Selected work

Representative Papers

Enhancing Presence, Deepening Fan Intensity: How Presence in Immersive Video Shapes Psychological Closeness to Performers

Jun 07, 2026

This study investigates the mechanism through which presence in immersive video influences audience parasocial intensity, with particular attention to the moderating role of camera distance. Employing a within-subjects design, the experiment manipulated shooting distance (1.2 m vs. 7.6 m) in 180-degree stereoscopic videos of a Japanese idol performance presented via head-mounted display. Presence was assessed using the SUS Presence Scale and measures of perceived psychological overlap, and mixed-design ANOVA was used to test hypothesized effects. For the first time, camera distance was treated as a controllable design variable, revealing that closer proximity significantly enhances perceived possibilities for action, social presence, and observability, thereby strengthening parasocial emotional connection. These findings underscore the critical role of camera distance in modulating the causal relationship between presence and affective intensity in immersive media.

0 citationsRead paper

Content-Aware Ad Banner Layout Generation with Two-Stage Chain-of-Thought in Vision Language Models

Dec 14, 2025

Traditional advertising layout generation relies on saliency detection, neglecting image semantics and spatial structure, resulting in suboptimal layout rationality. To address this, we propose a two-stage, semantics-driven layout generation method grounded in Vision-Language Models (VLMs). In the first stage, a VLM parses the background image to extract fine-grained semantic content and spatial relationships, producing a structured, text-based layout plan. In the second stage, this plan is precisely compiled into renderable HTML code. Our approach introduces the novel “semantic planning → code generation” chained reasoning paradigm, enabling the first instance of content-aware, fine-grained spatial reasoning for layout synthesis. Quantitative and qualitative evaluations demonstrate that our generated layouts better align with visual center-of-gravity principles and semantic logic: human satisfaction improves by 37%, and HTML renderability reaches 99.2%—significantly outperforming state-of-the-art methods.

0 citationsRead paper

Recent publications

Latest Papers

Enhancing Presence, Deepening Fan Intensity: How Presence in Immersive Video Shapes Psychological Closeness to Performers

Jun 07, 2026

This study investigates the mechanism through which presence in immersive video influences audience parasocial intensity, with particular attention to the moderating role of camera distance. Employing a within-subjects design, the experiment manipulated shooting distance (1.2 m vs. 7.6 m) in 180-degree stereoscopic videos of a Japanese idol performance presented via head-mounted display. Presence was assessed using the SUS Presence Scale and measures of perceived psychological overlap, and mixed-design ANOVA was used to test hypothesized effects. For the first time, camera distance was treated as a controllable design variable, revealing that closer proximity significantly enhances perceived possibilities for action, social presence, and observability, thereby strengthening parasocial emotional connection. These findings underscore the critical role of camera distance in modulating the causal relationship between presence and affective intensity in immersive media.

0 citationsRead paper

Content-Aware Ad Banner Layout Generation with Two-Stage Chain-of-Thought in Vision Language Models

Dec 14, 2025

Traditional advertising layout generation relies on saliency detection, neglecting image semantics and spatial structure, resulting in suboptimal layout rationality. To address this, we propose a two-stage, semantics-driven layout generation method grounded in Vision-Language Models (VLMs). In the first stage, a VLM parses the background image to extract fine-grained semantic content and spatial relationships, producing a structured, text-based layout plan. In the second stage, this plan is precisely compiled into renderable HTML code. Our approach introduces the novel “semantic planning → code generation” chained reasoning paradigm, enabling the first instance of content-aware, fine-grained spatial reasoning for layout synthesis. Quantitative and qualitative evaluations demonstrate that our generated layouts better align with visual center-of-gravity principles and semantic logic: human satisfaction improves by 37%, and HTML renderability reaches 99.2%—significantly outperforming state-of-the-art methods.

0 citationsRead paper