Machine learning for digital try-on: Challenges and progress

Liang, Junbang

doi:10.1007/s41095-020-0189-1

Cited by 9 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The total statistics are calculated based on the mean, median, and minimum standard values of the number of standard deviations. Figures 15a, 15b, and 15c show the number of daily visitors to the particular website and the conversion rate of the products, which is done [28,29]. Figure 16 shows the amount of seed forecast, which is based on the overall summation of total sales that have been achieved by the particular customer in the product type.…”

Section: Website Usage Analytics Sentiment Positive Feedbackmentioning

confidence: 99%

“…Figure 14 shows the total number of daily visits by the user. This is captured in the data 15 show the number of daily visitors to the particular website and the conversion rate of the products, which are done [28,29]. Figure 16 shows the amount of seed forecast, which is based on the totally real, effective board, and the total sales that have been achieved by the particular customer in the product type.…”

Section: Website Usage Analytics Sentiment Positive Feedbackmentioning

confidence: 99%

See 1 more Smart Citation

Retracted: Performance optimization of unstructured E‐commerce log data for activity and pattern evaluation using web analytics

Shukla¹,

Mishra

Sinha

et al. 2022

IET Communications

View full text Add to dashboard Cite

The above article from IET Communications, published online on 4 November 2022 in Wiley Online Library (wileyonlinelibrary.com), has been retracted by agreement between the Interim Editor‐in‐Chief, Jian Ren, the Institution of Engineering and Technology (the IET) and John Wiley and Sons Ltd. This article was published as part of a Guest Edited special issue. Following an investigation, the IET and the journal have determined that the article was not reviewed in line with the journal's peer review standards and there is evidence that the peer review process of the special issue underwent systematic manipulation. Accordingly, we cannot vouch for the integrity or reliability of the content. As such we have taken the decision to retract the article. The authors have been informed of the decision to retract.

show abstract

Section: Website Usage Analytics Sentiment Positive Feedbackmentioning

confidence: 99%

Section: Website Usage Analytics Sentiment Positive Feedbackmentioning

confidence: 99%

Retracted: Performance optimization of unstructured E‐commerce log data for activity and pattern evaluation using web analytics

Shukla¹,

Mishra

Sinha

et al. 2022

IET Communications

View full text Add to dashboard Cite

show abstract

“…Virtual try-on provides customers with optimal fit, and it is crucial to understand the fit of garments before the purchase to avoid returns (Hwangbo et al, 2020). Other studies confirmed that the application of this technology as an in-store try-on has the potential to minimize the distance between online and offline shopping (Cordier et al, 2001;Shin and Baytar, 2014;Adikari et al, 2020;Gauri et al, 2021;Liang & Lin, 2021).…”

Section: Virtual Try-onmentioning

confidence: 98%

“…Competition in the fashion industry promotes non-stop apparel overproduction and overconsumption. Moreover, the boom of online sales has increased the volume of online returns, where the wrong sizing and fitting are demonstrated being the main reasons for online customers to return purchased apparel (Yang and Xiong, 2019;Adikari et al, 2020;Gauri et al, 2021;Liang & Lin, 2021). This problem is being addressed through the development of virtual and augmented reality (VR & AR) apps and digital innovations, such as robot mannequins, systems-based algorithms, 3D technology.…”

Section: Thesis Statementmentioning

confidence: 99%

Digital Innovation for Sustainable Fashion: Virtual Fitting Rooms as a Strategy to Minimize Waste and E-commerce Returns

Vitola

2024

Preprint

View full text Add to dashboard Cite

<p>This study aims to determine the efficacy of digital innovations and Virtual Fitting Rooms (VFRs) in minimizing online returns and waste in the fashion industry. This study used both primary and secondary data, including 1) a narrative literature review approach based on data from multiple secondary sources, including scientific journals, e-commerce reports, tech company websites, and other relevant and verified sources, 2) an online survey with sixteen respondents and eight semi-structured interviews with tech companies and virtual fitting rooms developers were conducted to establish baseline data of their perception on the role of developers and VFR tech companies concerning sustainable fashion and reverse logistics. This study assessed information of current VFR apps, including issues with technology development, relationships with e-commerce retailers, effect of VFR in reducing online returns and increasing customer satisfaction. Collected data determined the effects of existing VFRs and digital solutions adopted by the fashion industry to help customers in the sizing and fitting process to reduce online returns and e-commerce waste.</p> <p>The results highlight that VFRs are effective in minimizing returns, increasing customer satisfaction, and promoting sustainability by reducing CO2 emissions due to transportation. This study shows that VFRs could reduce 31.3% of reverse logistic costs and minimize store sizing sampling. There is room for future research on the usage of VFR in 3D cloth simulation engines in pre-production and designers’ collections, which could potentially have a more significant environmental impact on the minimization of fashion waste and overproduction.</p>

show abstract

“…However, in backlight or insufficient light conditions, smartphones cannot capture clear images. Low-light images will show varying degrees of degradation, such as low brightness and contrast, unexpected noise, which seriously affect the visual effect [1]. In order to improve the quality of low-light images, we can enhance it from the perspective of supplementing light, increasing sensitivity and extending exposure.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical guided network for low‐light image enhancement

Feng

Fan

2021

IET Image Processing

View full text Add to dashboard Cite

Due to insufficient illumination in low‐light conditions, the brightness and contrast of the captured images are low, which affect the processing of other computer vision tasks. Low‐light enhancement is a challenging task that requires simultaneous processing of colour, brightness, contrast, artefacts and noise. To solve this problem, the authors apply the deep residual network to the low‐light enhancement task, and propose a hierarchical guided low‐light enhancement network. The key of this method is recombined hierarchical guided features through the feature aggregation module to realize low‐light enhancement. The network is based on the U‐Net network, and then hierarchically guided with the input pyramid branch in the encoding and decoding network. The input pyramid structure realizes multi‐level receptive fields and generates a hierarchical representation. The encoding and decoding structure concatenates the hierarchical features of the input pyramid and generates a set of hierarchical features. Finally, the feature aggregation module is used to fuse different features to achieve low‐light enhancement tasks. The effectiveness of the components is proved through ablation experiments. In addition, the authors are also evaluating on different data sets, and the experimental results show that the method proposed is superior to other methods in subjective and objective evaluation.

show abstract

Machine learning for digital try-on: Challenges and progress

Cited by 9 publications

References 23 publications

Retracted: Performance optimization of unstructured E‐commerce log data for activity and pattern evaluation using web analytics

Retracted: Performance optimization of unstructured E‐commerce log data for activity and pattern evaluation using web analytics

Digital Innovation for Sustainable Fashion: Virtual Fitting Rooms as a Strategy to Minimize Waste and E-commerce Returns

Hierarchical guided network for low‐light image enhancement

Contact Info

Product

Resources

About