Top > Research > Digital Content and Media Sciences Research Division

Digital Content and Media Sciences Research Division


The Division conducts research on various types of contents and media such as text and video in terms of analysis, creation, compilation and application, and their processing methods from the theories to the systems.

Foundations of Content Management


Aiming to increase the convenience of web services

The advent of the Internet has enabled us to use services that let us find the route to our destination and book airplane tickets, hotels and rental cars, all without getting up. Such services are scattered around the Internet and we search for them one by one. Would it not be more convenient if a computer could combine different services and provide us with one service that meets our needs? My research goa l is building a society in which we can enjoy services like these.

Using digital watermarking technology to prevent unauthorized use of digital content

These days we can enjoy digital content such as photos, videos and music via our cell phones and PCs whenever and wherever we want. As digital content becomes easier to copy, process and distribute than analog content such as movies and printed materials, anyone can casually create and distribute content to the world. On the other side of this coin is that it is also easy to copy, process and distribute content illegally, so there is an underlying risk of infringing on the rights of content creators or those involved in distribution. I am studying the technology called digital watermarking and the system technologies for making copyright protection and distribution control of the content easier in order to protect the rights to digital content and make distribution operate more smoothly.

Extracting knowledge from large-scale multimedia database

If large volumes of accumulated video and audio recordings could be utilized more effectively, they would be able to serve as useful resources for the development of computer vision and robotics technologies. My research goal is to achieve high-speed, flexible processing of large-scale multimedia databases of videos and audio recordings.

Using the information space formed by networks
KATO Hiroyuki

Information helps us in various situations and gives us various advantages. But for maximum usefulness, information has to be easy to use. Databases are designed with this in mind. In databases, the information collected is neatly organized for specific purposes. The advent of the Internet has brought dramatic changes to databases. Now we can build huge databases capable of providing the necessary information, unconstrained by time or distance, merely by connecting a number of databases in different locations around the world.The databases in actual use are pretty diverse. It's not practical or realistic to expect all databases to use the same format. The solution to this problem is a language called XQuery. It's one of my research interests.

Extract useful information from vast data constellations
TAKASU Atsuhiro

In today's information-oriented society, various data are collected and accumulated everyday around the world. It is meaningless to keep collecting data unless we utilize them through analysis and interpretation. In reality, however, the amount of data is too great and exceeds the processing capacity of humans. Since there is a limit on how we can improve our capacity, we need some sort of mechanism to assist this capacity. My research seeks to build a society in which we can extract useful information from these enormous data constellations and in doing so, accumulate mankind's information and knowledge.

Information services that broaden the mind and lead to profound thought
TAKANO Akihiko

Has the spread of the Internet improved society? The abundance of unreliable information and slanderous messages written anonymously sometimes lead to problems. Yet the Internet also provides great amounts of valuable and useful content. As someone involved in information technology, I am aiming to provide information services that broaden the mind and lead to profound thought while helping the search for reliable information.

Publicizing academic information effectively using the Internet
YAMAJI Kazutsuna

Researchers currently have extremely limited opportunities to publicize their research results since they normally do so only at academic conferences or in print form. Moreover, as the number of published papers and number of times papers are cited are often used as an index of their performance, only figures are emphasized in evaluating such performance, which is essentially unfair. Now that the Internet has made rapid progress and come to offer a range of uses, researchers can publicize their research results more efficiently. In my research, I am trying to create new academic media particularly for younger researchers to publicize their results and materials in sequence on the Internet so they can enjoy the benefits of the effects generated by publication.


Text and Language Media


Creating knowledge from language text

Language is an essential tool for humans. It is indispensable for communicating with each other and for leaving records. In other words, analyzing how a language is used allows us to observe human activity. This point is especially intriguing for me. I intend to extract knowledge from language text (simply, text), which is text written using a computer.

Serving as a compass in a chaotic sea of information

The amount of information surrounding us today has been increasing exponentially. This situation is called an "information explosion." Yet although the amount of knowledge owned by humans has also exploded, our information processing capacity has remained limited and has scarcely changed since 20,000 years ago. How then can we ever navigate through this vast ocean of information? This is my research interest. I mainly handle text (character) information. I intend to enable easy and appropriate extraction of knowledge and wisdom from this information in line with the intended use.

