Aesthetic Labels Research Articles

The Old Dream of Legendary Shanghai

The film “Song of Eternal Sorrow” derives from an adaptation of the classic novel with the identical title by Wang Anyi. Director Guan Jinpeng developed an individual history that parallels the course of Chinese history, with the route and destination of the characters exiled from Shanghai to Hong Kong and then dispersed from Hong Kong to the other parts of the world, the implicit narrative of Hong Kong in the shift of the main perspective, as well as the characteristics of the female narrative, all of which constitute a dynamic and multi-perspective perspective of Shanghai. With regard to environmental styling, the film places great emphasis on integrating the urban culture of Shanghai by means of scene design and prop design, such as the settings of the alleyway, the film set, as well as the Shanghai Apartments. With regard to character styling, the cheongsam, which serves as the aesthetic label for Shanghai females, is the core and highlight of the clothing design of the film. The variations in texture, color, pattern and style of the cheongsam tends to underline the variations in personality and the transformation of fate and mentality of the characters.

Distilling Knowledge From Object Classification to Aesthetics Assessment

In this work, we point out that the major dilemma of image aesthetics assessment (IAA) comes from the abstract nature of aesthetic labels. That is, a vast variety of distinct contents can correspond to the same aesthetic label. On the one hand, during inference, the IAA model is required to relate various distinct contents to the same aesthetic label. On the other hand, when training, it would be hard for the IAA model to learn to distinguish different contents merely with the supervision from aesthetic labels, since aesthetic labels are not directly related to any specific content. To deal with this dilemma, we propose to distill knowledge on semantic patterns for a vast variety of image contents from multiple pre-trained object classification (POC) models to an IAA model. Expecting the combination of multiple POC models can provide sufficient knowledge on various image contents, the IAA model can easier learn to relate various distinct contents to a limited number of aesthetic labels. By supervising an end-to-end single-backbone IAA model with the distilled knowledge, the performance of the IAA model is significantly improved by 4.8% in SRCC compared to the version trained only with ground-truth aesthetic labels. On specific categories of images, the SRCC improvement brought by the proposed method can achieve up to 7.2%. Peer comparison also shows that our method outperforms 10 previous IAA methods.

Reviewing strategies and the normalization of uncertain texts

Reviewers help ease cultural products’ testing transition from the stage of production to that of circulation. Given their intermediate position between stages, reviewers have to deal with uncertainty when valuating new cultural products. How do reviewers in a transnational setting make sense of a novel product that challenges existing aesthetic boundaries, has commercial success, and is made by a little-known creator? Along with the strategies of description, accommodation, and rejection, this paper argues that reviewers’ most effective, long-term strategy to normalize the uncertainty of a brand-new product is to come up with an aesthetic label for it, either by rescuing one (recycling) or by proposing a new one (neo-labeling). These two strategies of resignification help to normalize the product’s aesthetic uncertainty. This paper studies reviewers’ initial valuation of the novel One Hundred Years of Solitude. They applied the above-mentioned strategies to read the text, especially as they could not agree on its aesthetics. A key strategy consisted in recycling the little-known label magical realism. In the long-run, magical realism turned into the normal label applied to the novel worldwide. This paper offers insights into actors’ perception of uncertain cultural products and the standardization of heterogeneous interpretations of such products.

Learning to assess visual aesthetics of food images

Distinguishing aesthetically pleasing food photos from others is an important visual analysis task for social media and ranking systems related to food. Nevertheless, aesthetic assessment of food images remains a challenging and relatively unexplored task, largely due to the lack of related food image datasets and practical knowledge. Thus, we present the Gourmet Photography Dataset (GPD), the first large-scale dataset for aesthetic assessment of food photos. It contains 24,000 images with corresponding binary aesthetic labels, covering a large variety of foods and scenes. We also provide a non-stationary regularization method to combat over-fitting and enhance the ability of tuned models to generalize. Quantitative results from extensive experiments, including a generalization ability test, verify that neural networks trained on the GPD achieve comparable performance to human experts on the task of aesthetic assessment. We reveal several valuable findings to support further research and applications related to visual aesthetic analysis of food images. To encourage further research, we have made the GPD publicly available at https://github.com/Openning07/GPA.

