Hasil untuk "Aesthetics"

U. Beck, A. Giddens, S. Lash

George Gunkle, D. Berlyne

Shu Kong, Xiaohui Shen, Zhe L. Lin et al.

Real-world applications could benefit from the ability to automatically generate a fine-grained ranking of photo aesthetics. However, previous methods for image aesthetics analysis have primarily focused on the coarse, binary categorization of images into high- or low-aesthetic categories. In this work, we propose to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function. Our model incorporates joint learning of meaningful photographic attributes and image content information which can help regularize the complicated photo aesthetics rating problem.

Bindhu Alappat, Jayaraj Alappat

Anthocyanins are polyphenol compounds that render various hues of pink, red, purple, and blue in flowers, vegetables, and fruits. Anthocyanins also play significant roles in plant propagation, ecophysiology, and plant defense mechanisms. Structurally, anthocyanins are anthocyanidins modified by sugars and acyl acids. Anthocyanin colors are susceptible to pH, light, temperatures, and metal ions. The stability of anthocyanins is controlled by various factors, including inter and intramolecular complexations. Chromatographic and spectrometric methods have been extensively used for the extraction, isolation, and identification of anthocyanins. Anthocyanins play a major role in the pharmaceutical; nutraceutical; and food coloring, flavoring, and preserving industries. Research in these areas has not satisfied the urge for natural and sustainable colors and supplemental products. The lability of anthocyanins under various formulated conditions is the primary reason for this delay. New gene editing technologies to modify anthocyanin structures in vivo and the structural modification of anthocyanin via semi-synthetic methods offer new opportunities in this area. This review focusses on the biogenetics of anthocyanins; their colors, structural modifications, and stability; their various applications in human health and welfare; and advances in the field.

Andros Tjandra, Yi-Chiao Wu, Baishan Guo et al.

The quantification of audio aesthetics remains a complex challenge in audio processing, primarily due to its subjective nature, which is influenced by human perception and cultural context. Traditional methods often depend on human listeners for evaluation, leading to inconsistencies and high resource demands. This paper addresses the growing need for automated systems capable of predicting audio aesthetics without human intervention. Such systems are crucial for applications like data filtering, pseudo-labeling large datasets, and evaluating generative audio models, especially as these models become more sophisticated. In this work, we introduce a novel approach to audio aesthetic evaluation by proposing new annotation guidelines that decompose human listening perspectives into four distinct axes. We develop and train no-reference, per-item prediction models that offer a more nuanced assessment of audio quality. Our models are evaluated against human mean opinion scores (MOS) and existing methods, demonstrating comparable or superior performance. This research not only advances the field of audio aesthetics but also provides open-source models and datasets to facilitate future work and benchmarking. We release our code and pre-trained model at: https://github.com/facebookresearch/audiobox-aesthetics

Wenguan Wang, Jianbing Shen, Haibin Ling

We study the problem of photo cropping, which aims to find a cropping window of an input image to preserve as much as possible its important parts while being aesthetically pleasant. Seeking a deep learning-based solution, we design a neural network that has two branches for attention box prediction (ABP) and aesthetics assessment (AA), respectively. Given the input image, the ABP network predicts an attention bounding box as an initial minimum cropping window, around which a set of cropping candidates are generated with little loss of important information. Then, the AA network is employed to select the final cropping window with the best aesthetic quality among the candidates. The two sub-networks are designed to share the same full-image convolutional feature map, and thus are computationally efficient. By leveraging attention prediction and aesthetics assessment, the cropping model produces high-quality cropping results, even with the limited availability of training data for photo cropping. The experimental results on benchmark datasets clearly validate the effectiveness of the proposed approach. In addition, our approach runs at 5 fps, outperforming most previous solutions. The code and results are available at: https://github.com/shenjianbing/DeepCropping.

Alessandro Bertinetto

Shuaiqi He, Yongchang Zhang, Rui Xie et al.

Challenges in image aesthetics assessment (IAA) arise from that images of different themes correspond to different evaluation criteria, and learning aesthetics directly from images while ignoring the impact of theme variations on human visual perception inhibits the further development of IAA; however, existing IAA datasets and models overlook this problem. To address this issue, we show that a theme-oriented dataset and model design are effective for IAA. Specifically, 1) we elaborately build a novel dataset, called TAD66K, that contains 66K images covering 47 popular themes, and each image is densely annotated by more than 1200 people with dedicated theme evaluation criteria. 2) We develop a baseline model, TANet, which can effectively extract theme information and adaptively establish perception rules to evaluate images with different themes. 3) We develop a large-scale benchmark (the most comprehensive thus far) by comparing 17 methods with TANet on three representative datasets: AVA, FLICKR-AES and the proposed TAD66K, TANet achieves state-of-the-art performance on all three datasets. Our work offers the community an opportunity to explore more challenging directions; the code, dataset and supplementary material are available at https://github.com/woshidandan/TANet.

