Learning to Appreciate the Aesthetic Effects of Clothing

Abstract

How do people describe clothing? The words like “formal”or "casual" are usually used. However, recent works often focus on recognizing or extracting visual features (e.g., sleeve length, color distribution and clothing pattern) from clothing images accurately. How can we bridge the gap between the visual features and the aesthetic words? In this paper, we formulate this task to a novel three-level framework: visual features(VF) - image-scale space (ISS) - aesthetic words space(AWS). Leveraging the art-field image-scale space served as an intermediate layer, we first propose a Stacked Denoising Autoencoder Guided by CorrelativeLabels (SDAE-GCL) to map the visual features to the image-scale space; and then according to the semantic distances computed byWordNet::Similarity, we map the most often used aesthetic words in online clothing shops to the image-scale space too. Employing upper body menswear images downloaded from several global online clothing shops as experimental data, the results indicate that the proposed three-level framework can help to capture the subtle relationship between visual features and aesthetic words better compared to several baselines. To demonstrate that our three-level framework and its implementation methods are universally applicable, we finally present some interesting analyses on the fashion trend of menswear in the last 10 years.

Image Multi-Feature Fusion for Clothing Style Classification

“…Five distinct characteristics, including color, texture, shape, resolution, and style descriptors, were used to identify three distinct visual trends, namely floral prints, pastels, and neon colors, from the runway to street fashion. Jia J. et al [1] construct a three-level framework consisting of visual features, image scale space, and aesthetic vocabulary space to create a bridge between visual features and aesthetic language. S. Gao [2] proposed a clothing subjective style recognition method based on distance metric learning and multi-view learning methods, which effectively solving the multi-label classification problem.…”

“…In order to bridge the gap between visual features and aesthetic language, Jia J. et al [1] introduced an intermediate layer to form a novel three-level framework. S. Gao [2] proposed a clothing subjective style recognition method based on distance metric learning and multi-view learning methods to effectively solve the multi-label classification problem of clothing subjective style.…”

Towards Better Understanding the Clothing Fashion Styles: A Multimodal Deep Learning Approach

“…suit, coat, leggings, etc. ), even clothing images with similar visual features can present different fashion effects, showing that fashion styles are influenced by clothing categories (Jia et al 2016). So we take clothing categories as correlative labels, and promote the BDA to a novel structure named Bimodal Correlative Deep Autoencoder (BCDA), shown in Figure 3.…”

“…(Liu et al 2012) considers occasions in dressing and focus on scenario-oriented clothing recommendation. Although a latest work (Jia et al 2016) proposes to appreciate the aesthetic effects of upper-body menswear, it still lacks universality and ignores that the collocation of top and bottom has a significant impact on fashion styles. Thus, there still remain two challenges for us: 1) how to quantitatively describe the fashion styles of various clothing, 2) how to model the subtle relationship between visual features and fashion styles, especially considering the clothing collocations.…”

“…Fashion style modeling. A latest work (Jia et al 2016) proposes to appreciate the aesthetic effects of upper-body menswear. However, clothing variety and fashion collocation are significant elements of clothing fashion that we cannot ignore.…”