Understanding urban visual perception is crucial for modeling how individuals cognitively and emotionally interact with the built environment. However, traditional survey-based approaches are limited in scalability and often fail to generalize across diverse urban contexts. In this study, we introduce the UP-CBM, a transparent framework that leverages visual foundation models (VFMs) and concept-based reasoning to address these challenges. The UP-CBM automatically constructs a task-specific vocabulary of perceptual concepts using GPT-4o and processes urban scene images through a multi-scale visual prompting pipeline. This pipeline generates CLIP-based similarity maps that facilitate the learning of an interpretable bottleneck layer, effectively linking visual features with human perceptual judgments. Our framework not only achieves higher predictive accuracy but also offers enhanced interpretability, enabling transparent reasoning about urban perception. Experiments on two benchmark datasets—Place Pulse 2.0 (achieving improvements of +0.041 in comparison accuracy and +0.029 in ) and VRVWPR (+0.018 in classification accuracy)—demonstrate the effectiveness and generalizability of our approach. These results underscore the potential of integrating VFMs with structured concept-driven pipelines for more explainable urban visual analytics.
The purpose of this paper is to explore the effect of virtual environment based on digital technology in improving teenagers’ environmental literacy level. By designing a control study, participants were divided into experimental group and control group with different environmental literacy education methods, and T-test was used to analyze and evaluate their environmental literacy level changes before and after the experiment. Interviews were conducted after the experiment to explore the intervention effect of virtual environment on the environmental literacy level of adolescents. After t test, both groups showed significant improvement in the comprehensive scores of environmental literacy assessment. Moreover, the difference of the experimental group was more significant than that of the control group, especially in environmental awareness, environmental attitude and environmental behavior. (***p < 0.001). The interview results show that 90% of the participants in the experimental group believe that the virtual environment provides a better learning experience and improves their learning efficiency. In contrast, 70% of participants in the control group believed that the content of regular education had brought them great benefits. The role of digital technology in environmental literacy education is significantly higher than that of conventional education group. This finding provides scientific support for the improvement and innovation of environmental literacy education, and can encourage the application of virtual digital technology in environmental literacy education.
This study aimed to explore the effect of artificial intelligence-generated artwork (AIGC) as an adjunct to mindfulness meditation on the improvement of anxiety symptoms in retired people. We recruited a group of retired people with anxiety symptoms and randomly divided them into two groups: the mindfulness meditation group (N=20) and the mindfulness meditation +AIGC group (N=20). The mindfulness meditation group received traditional mindfulness meditation training, while the mindfulness meditation +AIGC group used AI to generate paintings related to the meditation theme after the meditation. The results showed that AIGC-assisted mindfulness meditation significantly improved anxiety symptoms in retired people. After treatment, the average HAM-A score decreased to 19.65 (SD=4.84) in the AIGC group, while the meditation group also improved, with an average HAM-A score decreased to 20.55 (SD=1.43). Independent sample t test showed that the AIGC group had significant improvement in Anxious mood, Cognitive, Depressive mood, and Behavior at interview (p<0.01**), while the meditation group(Medi group) had no significant improvement (p<0.05*). The results of this study verified that AIGC in auxiliary applications can more significantly improve the mental health of the retired population, and is expected to provide a new treatment approach to improve the mental health of the retired population.
Understanding urban visual perception plays a vital role in modeling how people cognitively and emotionally respond to the built environment. However, conventional survey-based methods are limited in scalability and spatial generalization. To address this, we present a transparent and interpretable framework that leverages recent advances in Visual Foundation Models (VFMs) and concept-based reasoning. Our approach, UP-CBM, constructs a task-specific concept vocabulary using GPT-4o and processes urban scene images via a multi-scale visual prompting strategy. This strategy generates CLIP-based similarity maps that supervise the learning of an interpretable bottleneck layer, enabling transparent reasoning between raw visual inputs and perceptual outcomes. Through comprehensive experiments on Place Pulse 2.0 (+0.041 in comparison accuracy, +0.029 in R2) and VRVWPR (+0.018 in classification accuracy), UP-CBM demonstrates superior predictive performance and transparency. These results underscore the value of combining VFMs with structured concept pipelines for robust and scalable urban visual data processing.
With the popularity of wearable devices such as smart watches and bracelets, using them in the field of human body recognition and decoding human behavioral activities from them is of great significance for applications such as health monitoring, daily behavior analysis, and smart home. To promote the application of smart wearable products in mental health, this paper will elaborate the importance of emotion recognition from the background of college students’ cell phone dependence and anxiety through literature research method and survey method, and analyze the current research status of wearable products in intelligent monitoring, explore the way of emotion recognition, and thus put forward the concept of a new type of smart decompression phone case.