Search results

Single-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.

To address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.

Empirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.

This paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

The purpose of this paper is to examine whether retailer brand equity levels vary between department store and specialty clothing store categories.

Retailer brand equity is conceptualized in this paper as a four‐dimensional construct comprising retailer awareness, retailer associations, retailer perceived quality and retailer loyalty. Categorization theory is used to explain the differences in retailer equity across the two different store categories. A doubly multivariate design is incorporated in a structured questionnaire used to collect data via mall‐intercepts in an Australian state capital city.

Results suggest that retailer brand equity varies significantly between department store and specialty store categories. Department store brands yielded significantly higher ratings for all the retailer brand equity dimensions than specialty store brands.

Researchers have argued that retailers possess brand equity. However, extant research does not provide any specific guidance in relation to the question of whether retailer brand equity levels vary from one store category to another. The present research fills an important gap by demonstrating that retailer brand equity levels vary significantly between department store and specialty clothing store categories.

The changes in the Czech Republic brought by the transition process had a significant impact on all sectors of the economy and none more so than on retailing. Presents the initial findings of a long‐term longitudinal study of clothing retailing in the Czech Republic examining the retail format and merchandise assortment structure of clothing retailing in the period of 1994‐1999. The research focused on Czech towns and specifically excluded the capital city of Prague. From the analysis of the retail format development two broad conclusions emerge. First, the smaller towns appear to be more conservative in terms of structural change. Second, there appears to be more extensive changes in retail format patterns occurring in the larger towns. .

Catalogue sales have received increasing attention due to their phenomenal growth in the USA. Professional women, because of their need for convenience and their buying power, are an important market for catalogue marketers. This study was designed to identify clothing categories which professional women tend to purchase through catalogues, compare professional women's involvement with professional clothing versus non‐professional clothing in relation to their catalogue usage and determine the variables that predict professional women's heavy catalogue usage for specific clothing categories. Data analyses were based on a mailed survey of a national sample of professional women catalogue shoppers (N=506). These consumers tended to purchase clothing in distinct categories rather than as one product class, and exhibited greater involvement with non‐professional clothing than with professional clothing. Profiles of frequent catalogue users for three clothing categories (street clothing, footwear and clothing for others) were identified, based on their involvement, lifestyle and demographic variables.

The paper aims to propose a novel method based on deep sparse convolutional neural network (CNN) for clothing recognition. A CNN based on inception module is applied to bridge pixel-level features and high-level category labels. In order to improve the robustness accuracy of the network, six transformation methods are used to preprocess images. To avoid representational bottlenecks, small-sized convolution kernels are adopted in the network. This method first pretrains the network on ImageNet and then fine-tune the model in clothing data set.

The paper opts for an exploratory study by using the control variable comparison method. To verify the rationality of the network structure, lateral contrast experiments with common network structures such as VGG, GoogLeNet and AlexNet, and longitudinal contrast tests with different structures from one another are performed on the created clothing image data sets. The indicators of comparison include accuracy, average recall, average precise and F-1 score.

Compared with common methods, the experimental results show that the proposed network has better performance on clothing recognition. It is also can be found that larger input size can effectively improve accuracy. By analyzing the output structure of the model, the model learns a certain “rules” of human recognition clothing.

Clothing analysis and recognition is a meaningful issue, due to its potential values in many areas, including fashion design, e-commerce and retrieval system. Meanwhile, it is challenging because of the diversity of clothing appearance and background. Thus, this paper raises a network based on deep sparse CNN to realize clothing recognition.

The purpose of this study is to construct consumer value structures for clothing.

Using content analysis, a total of 301 advertisements from the New Yorker and Esquire magazines are analyzed during one representative year out of each of the last four decades.

Consumer values reflected in clothing ads are identified as functional, social, emotional and epistemic. Functional value dominated throughout the 1970s, 1980s, and 1990s, but showed a decreasing trend. By the 2000s, emotional value had overtaken functional value in emphasis. Consumer consequences and product attributes, which fell under each of the consumer values, are also revealed. Of all the consumer consequences, high quality was connected the most frequently with functional value. At the same time, high quality served as an intermediary qualifier for symbols of social status, a consequence of social value. Fabric was the attribute linked most frequently to functional and social consequences.

Clothing companies can use the values, consequences and attributes presented here to differentiate between values, to determine the most effective attributes to emphasize, and to target certain audiences for their marketing and advertising strategies.

