Neo-Fashion: A Data-Driven Fashion Trend Forecasting System Using Catwalk Analysis

被引：16

作者：

Zhao, Li ^{[1
]}

Li, Muzhen ^{[1
]}

Sun, Peng ^{[2
]}

机构：

[1] Univ Missouri, Text & Apparel Management, 137 Stanley Hall, Columbia, MO 65211 USA

[2] Climate Corp, San Francisco, CA USA

来源：

CLOTHING AND TEXTILES RESEARCH JOURNAL | 2024年 / 42卷 / 01期

关键词：

trend forecasting; catwalk analysis; machine learning; artificial intelligence; computer vision;

D O I：

10.1177/0887302X211004299

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

Trend forecasting is a challenging and important aspect of the fashion industry. The authors design a novel fashion trend analysis system called "Neo-Fashion," which provides recommendations to fashion researchers and practitioners about potential fashion trends using computer vision and machine learning. Neo-Fashion includes three modules, a data collection and labeling module, an instance segmentation module and a trend analysis module. Diffusion of innovation theory is used as the main theoretical framework to understand fashion trends. 32,702 catwalk images from 2019 fashion week were collected, and 769 images were labeled as training data. Neo-fashion is able to identify and segment fashion items in the given images, and indicate the fashion trends in colors, styles, clothing combinations, and other fashion attributes. To optimize the system, more data sources can be included to not only reflect trends in even more categories but also aid in understanding the trickle-up or trickle-across process in fashion.

引用

页码：19 / 34

页数：16

共 33 条

[1] Fashion Forward: Forecasting Visual Style in Fashion [J].

Al-Halah, Ziad ;

Stiefelhagen, Rainer ;

Grauman, Kristen .

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :388-397

[2] Fashion Design for a Projected Future [J].

Ames, Annette .

CLOTHING AND TEXTILES RESEARCH JOURNAL, 2008, 26 (02) :103-118

[3]

Arous, 2017, ARXIV PREPRINT ARXIV

[4] A THEORY OF FADS, FASHION, CUSTOM, AND CULTURAL-CHANGE AS INFORMATIONAL CASCADES [J].

BIKHCHANDANI, S ;

HIRSHLEIFER, D ;

WELCH, I .

JOURNAL OF POLITICAL ECONOMY, 1992, 100 (05) :992-1026

[5] Automatic Fish Classification System Using Deep Learning [J].

Chen, Guang ;

Sun, Peng ;

Shang, Yi .

2017 IEEE 29TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2017), 2017, :24-29

[6] Color Trend Forecasting of Fashionable Products with Very Few Historical Data [J].

Choi, Tsan-Ming ;

Hui, Chi-Leung ;

Ng, Sau-Fun ;

Yu, Yong .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2012, 42 (06) :1003-1010

[7] Machine Learning (ML) for Tracking Fashion Trends: Documenting the Frequency of the Baseball Cap on Social Media and the Runway [J].

Getman, Rachel Rose ;

Green, Denise Nicole ;

Bala, Kavita ;

Mall, Utkarsh ;

Rawat, Nehal ;

Appasamy, Sonia ;

Hariharan, Bharath .

CLOTHING AND TEXTILES RESEARCH JOURNAL, 2021, 39 (04) :281-296

[8]

He K., 2015, CORR, Vabs/1502.01852, DOI [DOI 10.1109/CVPR.2016.90, 10.1109/CVPR.2016.90]

[9]

He KM, 2020, IEEE T PATTERN ANAL, V42, P386, DOI [10.1109/TPAMI.2018.2844175, 10.1109/ICCV.2017.322]

[10]

Jackson T., 2007, Fashion Marketing - Contemporary Issues, V2A, P168

← 1 2 3 4 →