Dressing for Attention: Outfit Based Fashion Popularity Prediction

Ling Lo, Chia-Lin Liu, Rong-An Lin, Bo Wu, Hong-Han Shuai, Wen-Huang Cheng

Abstract

Analysis of fashion trends is crucial. However, existing predictive algorithms of fashion popularity are restricted to be feasible on the coarse style level but not a finer item level. That is, they are only predictive in the future popularity of a given type of fashion styles (e.g., Rocker), but cannot be precisely down to a particular outfit look chosen by individuals. This paper thus proposes the first solution directly aimed at predicting the fine-grained fashion popularity of an outfit look by taking social media as the learning source. Particularly, a deep temporal sequence learning framework is developed and the proposed framework is evaluated on a real dataset of 380,000 street fashion images collected from the fashion website lookbook.nu. The experimental results show that our proposed framework outperforms the state-of-the-art approaches, with a relative increase of 11.51% to 27.62% (MSE metric) and 7.02% to 32.61% (CSE metric) in the prediction accuracy.
BibTeX
@inproceedings{lo2019dressing,
  author = {Ling Lo and Chia-Lin Liu and Rong-An Lin and Bo Wu and Hong-Han Shuai and Wen-Huang Cheng},
  title = {{Dressing for Attention: Outfit Based Fashion Popularity Prediction}},
  booktitle = {ICIP},
  year = {2019},
  doi = {10.1109/icip.2019.8803461},
}

Loading related content...

Figure