Merchandising/Marketing/Retailing: Branding

Where Do Consumers Look When Viewing Fashion Advertisements? Saliency Based Models for Visual Attention Prediction

---

Abstract

To investigate whether saliency modeling can be applied to the fashion area, this multidisciplinary study intended 1) to explore where consumers look at fashion advertisements using saliency-based models, and 2) to investigate which saliency model(s) are the most effective tools in predicting consumers’ visual attention when viewing fashion advertisements. Seventy college students were recruited to participate in the study at a mid-western university in the US. One hundred fashion images were selected from fashion magazines (e.g., Vogue) and divided into four image groups. Each participant was asked to view 25 fashion images and selected locations on each image that most attracted their attention by clicking a mouse on the screen. Ground-truth maps were created based on consumers’ attention. Six saliency models (AW5, COV, DeepFeat, GBVS, ISEEL, LDS) were applied to create saliency maps. The results of Ground-truth maps and saliency maps were compared, and further theoretical and practical implications were presented.

Keywords: salience algorithms, saliency modeling, advertisements, visual attention, Prediction

How to Cite:

Lee, S., Chen, Y., Mahdi, A., Qin, J. & Liang, Y., (2020) “Where Do Consumers Look When Viewing Fashion Advertisements? Saliency Based Models for Visual Attention Prediction”, International Textile and Apparel Association Annual Conference Proceedings 77(1). doi: https://doi.org/10.31274/itaa.12054