佐々木 史織

An imagination-based image search system is a new environment to acquire unknown but desired images by queries, which reflects user's dynamic imagination process. It leads to a new computation environment for searching images data resources in a contextual way. This paper presents a dynamic image-query creation method for imagination-based image search system and its application for travel information associated with scenery images. The main feature of our system is to extend analytical functions for image search, not only in retrieval processing, but also in query manipulation, according to the color-based combination of images with common features. A query creation method in this system is a novel approach to represent a user's imagination process. This method enables a user to create dynamically a query, which reflects the user's intention, impression and memory as his/her own context existing only his/her mind by color-based combinations of existent images in the real world. The proposed method consists of five operations for creating image-query vector from combinations of images, which are "plus", "intersection", "accumulation", as local operations and "minus" and "difference" as global operations. Using the imagination-based image search system for travel information associated with scenery images, users can easily discover images and information of places where they never been. The system performs a series of qualitative and quantitative experiments to examine the feasibility, effectiveness of proposed method and scalability of the system.

Cultural computing is an emerging field of multidisciplinary computer science. In the near future, cultural computing will have several important applications in the fields of business, knowledge society, environmental issues, health care, education and research. Our paper is written in collaboration with the authors, who are also participants in the collaborative research project "Ubiquitous Cross-Cultural Multimedia Systems for Mobile Computing Societies/Ubiquitous Cross-Cultural Knowledge Space". The issues discussed in our paper cover background knowledge related to cultural computing, general discussion of culture as a concept, an introduction to the concept and basic design of the Electronic Assistant for Cross-Cultural Communication, and an introduction to the design and implementation of the 3D Cross-Cultural Multimedia Museum" system and its applications. The 3D Cross-Cultural Multimedia Museum has been implemented as a prototype system of Cross-Cultural Cyber Space. The global changes caused not only by scientific and technological development, but by environmental issues as well, are our driving forces towards the era of cultural computing. Our paper is based on the presentations of the panel discussion at the EJC 2009 Conference.

Virtual communities rely primarily on ICT to connect their members to work together, and to share knowledge and practices. The importance of virtual collaborative work is increasing not only because of its economical and environmental benefits, but also due to its flexibility for establishing dynamically new cross-organizational and cross-cultural innovative teams. Virtual collaborative spaces should support their joint activities. In order to design and realize such spaces, an understanding of the tasks to be carried out by the virtual community is necessary, as well as an understanding of the related processes, contexts, and knowledge. In our paper, we introduce a reference model of a Cross-Cultural Cyber Space (CCS) for context-based knowledge creation and sharing between the members of the cross-cultural collaborative community. We also describe the prototype implementation of the CCS, a 3D cross-cultural art museum system.

This paper presents a design and implementation for the "4D World Map System," a knowledge representation system which enables semantic, temporal and spatial analysis of documents, and integrates and visualizes the analyzed results as a 4-dimentional dynamic historical atlas (4D World Map Set). The main feature of this system is to create various context-dependent patterns of historical/cultural stories according to a user's viewpoints dynamically. This system generates multiple views of semantic and temporal-spatial relationships among documents of the humanities and social sciences. This system organizes the relationships among documents into various historical/cultural stories by a user's viewpoints. A semantic associative search method is applied to this system for realizing the concept that "semantics" of words, documents, and events vary according to the "context". Semantically-evaluated and analyzed document data are also mapped dynamically onto a time-series multi-geographical space. This system provides high visibility of semantic correlations between documents in time series variation with geographic information. In this paper, we also show several experiments by using news articles and International Relations documents to clarify the feasibility of the system.

Cultural computing is an emerging field of multidisciplinary computer science. In the near future, cultural computing will have several important applications in the fields of business, knowledge society, environmental issues, health care, education and research. Our paper is written in collaboration with the authors, who are also participants in the collaborative research project "Ubiquitous Cross-Cultural Multimedia Systems for Mobile Computing Societies/Ubiquitous Cross-Cultural Knowledge Space". The issues discussed in our paper cover background knowledge related to cultural computing, general discussion of culture as a concept, an introduction to the concept and basic design of the Electronic Assistant for Cross-Cultural Communication, and an introduction to the design and implementation of the 3D Cross-Cultural Multimedia Museum" system and its applications. The 3D Cross-Cultural Multimedia Museum has been implemented as a prototype system of Cross-Cultural Cyber Space. The global changes caused not only by scientific and technological development, but by environmental issues as well, are our driving forces towards the era of cultural computing. Our paper is based on the presentations of the panel discussion at the EJC 2009 Conference.