Leida Li, Yipo Huang, Jinjian Wu et al.

People usually assess image aesthetics according to visual attributes, e.g., interesting content, good lighting and vivid color, etc. Further, the perception of visual attributes depends on the image theme. Therefore, the inherent relationship between visual attributes and image theme is crucial for image aesthetics assessment (IAA), which has not been comprehensively investigated. With this motivation, this paper presents a new IAA model based on Theme-Aware Visual Attribute Reasoning (TAVAR). The underlying idea is to simulate the process of human perception in image aesthetics by performing bilevel reasoning. Specifically, a visual attribute analysis network and a theme understanding network are first pre-trained to extract aesthetic attribute features and theme features, respectively. Then, the first level Attribute-Theme Graph (ATG) is built to investigate the coupling relationship between visual attributes and image theme. Further, a flexible aesthetics network is introduced to extract general aesthetic features, based on which we built the second level Attribute-Aesthetics Graph (AAG) to mine the relationship between theme-aware visual attributes and aesthetic features, producing the final aesthetic prediction. Extensive experiments on four public IAA databases demonstrate the superiority of the proposed TAVAR model over the state-of-the-arts. Furthermore, TAVAR features better explainability due to the use of visual attributes.

Linda Hagen

Marketers frequently style food to look pretty (e.g., in advertising). This article investigates how pretty aesthetics (defined by classical aesthetic principles, such as order, symmetry, and balance) influence healthiness judgments. The author proposes that prettier food is perceived as healthier, specifically because classical aesthetic features make it appear more natural. In a pilot, six main studies and four supplemental studies (total N = 4,301) across unhealthy and healthy, processed and unprocessed, and photographed and real foods alike, people judged prettier versions of the same food as healthier (e.g., more nutrients, less fat), despite equal perceived price. Even given financial stakes, people were misled by prettiness. In line with the proposed naturalness process, perceived naturalness mediated the effect; belief in a “natural = healthy” connection moderated it; expressive aesthetics, which do not evoke naturalness, did not produce the effect (despite being pretty); and reminders of artificial modification, which suppress perceived naturalness, mitigated it. Given that pretty food styling can harm consumers by misleading healthiness judgments for unhealthy foods, managers and policy makers should consider modification disclaimers as a tool to mitigate the “pretty = healthy” bias.

Yuzhe Yang, Liwu Xu, Leida Li et al.

Personalized image aesthetics assessment (PIAA) is challenging due to its highly subjective nature. People's aesthetic tastes depend on diversified factors, including image characteristics and subject characters. The existing PIAA databases are limited in terms of annotation diversity, especially the subject aspect, which can no longer meet the increasing demands of PIAA research. To solve the dilemma, we conduct so far, the most comprehensive subjective study of personalized image aesthetics and introduce a new Personalized image Aesthetics database with Rich Attributes (PARA), which consists of 31,220 images with annotations by 438 subjects. PARA features wealthy annotations, including 9 image-oriented objective attributes and 4 human-oriented subjective attributes. In addition, desensitized subject information, such as personality traits, is also provided to support study of PIAA and user portraits. A comprehensive analysis of the annotation data is provided and statistic study indicates that the aesthetic preferences can be mirrored by proposed subjective attributes. We also propose a conditional PIAA model by utilizing subject information as conditional prior. Experimental results indicate that the conditional PIAA model can outperform the control group, which is also the first attempt to demonstrate how image aesthetics and subject characters interact to produce the intricate personalized tastes on image aesthetics. We believe the database and the associated analysis would be useful for conducting next-generation PIAA study. The project page of PARA can be found at: https://cv-datasets.institutecv.com/#/data-sets.

Leida Li, Hancheng Zhu, Sicheng Zhao et al.

Traditional image aesthetics assessment (IAA) approaches mainly predict the average aesthetic score of an image. However, people tend to have different tastes on image aesthetics, which is mainly determined by their subjective preferences. As an important subjective trait, personality is believed to be a key factor in modeling individual’s subjective preference. In this paper, we present a personality-assisted multi-task deep learning framework for both generic and personalized image aesthetics assessment. The proposed framework comprises two stages. In the first stage, a multi-task learning network with shared weights is proposed to predict the aesthetics distribution of an image and Big-Five (BF) personality traits of people who like the image. The generic aesthetics score of the image can be generated based on the predicted aesthetics distribution. In order to capture the common representation of generic image aesthetics and people’s personality traits, a Siamese network is trained using aesthetics data and personality data jointly. In the second stage, based on the predicted personality traits and generic aesthetics of an image, an inter-task fusion is introduced to generate individual’s personalized aesthetic scores on the image. The performance of the proposed method is evaluated using two public image aesthetics databases. The experimental results demonstrate that the proposed method outperforms the state-of-the-arts in both generic and personalized IAA tasks.

