Fusing Hierarchical Convolutional Features for Human Body Segmentation and Clothing Fashion Classification
This work addresses the need for automated fashion trend recognition, which is useful for individuals and the fashion industry, but it is incremental as it builds on existing segmentation and classification techniques.
The paper tackled the problem of recognizing clothing fashion trends over time by mapping it to a classification task, using a novel deep neural network that fuses multi-scale convolutional features for accurate human body segmentation and then performs fashion classification on segmented parts, achieving effective results as demonstrated on 9,339 images from 8 years.
The clothing fashion reflects the common aesthetics that people share with each other in dressing. To recognize the fashion time of a clothing is meaningful for both an individual and the industry. In this paper, under the assumption that the clothing fashion changes year by year, the fashion-time recognition problem is mapped into a clothing-fashion classification problem. Specifically, a novel deep neural network is proposed which achieves accurate human body segmentation by fusing multi-scale convolutional features in a fully convolutional network, and then feature learning and fashion classification are performed on the segmented parts avoiding the influence of image background. In the experiments, 9,339 fashion images from 8 continuous years are collected for performance evaluation. The results demonstrate the effectiveness of the proposed body segmentation and fashion classification methods.