Yuxian paper cutting is a distinctive regional form within UNESCO-recognized Chinese paper cutting. Its opera figure images remain difficult to organize at scale because interpretation and cataloguing rely heavily on manual expertise, while automated tools for preliminary annotation and retrieval remain limited. This study formulates a domain-specific object detection task and constructs a curated dataset of 926 original images containing 976 annotated instances across three operational visual categories: armor-clad, robe-wearing, and female-role figures. A YOLOv8n-based detector is adapted by integrating the Spatial and Channel Synergistic Attention (SCSA) module and the Inner-IoU regression strategy. On the test set, the resulting configuration achieves 95.8% precision, 92.9% recall, 98.8% mAP@0.5, and 89.6% mAP@0.5:0.95, exceeding the YOLOv8n baseline by 3.0, 3.6, 2.9, and 2.9 percentage points, respectively. It also achieves a forward-pass throughput of 92.3 FPS under the reported GPU configuration. Among the evaluated configurations, the combined SCSA placement with Inner-IoU achieved the highest overall detection performance under the current dataset and experimental protocol. The results support its use for preliminary visual-category annotation, retrieval, and organization of Yuxian paper-cut opera figure resources. However, the findings are based on a small domain-specific dataset and require further validation across alternative data partitions and broader heritage collections.

Generative artificial intelligence (AI) is increasingly used to analyze and compare design alternatives, yet how design students evaluate AI advice and how such evaluation relates to final design judgments remain insufficiently understood. This study examines the associations among perceived AI interaction conditions, critical evaluation of AI advice, and expert-rated Design Judgment Quality. A cross-sectional study combined a standardized poster comparison task with a post-task questionnaire involving 118 visual communication design students. Participants interacted with Doubao-Seed-2.1-Pro and submitted design choices, rationales, and revision recommendations. Perceived Feedback Diagnosticity, Interaction Controllability, and three critical evaluation activities were measured through post-task self-reports, while Design Judgment Quality was independently assessed by three experts. Partial least squares structural equation modeling (PLS-SEM) was used for hypothesis testing. Feedback Diagnosticity was positively associated with Evidence Verification, Argument Scrutiny, Contextual Fit Evaluation, and Design Judgment Quality. Interaction Controllability was positively associated with Argument Scrutiny and Contextual Fit Evaluation, but not directly with Design Judgment Quality. Among the three evaluation activities, only Argument Scrutiny showed a significant positive association with expert-rated Design Judgment Quality. These findings suggest that AI-assisted design judgment requires attention to both the perceived value of AI feedback and how users examine AI recommendations and their underlying rationales.