Shanghai Theatre Academy (Chinese: 上海戏剧学院) is a public university in Shanghai, People's Republic of China dedicated to dramatic art education. Its predecessor was Shanghai Municipal Experimental Theatre School cofounded by the famous educator Gu Yuxiu (顾毓琇). Its alumni include actresses Pan Hong, Li Bingbing, Xing Fei, Fan Bingbing, Li Qin, Dilraba Dilmurat, Ma Yili, Xiao Song Jia, Wan Qian and Zhang Yuqi, and actors Tong Dawei, Lu Yi, and Deng Lun..
Narrative-driven product photography has become a prevalent paradigm in modern marketing, as coherent visual storytelling helps convey product value and establishes emotional engagement with consumers. However, existing image generation methods do not support structured narrative planning or cross-panel coordination, often resulting in weak storytelling and visual incoherence. In practice, narrative product photography is commonly presented as multi-grid collages, where multiple views or scenes jointly communicate a product narrative. To ensure visual consistency across grids and aesthetic harmony of the overall composition, we generate the collage as a single unified image rather than composing independently synthesized panels. We propose a self-reasoning agentic framework for narrative product grid collage generation. Given a product packshot and its name, the system first constructs a Product Narrative Framework that explicitly represents the product's identity, usage context, and situational environment, and translates it into complementary grids governed by a shared visual style. Constraint-aware prompts are then compiled and fed to a generation model that synthesizes the collage jointly. The generated output is evaluated on both content validity and photography quality, with explicit gates determining whether to proceed or refine. When evaluation fails, the system performs failure attribution and applies targeted refinement, enabling progressive improvement through iterative self-reflection. Experiments demonstrate that our framework consistently improves aesthetic quality, narrative richness, and visual coherence, compared to direct prompting baselines.
Daoism is an important indigenous religion of China that emerged from ancient totemic worship and shamanic practices, encompassing mysterious ritual arts known as fulu (talismans and registers). Daoist fulu writing constitutes an important content and manifestation of Daoist spiritual calligraphy, representing a significant embodiment of Daoist sacred knowledge and mystical power. This paper presents the first in-depth investigation into the sources of the mysterious numinous power inherent in Daoist fulu writing. We conclude that the spiritual power of fulu writing derives from three distinct yet interconnected levels: external divine spiritual power, innate primordial qi spiritual power, and the fundamental Dao spiritual power. These three sources are not mutually exclusive but rather work in coordination. Only through the integration of the fundamental Dao spiritual power at the primordial level with the High Master's own innate primordial qi spiritual power can external divine spiritual power be mobilized and utilized. This unity of subject and object, essence and application, forms a complete cycle that maximizes the spiritual efficacy of the talismans. Furthermore, to apply these research findings to promote contemporary artistic creation and enhance the mystical and innovative dimension of contemporary art at the visual level, the authors, drawing upon their personal Daoist cultivation experiences and fulu writing artistic practice, will further discuss the revelatory significance of fulu writing for contemporary calligraphic art creation.
Multimodal cultural data can be preserved and retrieved, yet they often remain difficult to understand as continuous relational contexts. This study proposes a hierarchical semantic organization framework for digital memory construction and examines how it connects back-end data organization with front-end user navigation. An exploratory design research approach was adopted. A Unity-based interactive prototype was developed from 113 world exposition-related event records and more than 3,000 image resources. Nine adult participants completed four tasks—structure identification, relation tracing, immediate path reconstruction, and confusion and recovery—each lasting approximately 5–8 min, followed by a post-task interview of approximately 5–10 min. Contemporaneous observation notes and written post-task interview records were analyzed through directed content analysis. Five participants began with a year or temporal entry, two used a single non-temporal entry, and two switched among multiple entries. Six participants explained at least one cross-event or cross-object relational context, six demonstrated multimodal contextualization, and six completely or substantially reconstructed their browsing paths immediately after the tasks. One participant showed a clear navigation difficulty; another briefly paused under high node density but did not meet the coding threshold for navigation difficulty. The study proposes a layered navigation mechanism that transforms uneven data coverage and depth into structures that are locatable, relatable, accessible, and returnable, while clarifying design boundaries concerning relation interpretability, current-position cues, return mechanisms, and information-density control.
We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and preference-adaptive modeling. Lighting design in live performance settings requires the seamless translation of musical features into dynamic lighting behaviors. However, traditional workflows remain time-consuming, labor-intensive, and difficult to transfer. AuraLuxMuse encodes music and professional cue sequences into a shared retrieval space, estimates cue-event density, and retargets selected fixture commands to the destination stage. It assists pre-production authoring by returning editable cues rather than replacing the designer with an unconstrained generator. At the heart of AuraLuxMuse are two key modules: Lighting-Aligned Music Pretraining (LAMP), which performs contrastive learning between audio and lighting cues for alignment, and Preference-Adaptive Mixture of Experts (PAMoE), which conditions preference-aware cue retrieval and adaptation on designers' intent through a gated ensemble of style-specific expert networks. To support training and evaluation, we introduce Musilux, the first dataset of paired musical audio and professional lighting cue sequences under diverse performance scenarios. We evaluate AuraLuxMuse across both virtual simulation environments and professional-grade laboratories. Experimental results, including objective and subjective evaluation, demonstrate that AuraLuxMuse retrieves and adapts stage-lighting cues that are visually cohesive, semantically meaningful, and artistically expressive, showing its potential for AI-assisted aesthetic stage design.
Since its release, Hayao Miyazaki's Princess Mononoke has often been interpreted within the frameworks of ecocriticism and feminism, but existing studies often neglect its implicit power structures. To overcome this limitation, this paper employs Gayatri Spivak's postcolonial feminist theory to critically reread the film. Through an analysis of the three main charactersLady Eboshi, San, and Ashitakathis paper finds that: Lady Eboshi's "female utopia," Tatara, is actually based on the plunder of the forest, and her discourse replicates the imperialist logic of conquering the "other"; San, as a "cultural hybrid" rejected by both humans and beasts, is trapped of being a "subaltern," and her resistance is assumed as irrationality by the dominant discourse; while Ashitaka's mediator role implicitly contains the "savior" narrative criticized by Spivak, weakening the subjectivity of female characters. The study shows that there is a complex relationship of oppression in Princess Mononoke, and Spivak's theory can help reveal this relationship.