Xiaofen Ji

Fashion trend forecasting is crucial for proactive supply chain management, sustainable production, and personalized marketing. However, accurately predicting fine-grained fashion trends across diverse user groups remains challenging, as conventional numerical models rely solely on historical popularity signals and cannot explicitly exploit the high-level semantic context underlying trend evolution. To address this limitation, we propose a Dual-Stream Driven Fashion Trend Forecasting (DDFTF) framework that integrates numerical forecasting with textual semantic reasoning. The numerical stream employs a multi-scale patch Transformer with metadata-aware feature fusion to capture temporal dynamics, while the semantic stream converts historical trends into structured textual descriptions, extracting interpretable semantic representations of global trends and turning points. A residual fusion module combines both streams by treating semantic signals as complementary corrections to numerical predictions. Extensive experiments on the FIT and GeoStyle benchmarks demonstrate that DDFTF consistently outperforms state-of-the-art methods, achieving up to a 14.6% relative MAE reduction in long-term forecasting. Ablation and qualitative analyses further show that the performance gains arise from meaningful semantic information rather than increased model capacity, while also improving the interpretability of fashion trend prediction. Our code is publicly available.

To develop a comprehensive framework for understanding the factors associated with Chinese Generation Z (Gen Z) consumers' intention to purchase second-hand clothing (SHC), this study analyzed a valid sample of 967 Chinese Gen Z respondents obtained through stratified quota sampling. Structural equation modeling (SEM) was conducted using AMOS. Guided by the Theory of Planned Behavior (TPB), the proposed model incorporated additional constructs related to values (biospheric and altruistic values) and social influence (subjective norm, group norm, and social identity). Model comparison using their variance explained ( R ² ) for purchase intention showed that the integrated model exhibited improved in-sample explanatory performance over the baseline TPB, explaining 53.7% of the variance in purchase intention vs. 34.2% for the TPB alone. Altruistic values (β = 0.154, p < 0.01), biospheric values (β = 0.143, p < 0.01), attitude (β = 0.168, p < 0.001), subjective norm (β = 0.187, p < 0.001), and social identity (β = 0.394, p < 0.001) were positively and significantly associated with purchase intention. Exploratory multi-group SEM revealed no significant differences by gender or city tier. Given the non-probability sampling and cross-sectional design, all findings should be interpreted as associational rather than causal. This study offers new insights into previously underexplored factors associated with SHC purchase intention among Chinese Gen Z consumers by integrating value-based and social influence constructs with the TPB.

This study establishes an integrated theoretical framework to comprehensively examine the factors influencing Chinese consumers’ second-hand clothing (SHC) purchase intention. Utilizing a randomly sampled dataset of 654 Chinese consumers, structural equation modeling (SEM) was conducted using AMOS software. The analysis demonstrates that our integrated model exhibits superior predictive power for SHC purchase intention compared to existing frameworks, achieving statistically satisfactory results. The findings provide support for all hypothesized relationships among the theoretical constructs, while the significant mediating effects of the proposed mediators were also confirmed. Notably, invariance tests revealed the moderating effect of past purchase experience.

The rapid growth in the global apparel market and the rise of online consumption underscore the necessity for intelligent clothing recommendation systems that balance visual compatibility with personalized preferences, particularly price sensitivity. Existing recommendation systems often neglect nuanced consumer price behaviors, limiting their ability to deliver truly personalized suggestions. To address this gap, we propose DeepFMP, a multimodal deep learning framework that integrates visual, textual, and price features through an enhanced DeepFM architecture. Leveraging the IQON3000 dataset, our model employs ResNet-50 and BERT for image and text feature extraction, alongside a comprehensive price feature module capturing individual, statistical, and category-specific price patterns. An attention mechanism optimizes multimodal fusion, enabling robust modeling of user preferences. Comparative experiments demonstrate that DeepFMP outperforms state-of-the-art baselines (LR, FM, Wide & Deep, GP-BPR, and DeepFM), achieving AUC improvements of 1.6–12.2% and NDCG@10 gains of up to 3.2%. Case analyses further reveal that DeepFMP effectively improves the recommendation accuracy, offering actionable insights for personalized marketing. This work advances multimodal recommendation systems by emphasizing price sensitivity as a pivotal factor, providing a scalable solution for enhancing user satisfaction and commercial efficacy in fashion e-commerce.

