Integrated Analytic Methodology Using Visual Image and Meta-Data for Product Recommendation
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Because the big data industry holds a significant position nowadays, Meta-Data has been adopted rapidly in various fields. In this paper, we introduce a model that exploits Meta-Data consisting of numerous production data to extract features using a pretrained deep learning model with image and text information. Thus, we can build a relational model between the production data to realize a recommendation system. Regarding the dataset, we determined that combining both image and text data is better than using one type of data to achieve a more accurate prediction from the relational model. Concerning the condition of two mixed languages (English and Korean), the method produces a satisfactory result. According to the relational model of the two products, we can design a recommendation system that suggests products that would be of interest to consumers.
Abstract
Because the big data industry holds a significant position nowadays, Meta-Data has been adopted rapidly in various fields. In this paper, we introduce a model that exploits Meta-Data consisting of numerous production data to extract features using a pretrained deep learning model with image and text information. Thus, we can build a relational model between the production data to realize a recommendation system. Regarding the dataset, we determined that combining both image and text data is better than using one type of data to achieve a more accurate prediction from the relational model. Concerning the condition of two mixed languages (English and Korean), the method produces a satisfactory result. According to the relational model of the two products, we can design a recommendation system that suggests products that would be of interest to consumers.
참고문헌 (17)
- Russakovsky O, "Imagenet large scale visual recognition challenge", Int J Comput Vision, 115, pp.211~252 (2015)
- Krizhevsky A, "Imagenet classification with deep convolutional neural networks", Adv Neur In, 25, pp.1106~1114 (2012)
- Simonyan K, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556, ~ (2014)
- Szegedy C, "Going deeper with convolutions", Proc Cvpr Ieee, pp.1~9 (2015)
- He K, "Deep residual learning for image recognition", Proc Cvpr Ieee, pp.770~778 (2016)
- Howard AG, "Mobilenets : Efficient convolutional neural networks for mobile vision applications", arXiv preprint arXiv:1704.04861, ~ (2017)
- Sandler M, "Mobilenetv2 : Inverted residuals and linear bottlenecks", Proc Cvpr Ieee, pp.4510~4520 (2018)
- Howard A, "Searching for mobilenetv3", Ieee I Conf Comp Vis, pp.1314~1324 (2019)
- Mikolov T, "Recurrent neural network based language model", Conf. of the International Speech Communication Association (INTER SPEECH), pp.1045~1048 (2010)
- Sak H, "Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition", arXiv preprint arXiv:1402.1128, ~ (2014)
- Sutskever I, "Sequence to sequence learning with neural networks", Adv Neur In, 27, pp.3104~3112 (2014)[DOI]
- Bahdanau D, "Neural machine translation by jointly learning to align and translate", arXiv preprint arXiv:1409. 0473, ~ (2014)
- Vaswani A, "Attention is all you need", Adv Neur In, 30, pp.5998~6008 (2017)[DOI]
- Devlin J, "BERT: Pre-training of deep bidirectional transformers for language understanding", arXiv preprint arXiv:1810.04805, ~ (2018)
- Reimers N, "Sentence-bert : Sentence embeddings using siamese bert-networks", arXiv preprint arXiv:1908.10084, ~ (2019)
- Ni J, "Justifying recommendations using distantly-labeled reviews and fine-grained aspects", Conf. on Empirical Methods in Natural Language Processing (EMNLP), pp.188~197 (2019)
- McAuley J, "Image-based recommendations on styles and substitutes", Sigir Forum, pp.43~52 (2015)