An Advert Creation System for Next-Gen Publicity

作者: Atul Nautiyal , Killian McCabe , Murhaf Hossari , Soumyabrata Dev , Matthew Nicholson

DOI: 10.1007/978-3-030-10997-4_47

关键词: Online advertisingDeep learningVideo sequenceMultimediaComputer sciencePhotogrammetryThe InternetPublicityArtificial intelligence

摘要: With the rapid proliferation of multimedia data in internet, there has been a fast rise creation videos for viewers. This enables viewers to skip advertisement breaks videos, using ad blockers and ‘skip ad’ buttons – bringing online marketing publicity stall. In this paper, we demonstrate system that can effectively integrate new into video sequence. We use state-of-the-art techniques from deep learning computational photogrammetry, effective detection existing adverts, seamless integration adverts sequences. is helpful targeted advertisement, paving path next-gen publicity. Code related paper available at: https://youtu.be/zaKpJZhBVL4.

参考文章(4)
Karen Simonyan, Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition computer vision and pattern recognition. ,(2014)
Patrick Pérez, Michel Gangnet, Andrew Blake, Poisson image editing international conference on computer graphics and interactive techniques. ,vol. 22, pp. 313- 318 ,(2003) , 10.1145/1201775.882269
Bruce D. Lucas, Takeo Kanade, An iterative image registration technique with an application to stereo vision international joint conference on artificial intelligence. pp. 674- 679 ,(1981)
Patrick Pérez, Michel Gangnet, Andrew Blake, Poisson image editing ACM Transactions on Graphics. ,vol. 22, pp. 313- 318 ,(2003) , 10.1145/882262.882269