No abstract

In e-commerce, consumer-generated videos, which in general deliver consumers' individual preferences for the different aspects of certain products, are massive in volume. To recommend these videos to potential consumers more effectively, diverse and catchy video titles are critical. However, consumer-generated videos seldom accompany appropriate titles. To bridge this gap, we integrate comprehensive sources of information, including the content of consumer-generated videos, the narrative comment sentences supplied by consumers, and the product attributes, in an end-toend modeling framework. Although automatic video titling is very useful and demanding, it is much less addressed than video captioning. The latter focuses on generating sentences that describe videos as a whole while our task requires the product-aware multigrained video analysis. To tackle this issue, the proposed method consists of two processes, i.e., granular-level interaction modeling and abstraction-level story-line summarization. Specifically, the granular-level interaction modeling first utilizes temporal-spatial landmark cues, descriptive words, and abstractive attributes to builds three individual graphs and recognizes the intra-actions in each graph through Graph Neural Networks (GNN). Then the global-local aggregation module is proposed to model inter-actions across graphs and aggregate heterogeneous graphs into a holistic graph representation. The abstraction-level story-line summarization further considers both frame-level video features and the holistic graph to utilize the interactions between products and backgrounds, and generate the story-line topic of the video. We collect a large-scale dataset accordingly from real-world data in Taobao, a world-leading e-commerce platform, and will make the desensitized version publicly available to nourish further development of the research community 1 . Relatively extensive experiments on various datasets demonstrate the efficacy of the proposed method.

No abstract

Practical skill-based education requires exemplary face-to-face operational teaching, and VR can enhance online distance learning, facilitating an alternative form of “face-to-face” teaching, which results in better teacher–student communication and learner self-efficacy. It also constitutes as a useful substitute for in-person teaching, and it also has a positive impact on learning effectiveness. In this study, a mixed-method approach was used, which utilized the following methodologies: a combination of quantitative and qualitative measures, document collection, case and comparative analysis, and VR teaching that utilizes “You, Calligrapher” as a survey tool. Teachers and students of art were selected, who then used an educational VR-based calligraphy game application for teaching activities. We investigated the impact of virtual time, space, and technical availability on learners’ understanding, imagination, and interactivity in VR education, and then we evaluated the positive impact via learner feedback. Research tools that we utilized consist of comprehension, imagination, and how feedback motivation scales with effective learning; we have also used Chinese calligraphy performance tests. The SPSS statistical analysis software was used for related statistical processing, and α was set to 0.05. The results of this study indicated that Chinese calligraphy studies in VR time and space affect students’ understanding and imagination but not their operational abilities. According to our research, a fundamental difference between traditional and modern teaching methods is a shift toward the use of VR (and the internet) in education. Therefore, the focus of this study is on understanding the impact on practical skills during distance learning and investing the impacts in order to form an effective approach to the use of VR in education.

This research analysed the integration of innovation and entrepreneurship education for students, majoring in digital media art design. Using a grounded theory approach, we investigated the experiences of two research groups: five leaders of digital media art design courses in colleges and universities, and five successful entrepreneurs who had majored in digital media art design and had achieved significantly in the industry after graduation. From the two dimensions of ‘innovation’ and ‘entrepreneurship’, as well as the two perspectives of ‘implementer’ and ‘party’, semi-structured interviews were conducted on the core competencies that innovation and entrepreneurship talents should have the methods and experience of innovation and entrepreneurship education, the difficulties and problems in the implementation of innovation and entrepreneurship education, the need for talent among enterprises and the factors affecting entrepreneurship success. By analysing and clustering the data, we were able to comprehensively identify the main problems and aspects that require more attention in terms of cultivating innovative and entrepreneurial talents in the digital media art design major. Based on the grounded theory research method, this paper established a theoretical model, outlining the innovation of the digital media art design major and the entrepreneurship education reform path. The key internal elements of the model include mechanisms for professional talent training, curriculum integration, teacher team construction and resource support. The school-enterprise cooperation mechanism is recognised as the key external element for innovation and entrepreneurship education reform. The results provide direction for future education and teaching reform, as well as professional input for the digital media art design major. The findings encourage those involved in the digital media art design major to cultivate more high-level, pioneering professionals, so as to adapt to the transformation and upgrading of economic and social development in the context of a growing digital economy.