Fashion analysis and understanding with artificial intelligence

Gu, Xiaoling; Gao, Fei; Tan, Min; Peng, Pai

doi:10.1016/j.ipm.2020.102276

Cited by 53 publications

(24 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[12][13][14] In order to improve the accuracy in recognizing garments, some of the research mentioned above contained preprocessed images to account for human posture and body parts (Figure 1(a)). Gu et al (2020) identified clothing attribute prediction as a major component of the fashion attribute prediction phase that can be denoted by three different types of learning 16 : (1) single-task learning; (2) multitask learning; and (3) transfer learning. The simplest, single-task learning, involves identifying clothing attributes from specific fashion domains.…”

Section: Detecting Clothing Categories and Attributes From Fashion Imagesmentioning

confidence: 99%

The exploration of artificial intelligence application in fashion trend forecasting

Shi

Chussid

Yang

et al. 2021

Textile Research Journal

View full text Add to dashboard Cite

Fashion trends today are changing much faster than ever before. Timely and reliable trend forecasting is, therefore, critical in the fashion industry. Traditional fashion forecasting requires professionals to abstract image-based information across design collections and time intervals from around the world, which is extremely time-consuming and labor intensive. Considering the financial cost associated with manual labeling and the accuracy of classifications based upon human subjective judgment, this explorative study proposes a data-driven quantitative abstracting approach using an artificial intelligence (A.I.) algorithm. Firstly, an A.I. model was trained to be familiar with fashion images from a large-scale dataset under different scenarios such as online stores and street snapshots; secondly, the model could detect garments and classify clothing attributes such as fabric textures, garment style, and design details from runway photos and videos; thirdly, the model could summarize fashion trends from the attributes it developed. The adoption of an A.I. algorithm proved to be an objective and systematic computerized method of interpreting fashion dynamics in a more efficient, accurate, sustainable, and cost-effective way.

show abstract

Section: Detecting Clothing Categories and Attributes From Fashion Imagesmentioning

confidence: 99%

The exploration of artificial intelligence application in fashion trend forecasting

Shi

Chussid

Yang

et al. 2021

Textile Research Journal

View full text Add to dashboard Cite

show abstract

“…For some people, fashion has its own meaning. It reflects people's social life, economic status, and even cultural background [1]. As time goes by, electronic and media social is rapidly evolving as same as fashion itself, which cannot be denied that it has become part of human life [2].…”

Section: Introductionmentioning

confidence: 99%

“…Through this, business owners need to create efficient and easy to use features for their target market to enhance a good customer experience [4]. Fashion business owners need to compete to give the best presentation of the products by providing a catchy e-commerce sites, also present rich and attractive content to gains customer's interest [1].…”

Section: Introductionmentioning

confidence: 99%

Cotton.Go’s Electronic Service Quality Improvement Using Importance Performance Competitor Analysis Approach

Aldiera

Wulandari

Kusmayanti

2024

IJIES

View full text Add to dashboard Cite

The number of competitors that have sprung up in the field of fashion especially in men's clothing, has caused Cotton.Go need to evaluate its e-commerce services to compete with them. Therefore, this research was conducted to evaluate the attributes of Cotton.Go’s e-commerce services by integrating the dimensions of Electronic Service Quality and Importance Performance Competitor Analysis (IPCA) method. According to research result, seven attributes of services in Cotton.Go’s e-commerce is needed for further research, which are web design, reliability, efficiency, responsiveness, security, flexibility, and fulfillment. This research produced that all of the attributes need urgent action to improve by looking at the negative performance differences value with its competitor. All attributes that need to be improved indicated that the performances are considered to be lower compared to the competitor and need immediate action to improve.

show abstract

“…The rapid evolution of development plans like Industry 4.0 and Made in China 2025, as well as emerging information technologies, such as Cloud Computing, Big Data, and the Internet of Things, plays an important role in the development of garment production (Damodaram and Ravindranath, 2010 ; Ngai et al, 2014 ; Dong et al, 2020 ; Gu et al, 2020 ). Many garment firms in the apparel industry have, in fact, introduced high-end technology to design innovative, stylish, and customized products to attract more potential customers.…”

Section: Introductionmentioning

confidence: 99%

“…Obviously, one of the necessary conditions for this process to take place is that the product manufacturer and the consumers dispose of some channels to communicate their preferences and, sometimes, their limits. Nowadays, this is not just more than possible, it is actually routine thanks to the increasing popularity of smartphones (Editing Team, 2019 ), wearable devices and other intelligent terminal devices, which give the customized garment manufacturer easy access to customers' information, preferences, and data, and allow the producer to get in contact with the customer even during the manufacturing and distribution processes [here, it is important to mention the newly available technologies like the 3D printing machine (Zhou et al, 2016 ), artificial intelligence (Gu et al, 2020 ), and big data (Dong et al, 2020 )].…”

Section: Introductionmentioning

confidence: 99%

Customer Behavior on Purchasing Channels of Sustainable Customized Garment With Perceived Value and Product Involvement

Yuan

et al. 2020

Front. Psychol.

View full text Add to dashboard Cite

Online shopping for customized garments has become the fastest-growing field of the Chinese eBusiness market. Most consumers not only limit themselves to buying standardized garments but also want to buy garments customized to their preferences. This phenomenon has pushed the fashion textile and apparel industry to change its supply chain operations to meet the customization demand. Besides, the fashion textile and apparel industry also want to study how different channel factors will affect consumers' perceived value and further influence consumers' purchasing decisions. We initiated this study and empirically tested more than 200 experienced consumers. This study collaborated with a fashion textile and apparel company that aims to implement customized product lines soon. Based on the perceived value theory and risk management theory, we investigated whether product involvement and channel identification on supply chain design will affects potential customized product consumers' purchasing decisions. The findings reveal that channel recognition affects consumer decisions by having a positive impact on their perceived value. The perceived risk and shopping channel involvement of consumers have a negative impact on their perceived values and channel selections. In addition, product involvement has a moderating effect on the relationship between channel's perceived risk, perceived values, and channel selections as well.

show abstract

Fashion analysis and understanding with artificial intelligence

Cited by 53 publications

References 11 publications

The exploration of artificial intelligence application in fashion trend forecasting

The exploration of artificial intelligence application in fashion trend forecasting

Cotton.Go’s Electronic Service Quality Improvement Using Importance Performance Competitor Analysis Approach

Customer Behavior on Purchasing Channels of Sustainable Customized Garment With Perceived Value and Product Involvement

Contact Info

Product

Resources

About