Video eCommerce++: Toward Large Scale Online Video Advertising

The prevalence of online videos provides an opportunity for e-commerce companies to recommend their products in videos. In this paper, we propose an online video advertising system named Video eCommerce ++, to exhibit appropriate product ads to particular users at proper time stamps of videos, which takes into account video semantics, user shopping preference, and viewing behavior feedback. First, an incremental co-relation regression (ICRR) model is novelly proposed to construct the semantic association between videos and products. To meet the requirement of online advertising, ICRR is implemented in an incremental way to reduce the time complexity. User preference diffusion (UPD) is induced under the framework of heterogeneous information network to construct user-product association from two different e-commerce platforms, Tmall and MagicBox, which alleviates the problems of data sparsity and cold start. A video scene importance model (VSIM) is proposed to model the scene importance by utilizing the user viewing behavior, so that ads can be embedded at the most attractive positions in the video stream. To combine the outputs of ICRR, UPD, and VSIM, a unified distributed heterogeneous relation matrix factorization (D-HRMF) is applied for online video advertising, which is efficiently conducted in parallel to address the real-time update problem, so that the whole system can be performed in real time. Extensive experiments conducted on a variety of online videos from Tmall MagicBox demonstrate that Video eCommerce++ significantly outperforms the state-of-the-art advertising methods, and can handle large-scale data in real time.

[1]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[2]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[3]  Chong-Wah Ngo,et al.  Practical elimination of near-duplicates from web video search , 2007, ACM Multimedia.

[4]  Jure Leskovec,et al.  Inferring Networks of Substitutable and Complementary Products , 2015, KDD.

[5]  Larry S. Davis,et al.  Collaborative Fashion Recommendation: A Functional Tensor Factorization Approach , 2015, ACM Multimedia.

[6]  Søren Holdt Jensen,et al.  Using Audio-Derived Affective Offset to Enhance TV Recommendation , 2014, IEEE Transactions on Multimedia.

[7]  Yang Liu,et al.  Video eCommerce: Towards Online Video Advertising , 2016, ACM Multimedia.

[8]  Marc'Aurelio Ranzato,et al.  Large Scale Distributed Deep Networks , 2012, NIPS.

[9]  Zhou Su,et al.  What Videos Are Similar with You?: Learning a Common Attributed Representation for Video Recommendation , 2014, ACM Multimedia.

[10]  Yizhou Sun,et al.  Personalized entity recommendation: a heterogeneous information network approach , 2014, WSDM.

[11]  Harish Katti,et al.  CAVVA: Computational Affective Video-in-Video Advertising , 2014, IEEE Transactions on Multimedia.

[12]  Yi Zhang,et al.  Novelty and redundancy detection in adaptive filtering , 2002, SIGIR '02.

[13]  Xiaodong He,et al.  A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems , 2015, WWW.

[14]  Tao Mei,et al.  VideoSense: A Contextual In-Video Advertising System , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[15]  Serge J. Belongie,et al.  Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[16]  Tao Mei,et al.  ImageSense: Towards contextual image advertising , 2012, TOMCCAP.

[17]  Trevor Darrell,et al.  LSDA: Large Scale Detection through Adaptation , 2014, NIPS.

[18]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  A. Rubin,et al.  Viewer Aggression and Homophily, Identification, and Parasocial Relationships With Television Characters , 2003 .

[20]  Fillia Makedon,et al.  Learning from Incomplete Ratings Using Non-negative Matrix Factorization , 2006, SDM.

[21]  Tao Mei,et al.  Contextual Internet Multimedia Advertising , 2010, Proceedings of the IEEE.

[22]  Ulrich Paquet,et al.  Beyond Collaborative Filtering: The List Recommendation Problem , 2016, WWW.

[23]  Qi Zhang,et al.  Stock Constrained Recommendation in Tmall , 2015, KDD.

[24]  Jian Zhang,et al.  Social Friend Recommendation Based on Multiple Network Correlation , 2016, IEEE Transactions on Multimedia.

[25]  Peng Jiang,et al.  Life-stage Prediction for Product Recommendation in E-commerce , 2015, KDD.

[26]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[27]  Philip S. Yu,et al.  PathSim , 2011, Proc. VLDB Endow..

[28]  Junjun Li,et al.  Bundle recommendation in ecommerce , 2014, SIGIR.

[29]  Wei-Ying Ma,et al.  Video summarization based on user log enhanced link analysis , 2003, ACM Multimedia.

[30]  Hai Jin,et al.  Differentially Private Online Learning for Cloud-Based Video Recommendation With Multimedia Big Data in Social Networks , 2015, IEEE Transactions on Multimedia.

[31]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[32]  Lifeng Sun,et al.  Joint Social and Content Recommendation for User-Generated Videos in Online Social Network , 2013, IEEE Transactions on Multimedia.

[33]  Guokun Lai,et al.  Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis , 2015, WWW.

[34]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[35]  Jun Wang,et al.  Unifying user-based and item-based collaborative filtering approaches by similarity fusion , 2006, SIGIR.

[36]  Viswanathan Swaminathan,et al.  Selection and Ordering of Linear Online Video Ads , 2015, RecSys.

[37]  Tao Mei,et al.  Contextual in-image advertising , 2008, ACM Multimedia.

[38]  Ido Guy,et al.  Recommending social media content to community owners , 2014, SIGIR.