This study introduces an educational framework that merges 3D modeling with AI-assisted narrative interaction to apply digital technology in cultural heritage education, exemplified by an ancient carriage culture. Through immersive tasks and contextual narratives, the course notably improved learners’ professional skills and cultural awareness. Experimental results revealed significant knowledge acquisition among participants post-engagement. Additionally, the user experience improved, with increased satisfaction in the narrative interaction design course. These enhancements led to heightened interest in cultural heritage and deeper knowledge acquisition. Utilizing Norman’s three-layer interaction model, Ryan’s contextual narrative theory, and Falk and Dierking’s museum learning experience model, the study developed a systematic course for multi-sensory design and contextual interaction, confirming the positive impact of multimodal interaction on learning outcomes. This research provides theoretical support for the digital transformation of cultural education and practical examples for educational practitioners and cultural institutions to implement in virtual presentations and online learning.

1. In recent years, with the rapid integration of artificial intelligence (AI) into global higher education, AI tools have become deeply embedded in teaching and learning processes. According to th...

Generative AI is increasingly used in heritage visualization, yet its outputs often raise concerns about cultural authenticity. Prior studies have focused more on technical fidelity and symbolic preservation than on how audiences evaluate the authenticity of AI-generated heritage imagery. To address this gap, this study develops and tests a Stimulus-Organism-Response model using AI-generated Wuxi clay figurine images. A randomized between-subjects online experiment with 330 participants examined the associations of visual information quality, AI technical novelty, and symbol salience with perceived aesthetics, perceived authenticity, cultural identity, and acceptance intention. The theory-specified model showed that visual information quality, technical novelty, and symbol salience were positively associated with perceived aesthetics, while perceived aesthetics and symbol salience were positively associated with perceived authenticity. Perceived aesthetics and perceived authenticity were also associated with cultural identity and acceptance intention. However, the HTMT analysis indicated limited discriminant validity, particularly among visual information quality, technical novelty, symbol salience, and perceived aesthetics. A supplementary second-order model representing these four perceptions as facets of an overall perceived design quality factor showed acceptable fit and comparable downstream associations. In this alternative specification, perceived authenticity was no longer independently associated with acceptance intention. Accordingly, the construct-specific path estimates should be interpreted cautiously. Overall, the findings are consistent with the presence of a substantial holistic evaluative component in audience responses to AI-generated heritage imagery.

Han pictorial stones constitute an important component of China’s ancient cultural heritage, and their depictions of chariots, horses, and human figures provide valuable visual evidence for investigating travel activities in the Han dynasty. The identification and localization of chariot-and-horse elements provide a foundation for the retrieval and statistical analysis of relevant materials. However, current documentation practices rely largely on manual identification and transcription, limiting the efficiency of large-scale processing. In Han pictorial stone images, weak contours, textural interference, dense occlusion, and scale variation pose substantial challenges for reliable object detection. Accordingly, 539 images were collected and annotated with 3736 instances. Building on this dataset, an improved YOLO11n model was proposed, incorporating the RubbingDown multi-branch downsampling structure, C3k2GRM module, and task-adapted ASF multi-scale fusion pathway for information preservation, contextual representation, and cross-scale feature fusion. The proposed model achieved mAP@0.5, mAP@0.5:0.95, and recall of 88.0%, 54.5%, and 86.5%, respectively, representing improvements of 5.5, 2.8, and 9.9 percentage points, respectively, over the YOLO11n baseline. The model maintained 2.58 M parameters, while GFLOPs increased from 6.3 to 7.3. The detection outputs could support future workflows for documenting, retrieving, quantitatively analyzing, and manually verifying chariot-and-horse elements in Han pictorial stone images.

Perceived authenticity may strengthen the credibility of virtual cultural heritage communication and foster sustained cultural engagement, yet authenticity theory remains insufficiently translated into actionable design guidance. This study employed an exploratory sequential mixed-methods design comprising ten qualitative interviews, exploratory and confirmatory factor analyses with two independent samples (n = 200 each), framework construction, and a between-group prototype evaluation (n = 61). The analyses indicated a context-specific two-factor structure: constructive authenticity, integrating evidence-based judgment, contextual interpretation, and narrative plausibility; and existential authenticity, encompassing participation, emotional engagement, personal meaning, and cultural connection. Objective authenticity converged with constructive authenticity rather than emerging independently, suggesting that users interpreted historical evidence through digitally mediated representations. These findings were translated into six coordinated design dimensions: historical environment design, historical information transparency, narrative plausibility, stylistic atmosphere, experiential immersion, and interactive engagement. In a single-theme comparison, the framework-guided prototype was associated with higher loyalty, satisfaction, cultural identity, and behavioral intention than the conventionally designed prototype (Hedges’ g = 1.265–1.636). Overall, the study offers a context-specific theoretical account and an actionable, evidence-informed framework that may support continued engagement and cultural transmission; long-term sustainability outcomes and cross-context transferability require further investigation.