The Experts below are selected from a list of 13791 Experts worldwide ranked by ideXlab platform
Xiaogang Wang - One of the best experts on this subject based on the ideXlab platform.
-
the garment Fashionable shape prognosticating based on manufacture database
Applied Mechanics and Materials, 2011Co-Authors: Xiaogang WangAbstract:Based on the research about outside shape of woman warm jacket more than twenty years, Fashion variables that were representative and can describe the Fashionable shape were discussed. Experiment was designed to achieve data of large numbers of female body. Body size variables were statistically analyzed to decide the module that was the basement for achieving data from historical photos. Fashionable characteristic diagrams of garment length, front chest width, shoulder length, collar height and their error bar charts were drawn for discussing the change of Fashionable shape. The Fashion Trends in the future were also prognosticated scientifically. At the same time, a historical database was developed for manufacture and designing, which it is the basement for automatic pattern designing. This new method for Fashion Trend research was introduced by data mining technology, which it opens our minds for garment science research and offers a new database for improving garment CAD system.
-
exploring the garment Fashionable shape oriented manufacture database
International Conference on Industrial Mechatronics and Automation, 2010Co-Authors: V E Kuzmichev, Yun Luo, Xiaogang WangAbstract:Based on the research about outside shape of woman warm jacket more than twenty years, Fashion variables that were representative and can describe the Fashionable shape were discussed. Experiment was designed to achieve data of large numbers of female body. Body size variables were statistically analyzed to decide the module that was the basement for achieving data from historical photos. Fashionable characteristic diagrams of garment length, front chest width, shoulder length, collar height and their error bar charts were drawn for discussing the change of Fashionable shape. The Fashion Trends in the future were also prognosticated scientifically. At the same time, a historical database was developed for manufacture and designing, which it is the basement for automatic pattern designing. This new method for Fashion Trend research was introduced by data mining technology, which it opens our minds for garment science research and offers a new database for improving garment CAD system..
Tatseng Chua - One of the best experts on this subject based on the ideXlab platform.
-
leveraging multiple relations for Fashion Trend forecasting based on social media
IEEE Transactions on Multimedia, 2021Co-Authors: Yujuan Ding, Lizi Liao, Wai Keung Wong, Tatseng ChuaAbstract:Fashion Trend forecasting is of great research significance in providing useful suggestions for both Fashion companies and Fashion lovers. Although various studies have been devoted to tackling this challenging task, they only studied limited Fashion elements with highly seasonal or simple patterns, which could hardly reveal the real complex Fashion Trends. Moreover, the mainstream solutions for this task are still statistical-based and solely focus on time-series data modeling, which limit the forecast accuracy. Towards insightful Fashion Trend forecasting, previous work [1] proposed to analyze more fine-grained Fashion elements which can informatively reveal Fashion Trends. Specifically, it focused on detailed Fashion element Trend forecasting for specific user groups based on social media data. In addition, it proposed a neural network-based method, namely KERN, to address the problem of Fashion Trend modeling and forecasting. In this work, to extend the previous work, we propose an improved model named Relation Enhanced Attention Recurrent (REAR) network. Compared to KERN, the REAR model leverages not only the relations among Fashion elements but also those among user groups, thus capturing more types of correlations among various Fashion Trends. To further improve the performance of long-range Trend forecasting, the REAR method devises a sliding temporal attention mechanism, which is able to capture temporal patterns on future horizons better. Extensive experiments and more analysis have been conducted on the FIT and GeoStyle datasets to evaluate the performance of REAR. Experimental and analytical results demonstrate the effectiveness of the proposed REAR model in Fashion Trend forecasting, which also show the improvement of REAR compared to the KERN.
Yujuan Ding - One of the best experts on this subject based on the ideXlab platform.
