Figure 1. Multi-domain image-to-image translation results on the CelebA dataset via transferring knowledge learned from the RaFD dataset. The first and sixth columns show input images while the remaining columns are images generated by StarGAN. Note that the images are generated by a single generator network, and facial expression labels such as angry, happy, and fearful are from RaFD, not CelebA. AbstractRecent studies have shown remarkable success in imageto-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.
Changing consumption behavior can offer co-benefits in reduction of environmental issues and encouraging improvements to environmentally friendly or sustainable production. We propose a novel value-social norm-enjoyment-based motivation (VSE) model and test the factors that influence individual pro-environmental apparel purchasing behavior. Data were obtained from 353 college students in Korea and analyzed by using SEM. Our results show that individuals who endorse bio-altruistic values who engage in eco-friendly environmental behavior in apparel domain are influenced by descriptive norms and injunctive norms. Further, enjoyment-based motivation was found to be a key mediator among bio-altruistic value, descriptive norms, and injunctive norms on pro-environmental purchasing behavior. However, injunctive norms do not directly influence purchasing behavior, but rather, are integrated to enjoyment-based intrinsic motivation, then indirectly affect purchasing behavior.
This paper investigates the diversity of costumes of Buddhist ritual dance in Mongolian and Korean Buddhism. Both the Mongolian Tsam dance and the Korean Nabi dance have developed to reflect the regional characteristics of costumes and symbolic systems and are closely related as far as the ideas of rebirth and afterlife are concerned. Both the Mongolian and the Korean dance, performed by monks, display common features that symbolise the spiritual role of the monks in guiding people on their way from birth to death. The symbolism of the ritual dance costume is related to the traditional culture, in both Mongolia and Korea, but Mongolian Tsam uses more shamanistic and decorative elements based on the ceremony of shamanism, while Korean Nabi dance shows an exceptional beauty in its self-restraint.
: This study focused on investigating factors of partnership formation for transactional enterprises on supply chain to form a transactional relationship centering around textile industry in Daegu and Gyeongbuk. The study also investigated the effect of the factors of partnership formation for mutual cooperation among textile manufacturers in Daegu and Gyeongbuk on partnership outcomes, and finally provided basic information that help enterprises form efficient partnership relationships with related manufacturers. The sample of the study was manufacturers of yarn, dyeing, weaving, process and fabrics in Daegu and Gyeongbuk that are registered on Korea Federation of Textile Industries. The total of 81 responses were used for data analyses, and factor analyses, regression analyses, and ANOVA were utilized appling SPSS 14.0 Package. The results of the research were as follows: First, among partnership formation factors mutual confidence was highly related to presentation of exclusive technological information, efforts to keep relationships between enterprises, presentation of information, and transactions between reliable enterprises that were formed despite of any losses. Second, it was also important that enterprises exchange and communicate their business goals with partners by having common goals. Third, it was also important that problems and damages were informed to and were shared with transaction companies. If conflicts between enterprises occurred, they can be smoothly solved based on the partnership formation. Fourth, enterprises form partnerships with transaction companies by considering their operation abilities. Fifth, transactions with enterprises which are mutually reliable and have superior technology and information contributed a lot to economic outcome. Lastly, the study revealed that among partnership formation factors mutual confidence to transaction companies influenced outcome of mutual confidence profit creation, outcome of technology & information efficiency were closely related to the ability to solve generated problem, and an important factor of the outcome of technology & information profit creation was communication.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.