No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Implementation of Dynamic Art Curation Engine in Global Art Collection Archive
In this paper, an implementation method of GACA, Global Art Collection Archive, is proposed. Each museum maintains their own archives of art collections. GACA dynamically integrate those collection data of artworks in each museum archive and provide them with REST API. GACA works as a integrated data platform for various kinds of viewing environment of artworks such as virtual reality, physical exhibitions, smartphone applications and so on. It allows users not only to view artworks, but also to experience the creativity of artworks through seeing, feeling, and knowing them, inspiring a new era of creation.
This paper introduces Art Sensorium Project that is founded in Asia AI Institute of Musashino University. A main target of the project is to design and implement a system architecture of unified art collections for virtual art experiences. To provide art experiences, a projection-based VR system, called Data Sensorium, is used to stage art materials in a form of real-sized virtual reality. Furthermore, a system architecture of a multidatabase system for heterogeneous art collection archives is presented, so a set of integrated art data is applied to Data Sensorium for newly generated art experiences.
This paper describes about project “Data Sensorium” launched at the Asia AI Institute of Musashino University. Data Sensoriumis a conceptual framework of systems providing physical experience of content stored in database. Spatial immersive display is a key technology of Data Sensorium. This paper introduces prototype implementation of the concept and its application to environmental and architectural dataset.
In order to provide art exhibitions in a virtual space which integrates various data of an art museum and gives an emotional experience, the Virtual Art Exhibition System is proposed. This research uses a multi-database called Artizon Cloud to display museum data, combinate with technologies called Data Sensorium and Torus Treadmill to project images and enable visitors to walk around the virtual museum. Moreover, the virtual museum will exploit the users intentions and be personalized, automatically generating further art exhibitions.
In many works related to architecture, the museum is the only place to store documents and display artifacts related to the historical process, reflecting the culture of a city, a nation, or a country. However, the strength of the technological age and the consequences of war occurred as the storm destroyed the cultural identity layers. The city has also faced the abandon of past achievements in the modernization context. The relationship between conservation and development is, therefore, a controversial issue in the process of reservation art folk painting and art museums. It is still a painful problem that has not yet ended in Vietnam. An undeniable fact is that the city-county has not appropriately preserved museums and art folk paintings in Vietnam. This fact has led to the young generation in the city are not interested in visiting the museum. Among the folk paintings in Vietnam, Dong Ho paintings belong to the line of paintings printed on wood carving planks, created, produced by the villagers of Dong Ho village, and developed into craft villages. This is a line of painting that attaches and vividly shows the traditional Vietnamese agricultural society, the working life of a traditional farmer, and the daily life of the Vietnamese people. Currently, Dong Ho folk paintings are in danger of dying out due to the impact of the market economy, changes in people’s aesthetic needs, and difficulties in the output of paintings. Besides, according to a number of painters, Dong Ho paintings are no longer as innocent, simple, “pure Vietnamese” as before, but are gradually being commercialized, with no rich colors like ancient paintings. Dong Ho painting profession today exists weakly, only a few families maintain. According to recent statistics, the number of artisans is only three people, the number of practitioners is about 20, the number of artists who are still capable of teaching is only two people (Mr. Nguyen Huu Sam and Mr. Nguyen Dang Che) are all elderly (Dung 2013). With the power of Virtual Reality, we can transfer not only the architectural aspect but also revive the cultural values hidden within art folk painting to the community as the best way to preserve the culture for all next generations without sacrificing the development potential of the country. Researching on “Application of Virtual Reality to enhance the interpretation, Dong Ho folk painting of Museum of Fine Arts in Ho Chi Minh city” was chosen for that purpose.KeywordsVirtual realityMuseum of fine artsInterpretationTechnology innovationDong Ho folk painting
How does the machine classify styles in art? And how does it relate to art historians' methods for analyzing style? Several studies showed the ability of the machine to learn and predict styles, such as Renaissance, Baroque, Impressionism, etc., from images of paintings. This implies that the machine can learn an internal representation encoding discriminative features through its visual analysis. However, such a representation is not necessarily interpretable. We conducted a comprehensive study of several of the state-of-the-art convolutional neural networks applied to the task of style classification on 67K images of paintings, and analyzed the learned representation through correlation analysis with concepts derived from art history. Surprisingly, the networks could place the works of art in a smooth temporal arrangement mainly based on learning style labels, without any a priori knowledge of time of creation, the historical time and context of styles, or relations between styles. The learned representations showed that there are a few underlying factors that explain the visual variations of style in art. Some of these factors were found to correlate with style patterns suggested by Heinrich Wölfflin (1846-1945). The learned representations also consistently highlighted certain artists as the extreme distinctive representative of their styles, which quantitatively confirms art historian observations.
