Search Results (111)

To address the temporal jitter with low segmentation accuracy and the lack of high-precision transformations for specific object classes in video generation, we propose the fish body pattern sync-style network for ornamental fish videos. This network innovatively integrates dynamic texture transfer with instance segmentation, adopting a two-stage processing architecture. First, high-precision video frame segmentation is performed using Mask2Former to eliminate background elements that do not participate in the style transfer process. Then, we introduce the wavelet-gated styling network, which reconstructs a multi-scale feature space via discrete wavelet transform, enhancing the granularity of multi-scale style features during the image generation phase. Additionally, we embed a convolutional block attention module within the residual modules, not only improving the realism of the generated images but also effectively reducing boundary artifacts in foreground objects. Furthermore, to mitigate the frame-to-frame jitter commonly observed in generated videos, we incorporate a contrastive coherence preserving loss into the training process of the style transfer network. This enhances the perceptual loss function, thereby preventing video flickering and ensuring improved temporal consistency. In real-world aquarium scenes, compared to state-of-the-art methods, FSSNet effectively preserves localized texture details in generated videos and achieves competitive SSIM and PSNR scores. Moreover, temporal consistency is significantly improved. The flow warping error index decreases to 1.412. We chose FNST (fast neural style transfer) as our baseline model and demonstrate improvements in both model parameter count and runtime efficiency. According to user preferences, 43.75% of participants preferred the dynamic effects generated by this method. Full article

South Korea is rapidly transitioning into an aging society, resulting in a growing demand for senior multi-family housing. Nevertheless, current façade designs remain limited in diversity and fail to adequately address the visual needs and preferences of the elderly population. This study presents a biophilic façade design approach for senior housing, utilizing Stable Diffusion (SD) fine-tuned with low-rank adaptation (LoRA) to support the implementation of differentiated biophilic design (BD) strategies. Prompts were derived from an analysis of Korean and worldwide cases, reflecting the perceptual and cognitive characteristics of older adults. A dataset focusing on key BD attributes—specifically color and shapes/forms—was constructed and used to train the LoRA model. To enhance accuracy and contextual relevance in image generation, ControlNet was applied. The validity of the dataset was evaluated through expert assessments using Likert-scale analysis, while model reliability was examined using loss function trends and Frechet Inception Distance (FID) scores. Our findings indicate that the proposed approach enables more precise and scalable applications of biophilic design in senior housing façades. This approach highlights the potential of AI-assisted design workflows in promoting age-inclusive and biophilic urban environments. Full article

Instance searches pertain to the identification of specific objects or scenes within a dataset that correspond to a given query image. The existing research primarily concentrates on improving the accuracy of machine-recognized instances, frequently neglecting the pivotal role of human–computer interaction. As a result, effectively searching for instances that align with user preferences continues to pose a substantial challenge. In this paper, we introduce an intuitive and efficient instance search method that incorporates human–computer interaction. Specifically, our proposed interactive instance search system includes tools that enable users to directly highlight specific instances of interest within the query image. Furthermore, we propose the use of learned perceptual image patch similarity to effectively bridge the semantic gap between low-level features and high-level semantics. Contrary to conventional metrics, such as cosine similarity, which rely on pixel-level or superficial feature comparisons, we employ deep neural networks to model perceptual differences in a hierarchical manner. The experimental results demonstrate that our approach surpasses traditional methods in terms of similarity-matching accuracy and exhibits robust performance on datasets such as Oxford5k and Paris6k. Full article