The essential contribution of this paper is that this study reveals a hierarchical dimension to clothing value and is the first study which attempts to construct a means‐end chain through the content analysis of advertisements.

The purpose of this paper is to establish the predictors of consumers’ annual monetary expenditures on clothing and footwear in Quito, the capital of Ecuador, a developing Latin American country.

The research followed an exploratory, sequential, mixed methods design. The first phase consisted of in-depth interviews with adult individuals. The second phase involved surveying a similar segment of the population.

The present study supports the importance of demographic and psychological factors as predictors. The study also identifies two new groups of predictors: consumers’ reception of used clothing and physical space at home and its management.

In addition to demographic variables, consumer panels that measure expenditures on clothing and footwear should include psychological measures of participants, particularly clothing involvement. Clothing manufacturers and retailers in developing countries should consider the impact of receiving used clothes by consumers. Because clothing buying and disposal behaviors are positively associated, companies should become more involved in their customers’ disposal behavior.

The contribution of the present study is twofold. First, it contributes to the understanding of clothing and footwear expenditures by considering the individual consumer as a unit of analysis. Furthermore, it provides insights into this behavior from a little-studied context.

The purpose of this paper is to construct a digital collection and database of traditional clothing that is convenient for the digital dissemination and application of traditional clothing and provide resources for research on clothing fashion, traditional clothing techniques, clothing culture, history and clothing teaching.

A real object analysis method was used in this paper, based on 15 core elements of the internationally common DC metadata standard, and with consideration to the characteristics of clothing products and clothing industry application specifications, the core elements of DC are expanded to facilitate the detailed record of the characteristic information of clothing, especially the implicit clothing culture. A code symbol compilation method was developed to give each piece of clothing a unique number, facilitating identification, classification and recording. At last, a metadata construction scheme for traditional clothing was developed. A traditional embroidered children's hat and Mamianqunt serve as examples to demonstrate the metadata elements.

The clothing meta-database provides a main body of traditional clothing while also paying attention to the collection of cultural elements. It is composed of five layers of classified data, source data, characteristic data, connotation data and management data, as well as 28 data elements, providing ease of sharing and interoperation.

This paper expands the subset of fashion metadata by describing traditional clothing metadata, especially the excavation of clothing cultural elements, and developing code compilation methods so that each clothing product can obtain a unique identification number, thereby building a traditional clothing metadata construction scheme consisting of five data layers and containing 28 data elements. This scheme records the information about each layer of traditional clothing in detail and provides shared data for discipline research and industry applications.

The purpose of this paper is to show how materialism, brand engagement in self‐concept (BESC), and status consumption influence clothing involvement and brand loyalty.

The authors use data from a survey of 258 US college students to test a model using structural equation modelling.

The results show that materialism, BESC, and status consumption positively influence clothing involvement and brand loyalty.

The study findings are bounded by the country and sample providing the data. The results strongly support hypotheses derived from the literature and provide important insights into the motives for clothing involvement and brand loyalty.

The findings suggest that appealing to these three important motivators can influence some consumers to choose specific brands of clothing.

This study is the first to demonstrate the influence of materialism, especially operationalized by Kasser's scale, and brand engagement in self‐concept on these clothing behaviors.

This study aims to investigate the apparel fit preferences of Mexican‐American women between the ages of 18 and 25 years old from the Southwestern USA. The study also seeks to analyze the effect of body shape perception, body mass index, and clothing size on apparel fit preferences.

Data were collected in an online survey using an original fit preference assessment scale. Sampling was restricted in terms of gender, age, subculture, and geography to control for the variability that exists in apparel preferences and the Hispanic market due to these factors. Descriptive and inferential statistics were used to describe the sample's fit preferences for casual pants, tops, skirts, and dresses and to determine whether physical body characteristics impact these preferences.

Overall, young Mexican‐American women preferred semi‐fitted apparel across all garment categories studied. Physical body characteristics tended to impact on the sample's preferences for close and loose‐fitting garments, with respondents who had narrower waists and smaller body sizes more likely to prefer close‐fitting garments. Respondents who had less defined waists and larger body sizes were more likely to prefer loose‐fitting garments.

Many apparel firms wish to create targeted products for the Hispanic consumer, given the substantial growth in the size and purchasing power of this market. However, firms have frequently had to rely on cultural stereotypes due to a lack of information. The study documented in the paper developed an original fit preference scale to obtain important information that can be used to impact on apparel product development for this consumer.