intelligence for Advertising, pp. 18–26
Weiss Y, Torralba A, Fergus R (2008) Spectral hashing. In: Proc. NIPS’08
Yang J, Li Y, Tian Y, Duan LY, Gao W (2010) Per-sample multiple kernel approach for visual concept learning. EURASIP J Image Video Process 2010:13
Acknowledgements
The research is supported by National Natural Science Foundation of China (Grant Nos.: 60905008, 60833006, 61070104, 90920303), and National Basic Research Program (973) of China under Contract No. 2010CB327905.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, J., Wang, B., Duan, Ly. et al. Interactive ads recommendation with contextual search on product topic space. Multimed Tools Appl 70, 799–820 (2014). https://doi.org/10.1007/s11042-011-0866-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-011-0866-2