Search

• A novel fashion product recommendation method using multimodal information. • Integrating both text and image mining techniques. • Facilitating similar and mix-and-match fashion product recommendations. • Leveraging text-based product attributes and image features in the recommendations. Fashion recommendation has attracted much attention given its ready applications to e-commerce. Traditional methods usually recommend clothing products to users on the basis of their textual descriptions. Product images, although covering a large resource of information, are often ignored in the recommendation processes. In this study, we propose a novel fashion product recommendation method based on both text and image mining techniques. Our model facilitates two kinds of fashion recommendation, namely, similar product and mix-and-match, by leveraging text-based product attributes and image features. To suggest similar products, we construct a new similarity measure to compare the image colour and texture descriptors. For mix-and-match recommendation, we firstly adopt convolutional neural network (CNN) to classify fine-grained clothing categories and fine-grained clothing attributes from product images. Algorithm is developed to make mix-and-match recommendations by integrating the image extracted categories and attributes information are with text-based product attributes. Our comprehensive experimental work on a real-life online dataset has demonstrated the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

‘ The word “fashion” is synonymous with the word “change”. Fashion begins with fabrics and fabrics begin with colour’ . This famous remark/definition of ‘fashion’ must now be revised in the era of digital technology. In this paper, we propose a novel print design concept, from 3D garments to 2D textiles. By taking advantage of the cutting-edge developments in surface parameterisation, cloth simulation and texture assignment, we develop a computer system that allows designers to create figure-flattering prints directly onto 3D garments, and will output 2D pattern pieces with matched texture that are ready for digital printing and garment production. It reverses the traditional design process from 2D fabrics to 3D garments. The results produced by the proposed method guarantee textural continuity in both garment and pattern pieces. It not only releases apparel makers from the tedious work of matching texture along seams, but also provides users with a new tool to create one-of-a-kind fashion products by designing personalised prints. [ABSTRACT FROM AUTHOR]

Multi-scale feature fusion is a commonly-used module in existing deep-learning models, and feature misalignment occurs in the process of feature fusion. The spatial misalignment hinders the learning of semantic representation with multi-scale levels, but which has not received much attention. This misalignment problem is caused by the feature position shift after using the convolution and interpolation operation in feature fusion. To solve the misalignment problem, this paper formulates the shift error mathematically and proposes a plug-and-play unbiased feature position alignment strategy to align convolution with interpolation. As a model-agnostic approach, unbiased feature position alignment can boost the performance of different models without introducing extra parameters. Furthermore, the unbiased feature position alignment is applied to build an unbiased human pose estimation method. Experimental results have demonstrated the effectiveness of the proposed unbiased pose model in comparison to the state-of-the-arts, especially in the low-resolution field. The codes are shared at https://github.com/WangChen100/Unbiased-Feature-Position-Alignment-for-Human-Pose-Estimation. [ABSTRACT FROM AUTHOR]