Aesthetic Labeling and Scale Shifting in Cultural Production and Circulation

Abstract Scholarship on production of cultural goods highlights translation of literary works as a key mechanism of cultural circulation. This article rethinks circulation beyond translation. It argues that changes in aesthetic labels applied to cultural goods can prompt a scale shifting that favors the diffusion of these goods beyond their vernacular space of circulation. This article studies the transnational success of the label literatura latinoamericana, which from the 1960s onward gained acceptance in Spanish, English, French, and other languages as the label that best captured the region’s literary uniqueness. This change in aesthetic labeling made it possible for literatura latinoamericana to enter world literature and for literary works such as One Hundred Years of Solitude to circulate at an unprecedented scale, as international bestsellers and classics. The article finds that aesthetic labeling – a “cultural kind” in the arts – is a far-reaching and understudied mechanism in cultural production and circulation.

Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning

Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both aesthetic labels and related image attributes. In this paper, we revisit the problem of image aesthetic assessment from the self-supervised feature learning perspective. Our motivation is that a suitable feature representation for image aesthetic assessment should be able to distinguish different expert-designed image manipulations, which have close relationships with negative aesthetic effects. To this end, we design two novel pretext tasks to identify the types and parameters of editing operations applied to synthetic instances. The features from our pretext tasks are then adapted for a one-layer linear classifier to evaluate the performance in terms of binary aesthetic classification. We conduct extensive quantitative experiments on three benchmark datasets and demonstrate that our approach can faithfully extract aesthetics-aware features and outperform alternative pretext schemes. Moreover, we achieve comparable results to state-of-the-art supervised methods that use 10 million labels from ImageNet.

A Unified Probabilistic Formulation of Image Aesthetic Assessment.

Image aesthetic assessment (IAA) has been attracting considerable attention in recent years due to the explosive growth of digital photography in Internet and social networks. The IAA problem is inherently challenging, owning to the ineffable nature of the human sense of aesthetics and beauty, and its close relationship to understanding pictorial content. Three different approaches to framing and solving the problem have been posed: binary classification, average score regression and score distribution prediction. Solutions that have been proposed have utilized different types of aesthetic labels and loss functions to train deep IAA models. However, these studies ignore the fact that the three different IAA tasks are inherently related. Here, we reveal that the use of the different types of aesthetic labels can be developed within the same statistical framework, which we use to create a unified probabilistic formulation of all the three IAA tasks. This unified formulation motivates the use of an efficient and effective loss function for training deep IAA models to conduct different tasks. We also discuss the problem of learning from a noisy raw score distribution which hinders network performance. We then show that by fitting the raw score distribution to a more stable and discriminative score distribution, we are able to train a single model which is able to obtain highly competitive performance on all three IAA tasks. Extensive qualitative analysis and experimental results on image aesthetic benchmarks validate the superior performance afforded by the proposed formulation. The source code is available at.

Distribution-Oriented Aesthetics Assessment With Semantic-Aware Hybrid Network

Image aesthetics assessment has emerged as a hot topic in recent years due to its potential in numerous high-level vision applications. In this paper, distinguished from existing studies relying on a single label, we propose quantifying image aesthetics by a distribution over multiple quality levels. The distribution-based representation characterizes the disagreement among users’ aesthetic preferences regarding the same image, and is also compatible with the traditional task of aesthetic label prediction. Our framework is developed based on fully convolutional networks and enables inputs of varying sizes. In this way, we circumvent the fixed-size constraint of prevalent convolutional neural networks, and avoid the risk of impairing the intrinsic aesthetic appeal of images. Moreover, given the fact that aesthetic perceiving is coupled with semantic understanding, we present a novel semantic-aware hybrid NEtwork (SANE), which harvests the information from object categorization and scene recognition to enhance image aesthetics assessment. Experiments on two benchmark datasets have well verified the effectiveness of our approach in both scenarios of aesthetic distribution prediction and aesthetic label prediction, and highlighted the benefits of input preserving as well as semantic understanding for images.