-
leveraging multiple relations for Fashion Trend forecasting based on social media
IEEE Transactions on Multimedia, 2021Co-Authors: Yujuan Ding, Lizi Liao, Wai Keung Wong, Tatseng ChuaAbstract:Fashion Trend forecasting is of great research significance in providing useful suggestions for both Fashion companies and Fashion lovers. Although various studies have been devoted to tackling this challenging task, they only studied limited Fashion elements with highly seasonal or simple patterns, which could hardly reveal the real complex Fashion Trends. Moreover, the mainstream solutions for this task are still statistical-based and solely focus on time-series data modeling, which limit the forecast accuracy. Towards insightful Fashion Trend forecasting, previous work [1] proposed to analyze more fine-grained Fashion elements which can informatively reveal Fashion Trends. Specifically, it focused on detailed Fashion element Trend forecasting for specific user groups based on social media data. In addition, it proposed a neural network-based method, namely KERN, to address the problem of Fashion Trend modeling and forecasting. In this work, to extend the previous work, we propose an improved model named Relation Enhanced Attention Recurrent (REAR) network. Compared to KERN, the REAR model leverages not only the relations among Fashion elements but also those among user groups, thus capturing more types of correlations among various Fashion Trends. To further improve the performance of long-range Trend forecasting, the REAR method devises a sliding temporal attention mechanism, which is able to capture temporal patterns on future horizons better. Extensive experiments and more analysis have been conducted on the FIT and GeoStyle datasets to evaluate the performance of REAR. Experimental and analytical results demonstrate the effectiveness of the proposed REAR model in Fashion Trend forecasting, which also show the improvement of REAR compared to the KERN.
V E Kuzmichev - One of the best experts on this subject based on the ideXlab platform.
-
exploring the garment Fashionable shape oriented manufacture database
International Conference on Industrial Mechatronics and Automation, 2010Co-Authors: V E Kuzmichev, Yun Luo, Xiaogang WangAbstract:Based on the research about outside shape of woman warm jacket more than twenty years, Fashion variables that were representative and can describe the Fashionable shape were discussed. Experiment was designed to achieve data of large numbers of female body. Body size variables were statistically analyzed to decide the module that was the basement for achieving data from historical photos. Fashionable characteristic diagrams of garment length, front chest width, shoulder length, collar height and their error bar charts were drawn for discussing the change of Fashionable shape. The Fashion Trends in the future were also prognosticated scientifically. At the same time, a historical database was developed for manufacture and designing, which it is the basement for automatic pattern designing. This new method for Fashion Trend research was introduced by data mining technology, which it opens our minds for garment science research and offers a new database for improving garment CAD system..
Wai Keung Wong - One of the best experts on this subject based on the ideXlab platform.
-
leveraging multiple relations for Fashion Trend forecasting based on social media
IEEE Transactions on Multimedia, 2021Co-Authors: Yujuan Ding, Lizi Liao, Wai Keung Wong, Tatseng ChuaAbstract:Fashion Trend forecasting is of great research significance in providing useful suggestions for both Fashion companies and Fashion lovers. Although various studies have been devoted to tackling this challenging task, they only studied limited Fashion elements with highly seasonal or simple patterns, which could hardly reveal the real complex Fashion Trends. Moreover, the mainstream solutions for this task are still statistical-based and solely focus on time-series data modeling, which limit the forecast accuracy. Towards insightful Fashion Trend forecasting, previous work [1] proposed to analyze more fine-grained Fashion elements which can informatively reveal Fashion Trends. Specifically, it focused on detailed Fashion element Trend forecasting for specific user groups based on social media data. In addition, it proposed a neural network-based method, namely KERN, to address the problem of Fashion Trend modeling and forecasting. In this work, to extend the previous work, we propose an improved model named Relation Enhanced Attention Recurrent (REAR) network. Compared to KERN, the REAR model leverages not only the relations among Fashion elements but also those among user groups, thus capturing more types of correlations among various Fashion Trends. To further improve the performance of long-range Trend forecasting, the REAR method devises a sliding temporal attention mechanism, which is able to capture temporal patterns on future horizons better. Extensive experiments and more analysis have been conducted on the FIT and GeoStyle datasets to evaluate the performance of REAR. Experimental and analytical results demonstrate the effectiveness of the proposed REAR model in Fashion Trend forecasting, which also show the improvement of REAR compared to the KERN.