Hancheng Zhu, Yong Zhou, Leida Li et al.

Due to the widespread popularity of social media, researchers have developed a strong interest in learning the personalized image aesthetics of online users. Personalized image aesthetics assessment (PIAA) aims to study the aesthetic preferences of individual users for images, which should be affected by the properties of both users and images. Existing PIAA approaches usually use the generic aesthetics learned from images as a prior model and adapt it to PIAA models through a small number of data annotated by individual users. However, the prior model merely learns the objective attributes of images, which is agnostic to the subjective attributes of users, complicating efficient learning of the personalized image aesthetics of individual users. Therefore, we propose a personalized image aesthetics assessment method that integrates the subjective attributes of users and objective attributes of images simultaneously. To characterize these two attributes jointly, an attribute extraction module is introduced to learn users’ personality traits and image aesthetic attributes. Then, an aesthetic prior model is built from numerous individual users’ annotated data, which leverages the personality traits of users and the aesthetic attributes of rated images as prior knowledge to model both the image aesthetic distribution and users’ residual scores relative to generic aesthetics simultaneously. Finally, a PIAA model is obtained by fine-tuning the aesthetic prior model with an individual user’s annotated data. Experiments demonstrate that the proposed method is superior to existing PIAA methods in learning individual users’ personalized image aesthetics.

Xiangfei Sheng, Leida Li, Pengfei Chen et al.

Image aesthetics assessment (IAA) aims at predicting the aesthetic quality of images. Recently, large pre-trained vision-language models, like CLIP, have shown impressive performances on various visual tasks. When it comes to IAA, a straightforward way is to finetune the CLIP image encoder using aesthetic images. However, this can only achieve limited success without considering the uniqueness of multimodal data in the aesthetics domain. People usually assess image aesthetics according to fine-grained visual attributes, e.g., color, light and composition. However, how to learn aesthetics-aware attributes from CLIP-based semantic space has not been addressed before. With this motivation, this paper presents a CLIP-based multi-attribute contrastive learning framework for IAA, dubbed AesCLIP. Specifically, AesCLIP consists of two major components, i.e., aesthetic attribute-based comment classification and attribute-aware learning. The former classifies the aesthetic comments into different attribute categories. Then the latter learns an aesthetic attribute-aware representation by contrastive learning, aiming to mitigate the domain shift from the general visual domain to the aesthetics domain. Extensive experiments have been done by using the pre-trained AesCLIP on four popular IAA databases, and the results demonstrate the advantage of AesCLIP over the state-of-the-arts. The source code will be public at https://github.com/OPPOMKLab/AesCLIP.

Yuzhen Niu, Shan-Ling Chen, B. Song et al.

Existing image aesthetics assessment methods mainly rely on the visual features of images but ignore their rich semantics. Nowadays, with the widespread application of social media, the comments corresponding to images in the form of texts can be easily accessed and provide rich semantic information, which can be utilized to effectively complement image features. This paper proposes a comment-guided semantics-aware image aesthetics assessment method, which is built upon a multi-task learning framework for image aesthetics prediction and comment-guided semantics classification. To assist image aesthetics assessment, we first model the semantics of an image as the topic features of its corresponding comments using Latent Dirichlet Allocation. We then propose a two-stream multitask learning framework for both topic feature prediction and aesthetic score distribution prediction. Topic feature prediction task enables to infer the semantics from images, since the comments are usually unavailable during inference and comment-guided semantics can only serve as supervision during training. We further propose to deeply fuse aesthetics and semantic features using a layerwise feature fusion method. Experimental results demonstrate that the proposed method outperforms state-of-the-art image aesthetics assessment methods.

Sergey Troitskiy, Emil Babaev, Elizaveta Belova et al.