Arte contemporânea: do que se trata? Notas feitas através da leitura do livro “The contingente object of contemporary art” de Martha Buskirk

O que designa exatamente aquilo que chamamos de “arte contemporânea” nos dias atuais? Essa expressão é um rótulo estético, um estilo, um gênero, um período histórico ou o quê? A respeito de certos artistas argumentarem que faz arte contemporânea aquele que produz arte no seu tempo presente, este texto busca deslindar a complexidade de questões sobre este “paradigma” artístico através da leitura do livro The contingent object of contemporary art de Martha Buskirk. A autora, além da problematização sobre a contingência do objeto, traz questões acerca da autoria, originalidade e inserção dos novos modos de produção e fruição no mundo da arte. Palavras-chave: arte contemporânea, autoria, obra de arte

Melville and Aesthetics ed. by Samuel Otter and Geoffrey Sanborn (review)

Reviewed by: Melville and Aesthetics ed. by Samuel Otter and Geoffrey Sanborn Dennis Berthold SAMUEL OTTER AND GEOFFREY SANBORN, EDS. Melville and Aesthetics New York: Palgrave Macmillan, 2011. viii + 263 pp. In a searching and provocative introduction, Samuel Otter and Geoffrey Sanborn articulate the grand motive behind this important collection of twelve essays—”to move beyond the false choices that have bedeviled the profession: form or history, practical criticism or theory, aesthetics or politics” (6). “Literature is,” they continue, “neither a strictly political nor a strictly aesthetic affair. Instead (to rework a passage from chapter 93 of Mardi), literature poses questions that are more final than any answers” (6). The stylistic richness of Melville’s writing; his constant reinvention of narrative, point of view, and structure; his daring use of allusion, metaphor, image, and symbol; his experiments in meter, rhyme, and assonance—in short, his “acute sensitivity to the writtenness of all writing—make him a richly suggestive figure” (5) for re-emphasizing aesthetics as a major preoccupation of literary study that can “stand alongside—not displace—the ideological approach” (3). Clearly, Otter and Sanborn are after a big fish, and see Melville as the pilot who will guide them to it. The craft they ride on is both vehicle and tenor of their quest, and the varied critical methodologies in each essay give them plenty of sea-room to pursue it. Deliberately emphasizing diverse perspectives not only on Melville but also on the definition of aesthetic criticism itself, the editors seek to foster a “multiplicitous particularity” (3) of views to illuminate the aesthetic richness and ideational complexity of Melville’s writing. The editors fashion an ensemble of twelve scholars whose voices mix the cadences of historical, linguistic, poststructuralist, transnational, biographical, and queer criticism with the demands of formalist analysis and close reading. Although the book has no titled subdivisions, the introduction points out that the first three essays discuss “The Matter of Style,” while the next nine function as “Case Studies” of particular works: three on Moby-Dick; a cluster of four on Pierre, “Bartleby,” Israel Potter, and The Confidence-Man; and two on Battle-Pieces and Clarel. Alex Calder opens the collection with a metacritical overview of the charge that Melville is a bad writer, an objection familiar to anyone who has read the [End Page 75] contemporary reviews of Mardi, Moby-Dick, or Pierre. Rather than mounting a defense against such critique, Calder recognizes “that Melville had a genius for striking a wrong note” (30) as in “The Bell Tower” (one must forgive Calder the pun), yet such ostensible missteps often gave him the artistic freedom to vitalize and deepen his texts. Calder describes how New Critic R. P. Blackmur, in his 1938 essay on “The Craft of Herman Melville,” codified Melville’s bad writing under the rubric of “putative form,” an artificial, stagy, non-dramatic method of writing that undermines the sincerity of Melville’s philosophical skepticism and that drove generations of Melville critics to focus on theme and ideology rather than style. Warner Berthoff, in The Example of Melville (1962), countered Blackmur’s attack by approaching Melville through organicism, the romantic aesthetic that valorizes excess, disorder, invention, subjectivity, plurality, and creative liberty. These schools of thought, Calder argues, polarize Melville’s narratives at the extremes of Chekhovian drama for Blackmur and gothic romance for Berthoff, ignoring the tradition of Rabelais, Cervantes, and Sterne—or what Calder calls “modal discontinuity” (27), a term drawn from the behaviorist aesthetics of Morse Peckham, who considered Clarel Melville’s finest work save Moby-Dick. Still, for Calder, no single aesthetic label can capture the dialogic richness and generic variety of Melville’s textual practice, and if his writing is sometimes “bad,” it nonetheless provided him a “psychic insulation” (31) from literary norms and liberated his stylistic genius. Theo Davis reinforces Calder’s critique of New Critical aesthetics by praising Melville’s ornamental metaphors: the excessive, “errant, possibly irrelevant” comparisons and elaborations that give pleasure even as they digress from a perceptible narrative trajectory (34). Davis explains that such departures from formal unity troubled W. K. Wimsatt, as they had the eighteenth-century rhetorician Hugh Blair, and both Friedrich von...