From the perspective of social media data, this study investigates the coupling relationship between tourists’ spatial perception and tourism image in traditional old urban areas. Using Nanxun Ancient Town as a case study, this paper reveals the interaction and mutual influence between tourists’ perception of space and tourism image in the development of traditional ancient town tourism. We employed Python 3.13.0 to gather 10,789 valuable comments from tourists from Dianping 11.35.3, Ctrip 8.78.4, and Mafengwo 11.2.6. Mini Tag Cloud software is used to analyze the text data, systematically classify the cognitive image of tourists, and identify negative emotional factors. This paper constructs a four-dimensional landscape spatial perception evaluation system centered on “high-frequency words”, “perceptual dimensions”, “semantic networks”, and “emotional tendencies”. The key findings are as follows: (1) Tourists’ spatial perception exhibits pronounced characteristics of subjective preference and emotional attachment influenced by emotional factors. Overall, tourists exhibited positive emotional perceptions, with 59.51% positive emotions, 21.16% neutral emotions, and 19.33% negative emotions. (2) The perception of Nanxun Ancient Town’s tourism image can be summarized into four dimensions. Here are the dimensions in order of how important they are: historical culture and folk heritage (34.18%), perceptions of natural landscape and architectural style (31.03%), perceptions of tourism services and facilities (18.37%), and psychological identity and emotional interaction (16.42%). (3) Tourism image reciprocally influences tourists’ spatial perception. A positive tourism image is anticipated to encourage tourists to explore the spatial details of the ancient town more deeply, enhancing their positive spatial perception and experience. There exists a coupling relationship between tourists’ spatial perception and tourism image. (4) Key aspects of tourists’ perception of Nanxun Ancient Town include its historical and cultural significance, as well as commercialization. Future studies could focus on tourists’ spatial perception and tourism destination brand image building, and tourism policy makers should pay attention to tourists’ perception of Nanxun Ancient Town’s history, culture and commercialization, and use the coupling of the two to improve development and service policies. Full article

Xishu Gardens, an exemplary narrative of classical Chinese gardens, faces challenges in preserving its commemorative spatial structures while accommodating modern visitors’ needs. While trajectory analysis is critical, existing studies struggle to interpret multi-dimensional perception-preference data owing to spatiotemporal mismatches in multi-source datasets. This study adopted an improved Ward–K-medoids hybrid clustering algorithm to analyze 885 trajectory samples and 34,384 synchronized data points capturing emotional valence, cognitive evaluations, and dwell time behaviors via panoramic digital twins across three heritage sites (Du Fu Thatched Cottage, San Su Shrine, and Wangjiang Tower Park). Our key findings include the following: (1) Axial bimodal patterns: Type I high-frequency looping paths (27.6–68.9% recurrence) drive deep exploration, in contrast to Type II linear routes (≤0.5% recurrence), which enable intensive node coverage. (2) Layout-perception dynamics: single-axis layouts maximize behavioral engagement (DFTC), free-form designs achieve optimal emotional-cognitive integration (WTP), and multi-axis systems amplify emotional-cognitive fluctuations (SSS). (3) Spatial preference hierarchy: entrance and waterfront zones demonstrate dwell times 20% longer than site averages. Accordingly, the proposed model synchronizes Type II peak-hour throughput with Type I off-peak experiential depth using dynamic path allocation algorithms. This study underscores the strong spatial guidance mechanisms of Xishu Gardens, supporting tourism management and heritage conservation. Full article

Consumer attitude shift and green transport advocacy in the sharing economy highlight shared two-wheeled electric scooters (STWESs) for short-distance commuting. Current designs often overlook user emotions and aesthetic alignment with product characteristics. A product design methodology is proposed in this study, constructing optimization models from both the functional experiential and perceptual visual layers. Utilizing context analysis theory (CAT) and the KANO model, an STWES contextual requirements optimization model is formulated. The expert method is then applied to identify five key design elements, generating a category diagram based on typical samples, followed by Kansei evaluation. Using quantitation theory type I (QT-1), regression equations are fitted to determine the impact of different design categories on Kansei evaluation. Illustrated in a campus setting, this approach optimizes the shared mobility experience, meeting college students’ aesthetic preferences. This method serves as a valuable reference for product design in diverse contexts. Full article

