Taipei National University of the Arts

Industry 5.0 transforms industrial ecosystems via artificial intelligence (AI), human–machine collaboration, and sustainability-focused innovations. This systematic literature review examines Industry 5.0′s role in energy transition through digital transformation, sustainable supply chains, and energy efficiency strategies. Key findings highlight AI-driven smart grids, blockchain-enabled energy transactions, and digital twin simulations as enablers of low-carbon, adaptive industrial operations. This review uniquely integrates technological, managerial, and policy perspectives, providing actionable insights for policymakers and industry leaders. Industry 5.0 enhances innovative energy management, renewable energy integration, and flexible energy distribution, strengthening resilience and sustainability. It fosters environmental responsibility, social impact, and circular economy principles, laying the foundation for a low-carbon economy and accelerating the global energy transition.

This study takes the Zhongyuan settlement of the Seediq in central Taiwan as a case in point to explore from a small spatial span the relationship between Seediq traditional weaving, which is closely related to the natural environment, and SEPL in the development of cultural business mechanisms. The settlement is proud to have a large number of people with traditional weaving skills and strives to promote traditional weaving and innovation. Under the pressure of cultural and commercial mechanisms, it still hopes to slowly progress towards the dream of becoming a weaving craft village. The preliminary conclusions of this study are (1) from the orientation of the relationship between weaving skills and the environment, the case embodies the wisdom of human beings to respond to the natural environment; (2) from the orientation of the environment and landscape, homestead ramie fields have been restored but their function has changed from meeting daily needs to teaching or cultural experiences; (3) traditional weaving is limited by slow manual speed, high labour costs, and the mission of cultural preservation, so profits are limited. Adjustments to methods geared to developing financial resources for diversified development include winning funding support from government departments based on cultural preservation and satoyama contributions, and enriching ecological and environmental knowledge for cultural tours as a cultural business mechanism; (4) cooperation between the settlement and the university can play a small role in the content of the proposals on the satoyama spirit; (5) revitalization of weaving and tribal guiding are two cultural business mechanisms that form the protective umbrella of the Zhongyuan settlement SEPL.

The ultimate goal of art communication is to foster public acceptance of art culture.Art galleries play a crucial role in this communication process by catering to and promoting the diverse needs of audiences.With the advancement of digital technology, museums have more possibilities for exhibit display and collection management.The traditional functions of museums have evolved, raising questions about how digital displays can be planned and presented to enhance learning among visitors.What factors should be considered in the interaction design of digital devices within exhibition venues?This shift in presentation style has transformed museums from merely displaying collections to potentially being standalone pieces of art themselves.Compared to static cultural commemorative exhibitions, digital interaction stimulates visitors' senses in various ways.Art museums benefit from enhanced lighting, sound, identification, and tactile experiences, which offer additional avenues for acquiring information.This paper, based on "museology" theories, discusses user participation and design in interactive art museum exhibits, analyzing the significance of interactive installations in art exhibitions and the future direction of art exhibitions.

Abstract Sketch‐based image retrieval (SBIR) is an emerging task in computer vision. Research interests have arisen in solving this problem under the realistic and challenging setting of zero‐shot learning. Given a sketch as a query, the search goal is to retrieve the corresponding photographs in a zero‐shot scenario. In this paper, we divide the aforementioned challenging work into three tasks and propose a sharing model framework that addresses these problems. First, the weights of the proposed sharing model effectively reduced the modality gap between sketches and photographs. Second, semantic information was used to handle different label spaces during the training and testing stages. The sketch and photograph domains share semantic information. Finally, a memory mechanism is used to reduce the intrinsic variety in sketches, even if they all belong to the same class. Sketches and photographs dominate the embeddings in turn. Because sketches are not limited by language, our ultimate goal is to find a method to replace text searches. We also designed a demonstration program to demonstrate the use of the proposed method in real‐world applications. Our results indicate that the proposed method exhibits considerably higher zero‐shot SBIR performance than do other state‐of‐the‐art methods on the challenging Sketchy, TU‐Berlin, and QuickDraw datasets.

Chinese traditional glove puppetry is a folk art with a long history. It is worth inheriting and safeguarding this distinguished intangible cultural traditional art using virtual reality. With this background, this study integrates the digital resources of glove puppetry from the perspective of satisfying users’ performance needs. In this study, a multi-user, cloud-based virtual reality glove puppetry system was developed that enhances the classic works of glove puppetry. Each user has a unique perception of the virtual environment and can interact remotely. The system involves human–computer and human–human interactions. This study also describes the design and control of glove puppets. The virtual reality system provides a unique entertainment experience to users of all ages. Through a questionnaire administered to 30 subjects after the user play, this study investigated the operation and experience of this system. According to the research findings, the proposed cloud-based VR system is not only easy to use, but also helps to preserve traditional intangible culture. Our research has high theoretical value and can help preserve traditional glove puppetry. Our cloud-based virtual reality system offers a new application for disseminating and preserving intangible cultural heritage.

The newly developed computer vision pose estimation technique in artificial intelligence (AI) is an emerging technology with potential advantages, such as high efficiency and contactless detection, for improving competitive advantage in the sports industry. The related literature is currently lacking an integrated and comprehensive discussion about the applications and limitations of using the pose estimation technique. The purpose of this study was to apply AI pose estimation techniques, and to discuss the concepts, possible applications, and limitations of these techniques in table tennis. This study implemented the OpenPose pose algorithm in a real-world video of a table tennis game. The research results show that the pose estimation algorithm performs well in estimating table tennis players’ poses from the video in a graphics processing unit (GPU)-accelerated environment. This study proposes an innovative two-stage AI pose estimation method for effectively addressing the current difficulties in applying AI to table tennis players’ pose estimation. Finally, this study provides several recommendations, benefits, and various perspectives (training vs. tactics) of table tennis and pose estimation limitations for the sports industry.

In this paper, we propose an immersive and interactive way to explore the virtual space of a future museum using Mediapipe body pose tracking solution, Unity 3D game engine, and a machine learning model. Users can explore the built virtual space by movement translating and scaling changing for the virtual avatar. Without wearing any wearable devices or operating any joysticks, according to the trained LSTM machine learning behavior models, users can control the avatar in the built virtual space.