Virtual communities rely primarily on ICT to connect their members to work together, and to share knowledge and practices. The importance of virtual collaborative work is increasing not only because of its economical and environmental benefits, but also due to its flexibility for establishing dynamically new cross-organizational and cross-cultural innovative teams. Virtual collaborative spaces should support their joint activities. In order to design and realize such spaces, an understanding of the tasks to be carried out by the virtual community is necessary, as well as an understanding of the related processes, contexts, and knowledge. In our paper, we introduce a reference model of a Cross-Cultural Cyber Space (CCS) for context-based knowledge creation and sharing between the members of the cross-cultural collaborative community. We also describe the prototype implementation of the CCS, a 3D cross-cultural art museum system.

This paper presents a dynamic image-query creation and metadata extraction method with semantic correlation computation between color-combinations and impressions of multiple image data. The main features of our method are (1) to create an image-query which reflects user's intention dynamically according to the color-based combinations of images with common features selected by a user as context, (2) to extract appropriate impression by each image collection which cannot be easily extracted from a single image, (3) to provide users an image retrieval environment reflecting historical and cultural semantics and impression of color especially for cultural properties, and (4) to enable an image retrieval environment for the collection of images by time, culture, author e.t.c.. The queries are created by the combination of multiple image sets and operations, which are intersection, accumulation, average, difference of color elements of sample images. First, a set of multiple images with common features is set as sample data for a query creation. Second, color histograms are extracted from the image sets for creating feature vector of a query. Third, the correlations between an image-query vector and target image vectors are calculated on a space which represents the relationship between color and the impression according to historical and cultural semantics of color. This image-query creation method representing impression of color makes it possible to expand the range of image retrieval for a large number of image data of cultural property in digital archives, such as electronic library and electronic museum, automatically. © 2009 The authors and IOS Press.

In this paper, we present an implementation method of continuous media data rendering system to visualize a psychological impression-transition continuously. The important feature of this method is to realize visualization of psychological impress ion-transition by realizing the following steps: 1) creating impression-vector-space to calculate the correlation value between the media data and the query words, 2) creating databases by the psychological impress ion-transition methods, such as color psychology and music psychology, 3) converting the into query words the words on the impression-transition-wordspace, 4) selecting the starting and terminal points given by a user and ranking the media data according to the route, the user's context. From the viewpoint of visualization, it is interesting to use this system for representing impression-transition by applying psychological models related to media data, such as color and music. With a continuous rendering system for color data, we have performed several experiments to clarify the feasibility of our method to visualize continuous impression-transition change.

In this paper, we present a goal-oriented language teaming system which assists autonomous foreign language learning. The aim of our research is constructing a system which enables automatic provision of contents on the Internet as teaming materials for foreign language learners, according to each learner's studying purpose, language proficiency and area of interest as "Study Context". The system consists of four functions: (I) Study Context Extractor which extracts each user's study context by using the input of sample contents that the user considers to reflect their situation in terms of language levels and areas of interest, (2) Automatic Metadata Generator which generates metadata of contents on the Internet, (3) Learning Level Filter which selects contents by assessing the language proficiency level and target language level of the user, and (4) Semantic Information Filter which provides learning materials according to the user's area of interest or discipline. By using our system, with only the input of sample contents (texts) as the indication of user's present proficiency, target language level and study purposes, users can automatically acquire learning materials which accord with their purpose for studying, language proficiency and area of interest. In this paper, we also present an implementation method of our goal-oriented language learning system and experimental results to clarify the feasibility and effectiveness.

In this paper, we present a new creation method of a semantic retrieval space for a specialized field of study, especially for the field of International Relations (IR), and new evaluation criteria for verifying practical effectiveness of the created space. This space creation method needs only a general dictionary and a lexicon of the technical terms for a specific field. Using the newly created space, we realized semantic associative search for documents which include various technical terms with general words, and also documents which include general words with technical terms. Furthermore, to verify practical effectiveness of the space creation method, that is, how much knowledge we can acquire from the created space newly, we present some evaluation criteria besides precision and recall