Emerging evidence underscores the beneficial effects of campus green spaces (CGSs) on student well-being and recovery. Previous research has predominantly examined the independent roles of landscape characteristics and preferences in mental restoration. However, limited studies have explored the complex interrelationships among restorative effects, landscape characteristics, preferences, and place-bonding factors, particularly within the context of CGSs. To address this gap, this study developed a validated campus landscape perception scale comprising three dimensions (perception of natural characteristics, perception of artificial characteristics, spatial perception) and 20 related indicators. In the second phase, the scale was used to investigate the influence mechanism of perceived campus landscape characteristics on mental restoration. A total of 36 CGSs across six higher education institutions in Nanjing were selected, representing diverse spatial types. The restoration experiences of 759 participants were measured using psychological indicators when viewing these landscapes. With the help of deep learning techniques, landscape elements were integrated with perceptual factors for partial least squares (PLS)-based statistical analysis. Our findings indicate that the natural and spatial dimensions significantly influence mental restoration, whereas the artificial dimension does not directly impact psychological health. Nevertheless, all dimensions indirectly enhance mental restoration through landscape preference and perceived restorativeness. The study also revealed the moderating effect of objective landscape elements on the relationship between the perception of landscape characteristics and landscape preference. This study confirms the positive role of perceived campus landscape characteristics in fostering mental restoration among students and elucidates the intricate pathway of influence, namely “perception of landscape characteristics → landscape preference → perceived restorativeness → mental restoration”. These findings offer new insights into the complex processes of environmental restoration, where psychological and physical factors are intertwined. Finally, theoretical and managerial implications for improving landscape planning in restoration research are proposed. Full article

Aesthetics primarily focuses on the study of art, encompassing the aesthetic categories of beauty and ugliness, as well as human aesthetic activities. Image Aesthetics Assessment (IAA) seeks to automatically evaluate the aesthetic quality of images by mimicking the perceptual mechanisms of humans. Recently, researchers have increasingly explored using user comments to assist in IAA tasks. However, human aesthetics are subjective, and individuals may have varying preferences for the same image, leading to diverse comments that can influence model decisions. Moreover, in practical scenarios, user comments are often unavailable. Thus, this paper proposes a CLIP-based method for IAA (IAACLIP) using generative descriptions and prompts. First, leveraging the growing interest in multimodal large language models (MLLMs), we generate objective and consistent aesthetic descriptions (GADs) for images. Second, based on aesthetic images, labels, and GADs, we introduce a unified contrast pre-training approach to transition the network from the general domain to the aesthetic domain. Lastly, we employ prompt templates for perceptual training to address the lack of real-world comments. Experimental validation on three mainstream IAA datasets demonstrates the effectiveness of our proposed method. Full article

To make guitars with high sonic quality, it is essential to understand the relationship between the physical characteristics of the selected materials and the acoustic characteristics of the final instrument and how they will be perceived. The selection of wood for the soundboard is a crucial step in the guitar-making process. One relevant physical characteristic is internal material damping, about which, however, only little is known in comparison to other characteristics such as density and Young’s modulus. The present study investigated the relationship of soundboard damping to both physical and perceptual aspects of guitar sound. Three similar steel-string guitars were built with the damping of their soundboards varying between low, mid and high. Measurements of the transfer function and the plucked tone decay of the final guitars were carried out. A listening test and a playing test were conducted. The participants were asked to rate preference and seven sound attributes comprising loudness and both spectral and temporal aspects. To prepare the listening test, a short sequence was recorded by a professional guitarist with each guitar. The results suggest that varying soundboard damping had no practically relevant influence on the physical and perceptual aspects of the sound of the guitar used in this study. Full article