The study, conducted in March 2022, involved the analysis of the content in several social media chats and groups; the participants of those chats live in the same place and therefore have a common experience of the space. The study was based on the hypothesis of a direct connection between the mental map (a system of individual ideas about space), the cultural reputation of topoi, and urban trauma, embodied in the unease infrastructure. The problem of assessing the significance of a place was solved by means of folklore toponymies – the mechanism of renaming, which indicates the degree of awareness about a specific place and defines its location on the mental map as well as ascribes a certain status to it. These statuses demonstrate the degree of significance of a place for a certain subject and form a kind of hierarchy, a system of topographical preferences. Thanks to online communication, people can not only transmit information much faster than the traditional forms of folklore dissemination allow, but also broadcast personal attitudes, conveying them as a bundle of meanings (for example, while inventing new toponyms). Therefore, one of the objectives of the study was to identify established folklore toponyms in online communication: they serve as markers of attitudes, reputation, and significance; we also try to catalogue attempts to “rename” different places. Another task was to find the symptoms of such anxiety in online communication.

Juan Manuel Lozano de Poo

La interacción social se ha transformado significativamente por la omnipresencia en el hogar de dispositivos portátiles conectados a la red. Las plataformas digitales son parte de la vida doméstica y abarcan prácticamente el espectro completo de la actividad humana. Los cambios y las permanencias en las formas de habitar dan cuenta del fenómeno de la digitalización y las implicaciones que tienen las formas de comunicación impuestas en la era de la información sobre las personas. Este trabajo explora la producción y reproducción de nuevos patrones de interacción y modos de habitar desde lo privado, bajo una multiplicidad intergeneracional de conformaciones familiares (solteros, nido completo, nido vacío y madres/padres solteros) que se encuentran en las tres etapas del ciclo de la vida. Los nuevos usos y organizaciones espaciotemporales en el hogar digitalizado están resignificando las dimensiones de corporeidad y contigüidad; ambas cualidades constitutivas para el cuidado del ser y la existencia humana. Como consecuencia, las alteraciones en la proximidad y el aislamiento entre los seres humanos producto de la digitalización exhiben una domesticidad supeditada a la interacción ciberfísica acrítica en el habitar de la tercera década de siglo XXI.

Vlad Hosu, Bastian Goldlücke, D. Saupe

We propose an effective deep learning approach to aesthetics quality assessment that relies on a new type of pre-trained features, and apply it to the AVA data set, the currently largest aesthetics database. While previous approaches miss some of the information in the original images, due to taking small crops, down-scaling or warping the originals during training, we propose the first method that efficiently supports full resolution images as an input, and can be trained on variable input sizes. This allows us to significantly improve upon the state of the art, increasing the Spearman rank-order correlation coefficient (SRCC) of ground-truth mean opinion scores (MOS) from the existing best reported of 0.612 to 0.756. To achieve this performance, we extract multi-level spatially pooled (MLSP) features from all convolutional blocks of a pre-trained InceptionResNet-v2 network, and train a custom shallow Convolutional Neural Network (CNN) architecture on these new features.

S. Perrig, David Ueffing, K. Opwis et al.

Past research has demonstrated that aesthetics affect users' experiences in various ways. However, there is little research on the impact of interface aesthetics on user performance in a smartphone app context. The present paper addresses this research gap using an online experiment (N = 281). Two variants of the same web app were created and manipulated in their aesthetics. Participants were randomly assigned to either variant and asked to explore the app before answering questions concerning the app's content. Results showed a significant positive effect of aesthetics on perceived usability and aesthetics. Furthermore, results point toward a positive impact of interface aesthetics on performance (i.e., the number of questions answered correctly). Thus, results indicate that a visually appealing smartphone web app increases users' subjective experience and objective performance compared to an unaesthetic app. This suggests that user interface aesthetics impact users' experiences and provide stakeholders with quantifiable value and competitive advantage.

Wei Yang, Qiuxia Chen, Xiaoting Huang et al.

As heritage is the precious treasure of human society, heritage also carries the genes of culture. It is of vital importance to effectively develop heritage tourism resources and explore the mechanisms that influence tourists’ cultural identity. This study has integrated the stimulus-organism-response (SOR) framework with the attitude-behavior-context (ABC) theory to construct a hypothetical model of heritage tourism aesthetics, tourist involvement, mental experience, and cultural identity so as to figure out their relationships. The questionnaires were collected to investigate the impact paths and mechanisms between heritage aesthetics, tourist involvement, mental experience, and cultural identity. The structural equation model was used to examine the relationship between heritage tourism aesthetics, tourist involvement, mental experience, and cultural identity. The main findings include: (1) the positive impact of aesthetics driving mental experience and cultural identity is significant; (2) the impact of tourist involvement on mental experience and cultural identity is also significant; (3) the impact of aesthetics on cultural identity is not significant, but mental experience mediates the relationship between aesthetics and cultural identity in heritage tourism. This study provides a new research framework and perspective for the aesthetics, tourist involvement, mental experience, and cultural identity of tourists in heritage tourism. This study also provides practical implications for government culture sectors to propagandize culture and for heritage destination managers to better manage heritage sites.