Waste clothing, as a renewable resource, has received increasing attention. Due to high production costs, establishing an efficient supply chain for the recycling of waste clothing is a problem that brand owners need to solve. This study uses mathematical modeling methods to study the closed-loop supply chain models of original equipment manufacturers and cutting making trimming (CMT) in the recycling of waste clothing. By using the Stackelberg game method to analyze the model, the optimal decisions and profits of supply chain members under these two modes were obtained. Based on this, further comparative analysis was conducted between the two modes. Our research finds that brand owners choose to produce and sell recycled clothing not for profit maximization, but based on enhancing brand image or corporate social responsibility considerations. For the brand owner, adopting the CMT model is more advantageous, but this mode requires higher production technology for the recycled fabric supplier.

The fast fashion industry has been widely criticized for its substantial consumption of resources and significant environmental pollution. In contrast, virtual fashion clothes are attracting attention from consumers and academics for their notable sustainability benefits and potential for fashion innovation. However, research on consumer acceptance of virtual clothes and the role of sustainability remains limited. This study aims to fill this gap by applying the Emotional Three-Level Theory to identify key virtual fashion attributes, including aesthetic, reality, personalization, presentation, sustainability, and inclusivity features, and evaluating their impact on acceptance using the Technology Acceptance Model (TAM). A survey of 503 Generation Z consumers in China, analyzed through structural equation modeling, reveals that perceived enjoyment, usefulness, and ease of use significantly influence the intention to adopt virtual fashion clothes. Aesthetic and realistic features enhance enjoyment, while personalization and presentation improve usefulness and ease of use. Sustainability features positively impact all three factors, promoting consumer acceptance. These findings offer theoretical insights for virtual fashion research and practical guidance for the fashion industry to leverage virtual technologies for environmental sustainability. Notably, the study emphasizes the potential of virtual clothes in promoting sustainable development in the fashion industry.

Purpose: Breast cancer has become the largest cancer in the world today. Health problems for women with breast cancer need to be addressed urgently. This study aims to select the best method for preparing temperature-sensitive sports underwear, and to verify the feasibility of using K-type thermocouple threads in underwear fabrics.Design/methodology/approach: In the experiments, two samples were designed for temperature-sensitive performance tests and the effects produced by different outer layer structures were investigated. In the second step, K-type thermocouple wires were integrated into sports underwear. The comfort and feasibility of the temperature-sensitive underwear were investigated.Findings: It was finally verified to obtain the best comfort and temperature-sensing performance of K-type thermocouple filaments integrated into sports underwear with plain stitching.Originality/value: The underwear has a certain prospect for the application of smart apparel based on breast cancer health monitoring, which is of some significance for monitoring smart apparel.

Purpose: Esthetic trend changes with the development of society and cultural differences. A minimizer bra designed to make breasts appear smaller is now popular with large-breasted women in China. To conform to the requirements of modern aesthetics in China, this paper aims to investigate vital features of breast appearance that influence people’s subjective evaluation of breast size and analyze how bra design parameters affect breast shape and make breasts appear smaller.Design/methodology/approach: This study used 3D scanning technology and reverse engineering software to obtain objective breast measurements in detail. A subjective evaluation experiment was conducted to evaluate the overall performance of seven minimizer bras compared to a basic comparison bra. Around 20 design parameters of 8 sample bras were identified to make a further study about the correlation between bra design features and breast shaping effect. To gain a deeper understanding of how bras interact with breast tissue, this study presented heat maps of the breast surface to visualize the deformation of breast shape.Findings: Nine breasts' characteristics, such as the distance between bust points, breast depth, outer breast curvature and slope, etc. have been determined to be highly correlated with the visual reduction effect of breasts. In addition, for the bras in this experiment, the high-performance bra for women with large breasts tends to have a wider side panel, a wider under band, higher gore and a stronger transverse rigidity of the bra cup. According to the observation of heat maps of the breast surface, soft full-figure bras provide a wider range of compression to the breasts and effectively flatten the breasts.Originality/value: This paper first aimed at the need to shape the ideal breast appearance for large-breasted women and make a further study of several hot-selling minimizer bras in China. The suggestions given in this paper help lingerie manufacturers better understand how design features of bras can affect their shaping effect and improve the wearing effect of minimizer bras for large-breasted women.