Social sustainability relies on the promotion of social processes and structures that ensure the basic needs of individuals and communities are met while also encouraging constructive interactions among them. This paper offers an overview of the characteristics of Italy’s peripheral rural areas and presents findings from a targeted survey conducted across three southern Italian regions. Evaluations collected from a sample of residents were analyzed using the class of CUB models, which are suitable for preference and opinion data. Subjective perceptions of well-being and quality of life, community participation, and the quality of social relationships were examined. Residents’ opinions on the available services in the areas, including economic facilities, digitalization, and transportation, were also considered. Our research indicates that perceptions of well-being in the peripheral areas of Italy are remarkably influenced by individuals’ assessments of their income adequacy. Our findings establish a strong connection between a positive self-assessment of well-being and the belief that income can sufficiently meet needs. Exploring the perceptual dimensions of well-being can offer valuable insights for stakeholders and decision-makers in developing policy efforts and community-led social innovations, which are critical for fighting sentiments of marginalization in rural areas caused by economic perceptions. Full article

Urban street spaces play a crucial role in children’s daily commuting and social activities. Therefore, the design of these spaces must give more consideration to children’s perceptual preferences. Traditional street landscape perception studies often rely on subjective analysis, which lacks objective, data-driven insights. This study overcomes this limitation by using eye-tracking technology to evaluate children’s preferences more scientifically. We collected eye-tracking data from 57 children aged 6–12 as they naturally viewed 30 images depicting school commuting environments. Data analysis revealed that the proportions of landscape elements in different street types influenced the visual perception characteristics of children in this age group. On well-maintained main and secondary roads, elements such as minibikes, people, plants, and grass attracted significant visual attention from children. In contrast, commercial streets and residential streets, characterized by greater diversity in landscape elements, elicited more frequent gazes. Children’s eye-tracking behaviors were particularly influenced by vibrant elements like walls, plants, cars, signboards, minibikes, and trade. Furthermore, due to the developmental immaturity of children’s visual systems, no significant gender differences were observed in visual perception. Understanding children’s visual landscape preferences provides a new perspective for researching the sustainable development of child-friendly cities at the community level. These findings offer valuable insights for optimizing the design of child-friendly streets. Full article

As China’s urban development enters the era of stock optimization, the practice of transforming and utilizing spaces under urban overpasses is rapidly gaining momentum. Converting these underpass spaces into sports areas has emerged as a new form of creating public space. Understanding the perceptions of users from different age groups towards these underpass spaces holds significant guiding value for optimizing the design of such areas and improving the quality of service. Taking the Yanshan Interchange Lowline Park in Jinan as an example, this research applied methods of observation, interviews, questionnaires, and importance–satisfaction analysis (ISA) to investigate the activity preferences and the similarities and differences in the perceptions of spatial environment elements in underpass spaces among four age groups: children, youth, middle-aged adults, and the elderly. The findings indicate that different age groups exhibit varying degrees of sensitivity to spatial information, demand levels, and perceptual perspectives in underline parks, which result in distinct spatiotemporal distributions and spatial perception disparities when using the park. All the groups agree that the underpass sports space requires significant improvements in terms of comfort and safety. Based on this, this study proposes age-friendly urban space renewal strategies for spaces under elevated highways, focusing on addressing areas with lower satisfaction across all age groups. These strategies include optimizing the allocation of time, area, and activity types within activity spaces, enhancing the safety and comfort of activity areas, and enriching the cultural connotation and inclusivity of the space. This research provides a theoretical basis for optimizing and creating age-friendly or age-specific urban sports public spaces under elevated highways. Full article