Technologies related to artificial intelligence (AI) have a strong impact on the changes of research and creative practices in visual arts. The growing number of research initiatives and creative applications that emerge in the intersection of AI and art motivates us to examine and discuss the creative and explorative potentials of AI technologies in the context of art. This article provides an integrated review of two facets of AI and art: (1) AI is used for art analysis and employed on digitized artwork collections, or (2) AI is used for creative purposes and generating novel artworks. In the context of AI-related research for art understanding, we present a comprehensive overview of artwork datasets and recent works that address a variety of tasks such as classification, object detection, similarity retrieval, multimodal representations, and computational aesthetics, among others. In relation to the role of AI in creating art, we address various practical and theoretical aspects of AI Art and consolidate related works that deal with those topics in detail. Finally, we provide a concise outlook on the future progression and potential impact of AI technologies on our understanding and creation of art.
For dynamically integrating professional knowledge of curators, a multidatabase system architecture for an art museum, Artizon Cloud is proposed. A location based data provision is defined in the architecture for visitors. A system and applications are implemented and provided in an actual museum, and heterogeneous archives that were independently implemented as databases with Web UIs are dynamically extracted, integrated, and staged in visitors’ devices.
Museums are interested in the digitizing of their collections not only for the sake of preserving the cultural heritage, but to also make the information content accessible to the wider public in a manner that is attractive. Emerging technologies, such as VR, AR and Web3D are widely used to create virtual museum exhibitions both in a museum environment through informative kiosks and on the World Wide Web. This paper surveys the field, and while it explores the various kinds of virtual museums in existence, it discusses the advantages and limitation involved with a presentation of old and new methods and of the tools used for their creation.
A system that allows museums to build and manage Virtual and Augmented Reality exhibitions based on 3D models of artifacts is presented. Dynamic content creation based on pre-designed visualization templates allows content designers to create virtual exhibitions very efficiently. Virtual Reality exhibitions can be presented both inside museums, e.g. on touch-screen displays installed inside galleries and, at the same time, on the Internet. Additionally, the presentation based on Augmented Reality technologies allows museum visitors to interact with the content in an intuitive and exciting manner.
With the vast expansion of digital contemporary painting collections, automatic theme stylization has grown in demand in both academic and commercial fields. The recent interest in deep neural networks has provided powerful visual features that achieve state-of-the-art results in various visual classification tasks. In this work, we examine the perceptiveness of these features in identifying artistic styles in paintings, and suggest a compact binary representation of the paintings. Combined with the PiCoDes descriptors, these features show excellent classification results on a large scale collection of paintings.
In this paper we describe the problem of painter classification, and propose a novel approach based on deep convolutional autoencoder neural networks. While previous approaches relied on image processing and manual feature extraction from paintings, our approach operates on the raw pixel level, without any preprocessing or manual feature extraction. We first train a deep convolutional autoencoder on a dataset of paintings, and subsequently use it to initialize a supervised convolutional neural network for the classification phase.
The proposed approach substantially outperforms previous methods, improving the previous state-of-the-art for the 3-painter classification problem from 90.44 % accuracy (previous state-of-the-art) to 96.52 % accuracy, i.e., a 63 % reduction in error rate.
The objective of this work is to find objects in paintings by learning object-category classifiers from available sources of natural images. Finding such objects is of much benefit to the art history community as well as being a challenging problem in large-scale retrieval and domain adaptation.
We make the following contributions: (i) we show that object classifiers, learnt using Convolutional Neural Networks (CNNs) features computed from various natural image sources, can retrieve paintings containing these objects with great success; (ii) we develop a system that can learn object classifiers on-the-fly from Google images and use these to find a large variety of previously unfound objects in a dataset of 210,000 paintings; (iii) we combine object classifiers and detectors to align objects to allow for direct comparison; for example to illustrate how they have varied over time.
Deeper neural networks are more difficult to train. We present a residual
learning framework to ease the training of networks that are substantially
deeper than those used previously. We explicitly reformulate the layers as
learning residual functions with reference to the layer inputs, instead of
learning unreferenced functions. We provide comprehensive empirical evidence
showing that these residual networks are easier to optimize, and can gain
accuracy from considerably increased depth. On the ImageNet dataset we evaluate
residual nets with a depth of up to 152 layers---8x deeper than VGG nets but
still having lower complexity. An ensemble of these residual nets achieves
3.57% error on the ImageNet test set. This result won the 1st place on the
ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100
and 1000 layers.
The depth of representations is of central importance for many visual
recognition tasks. Solely due to our extremely deep representations, we obtain
a 28% relative improvement on the COCO object detection dataset. Deep residual
nets are foundations of our submissions to ILSVRC & COCO 2015 competitions,
where we also won the 1st places on the tasks of ImageNet detection, ImageNet
localization, COCO detection, and COCO segmentation.
Van Gogh - This is how I see the world
- Kadokawa Musashino Museum
Dynamic Art Curation Method with Pretrained Models of Art Interpretation
- Tsuchiya
Paris Musées: Les collections en ligne des musées de la Ville de Paris
- Paris Musées
New technologies and tools for immersive and engaging visitor experiences in museums
- D Pantile
- R Frasca
- A Mazzeo
- M Ventralla
- G Verreschi
Dynamic Art Curation Method with Pretrained Models of Art Interpretation
- Y Tsuchiya
- N Nakanishi
- N Ishibashi