As an important type of linear cultural heritage and a waterfront landscape that integrates both artificial and natural elements, heritage canals provide the public with a multidimensional perceptual experience encompassing aesthetics, culture, and nature. There remains a lack of refined, micro-level studies on heritage canal landscapes from a multidimensional perspective of visual preference. This study focuses on a typical segment of the Grand Canal in China, specifically the ancient canal section in Yangzhou. We employed SegFormer image semantic segmentation techniques to interpret features from 150 panoramic images, quantitatively identifying the waterfront environmental characteristics of the heritage canal. Four perceptual dimensions were constructed: aesthetic preference, cultural preference, natural preference, and hydrophilic preference. Through a questionnaire survey and various statistical analyses, we revealed the relationships between visual preferences for the waterfront landscape of heritage canals and environmental characteristics. The main findings of the study include the following: (1) Aesthetic preference is positively correlated with cultural, natural, and hydrophilic preferences, while natural preference shows a negative correlation with cultural and hydrophilic preferences. (2) Aesthetic preference is influenced by a combination of blue-green natural elements and artificial factors. Natural preference is primarily affected by increased vegetation visibility, cultural preference is associated with a higher proportion of cultural facilities and high-quality pavements, and hydrophilic preference is linked to larger water surface areas, fewer barriers, and better water quality. (3) There are spatial differences in canal waterfront landscape preferences across different urban areas, with the old city exhibiting higher aesthetic, cultural, and hydrophilic preferences than the new city and suburban areas. Finally, this study proposes strategies for optimising and enhancing the quality of waterfront landscapes of heritage canals, aiming to provide sustainable practical guidance for the future planning and management of these heritage sites. Full article

In addition to their practical and aesthetic qualities, ceramic teapots are highly decorative and stylish. Based on the theory of perceptual engineering, this study employs eye-tracking technology and semantic-difference methods to investigate user preferences for ceramic teapot shapes. Using eye-movement experiments, the study first determines users’ visual attention to different morphological regions. Using the orthogonal alignment method, nine styling samples were developed by combining expert classification of classic and traditional teapot styling elements. By combining a semantic perception questionnaire with a satisfaction questionnaire, the study evaluated users’ visual attention to these samples and their satisfaction with them. It was found that shapes characterized by classic, rounded, and proportional coordination were more in line with consumers’ aesthetic preferences despite the differences in semantic evaluations among consumers of different genders and ages, which led to relatively consistent consumer satisfaction. The purpose of this study is not only to provide a scientific basis for styling ceramic teapots but also to assist designers in grasping the laws of consumer preference in order to create better products. Full article

The popularity of brachycephalic dogs has increased worldwide despite growing evidence of their profound health and welfare issues, largely as a result of their extreme conformation. This study aimed to evaluate the prevalence and risk factors for known perceptual barriers to improving their welfare. An online survey of n = 2006 UK dog owners was conducted, including owners of non-brachycephalic (non-BC; n = 964), mild-moderate brachycephalic (M-BC; n = 706), and extreme brachycephalic (E-BC; n = 336) dogs. The survey explored contemporary knowledge and attitudes toward brachycephalic dogs, with multivariable statistical analyses identifying risk factors for normalisation of brachycephaly-related abnormalities, preference for flat faces and ‘laziness’ in dogs, and self-reported intractability to being deterred from buying a brachycephalic breed. Almost 1 in 7 E-BC owners considered that there was ‘nothing’ that could dissuade them from buying a brachycephalic dog, predicted by a strong preference for flat faces as a highly desirable aesthetic characteristic and beliefs that brachycephaly did not negatively impact lifespan. E-BC owners were most likely to consider flat faces a highly desirable aesthetic characteristic, predicted by highly valuing ‘laziness’ as a behavioural characteristic. Preference for ‘laziness’ as a behavioural characteristic was predicted by low levels of pre-purchase research and aesthetic preferences (e.g., flat faces, large size). High levels of normalisation of brachycephaly-related abnormalities were observed across all ownership groups, particularly for clinical signs related to exercise intolerance, with these beliefs predicted by deficits in dog acquisition behaviours and knowledge, and intractability from being deterred from purchasing a flat-faced dog. These findings highlight the pervasiveness of perceptual barriers that inhibit campaigning regarding brachycephaly and the need for targeted interventions to address misconceptions (e.g., ‘myth busting’ laziness as a positive trait), while being mindful of the heterogeneity of beliefs within the brachycephalic-owning population, particularly the intractable sub-population to whom shifting preferences away from flat-faced conformations may prove impossible without stronger measures, e.g., legislative change. Full article