Aiming to create a search engine originating in Japan

When people hear the term "search engine," the first names that likely come to mind are Google and Yahoo!. These both started in the United States and are now used around the world. Virtually no search engines originate in Japan. Restrictions unique to Japan, such as copyright issues, have a great deal to do with this, but this does not mean that we should completely depend on overseas search engines, which are indeed information infrastructure of this era. This is why I am intent on developing an original and novel search engine in collaboration with those interested in this field.

At the root of language is sure to be a set of rules peculiar to human beings
MIYAO Yusuke

Despite being intelligent entities, monkeys lack a language like that of human beings. If one considers why only human beings can use language, one concludes that there exist some rules peculiar to human beings in their brains. I hope to discover the rules at the root of language, which we use every day without thinking.


Pattern Media


Obtaining new information from interconnected data

To enable the utilization of wide-ranging meteorological information for forecasting weather and preventing disasters, it is important to obtain useful information from not only observation data but also large amounts of information of various types, such as news articles and information from ordinary people. To that end, I would like to explore methods for obtaining new information from the interconnection of diverse information by applying the results of research into image processing and image searching.

Flexible free-viewpoint/focus image reconstruction

After capturing images, people sometimes wish they would change the setting of the camera, for example, viewpoint, focus, and so on. Our research enables us to realize such flexible free-viewpoint/focus image reconstruction by capturing and processing the detailed information of rays from objects with multiple cameras or special cameras.

Visual imaging technology that merges into the fabric of daily life
SATO Imari

Computers have added great convenience to our lives but remain―for now―convenient machines that sit on desktops. Many people believe computers will evolve to incorporate a "spatially flexible interface" that lets users access them from anywhere in their house, using gestures to obtain information or to display an image wherever it's needed. I study video technologies to help realize such futuristic functions.

Creating a sense of vision capable of understanding the meanings of moving pictures
SATOH Shin'ichi

My research seeks to create an "artificial eye" that can see the world just as we do. This is a kind of visual system that can provide smalltalk while enjoying a TV drama. Moreover, it understands and learns the information that enters through the eye, like a human baby. It even learns skills by watching, for instance, documentaries that showing craftspeople at work. My goal is to realize such a visual system.

Reconstructing computer vision from the standpoint of discrete geometry

My research focuses on scrutinizing methods of computer vision from the standpoint of applied mathematics and becoming able to discuss precision and similar topics. Computer vision can be described as a technology that recognizes an object shown in a two-dimensional image taken with a digital camera. This technology has made great progress and become familiar to us to the point where it is being applied to consumer digital cameras. The achievements of computer vision are, for example, technologies such as focusing on an object shown within a viewfinder by separating it from the background and adjusting exposure to recognize and take clear pictures of human faces. I engage in mathematical research to find a way to recognize objects.

Tools for easily creating Computer Graphics contents

Computer Graphics (CG) is all about building a virtual world inside a computer using mathematical representations and displaying it on a screen. Thanks to recent advances, these days it is often difficult for us to tell if a scene in a feature film is a real footage or a synthetic animation. The creation of such high-quality CG artworks still requires, however, considerable amount of human labor and financial resources. My research goal is to design new tools that make this creation process easier.

Seeking to build interactive multimedia systems that offer outstanding compression and data distribution performance

My area of expertise is signal processing, and I look at the entire communication process to help optimize, design, and develop systems like free viewpoint television (FTV). For FTV, video has to be generated, compressed, and transmitted to suit a particular perspective selected by any of a wide range of different users. I expect dramatic changes in the familiar TV sets currently found in every household.

Computer Vision for Perfect Shoes Fitting
ZHENG Yinqiang

Our research focus is on the geometric and photometric branches of computer vision. As for the geometric aspect, the major task is to reconstruct 3D scenes and locate cameras in large-scale scenarios. The photometric aspect aims to sense the illumination environment and optical properties of scene objects. We are interested in exploring physical models and developing appropriate mathematical optimization algorithms to solve various problems in these two branches.

Creating a visual encyclopedia
MO Hiroshi

In broadcasts such as TV programs, viewers have merely been passive receivers of information. However, functions such as on-demand viewing have enabled viewers to actively choose the programs they want to see and we will now see an era in which viewers can "use" images as knowledge. Video, which is capable of expressing information in picture form, is one of the easiest-to-understand knowledge sources. Not only is it easy to find the required images, it is essential to develop technology to recognize what images mean and establish a mechanism to index and automatically organize the information. I am currently developing these effective technologies.

Building a truly usable video search engine
LE Duy-Dinh

My research focuses on building a truly usable video search engine. To make video searchable, we first break down a video into a number of short shots. We then tag each shot with a title and information: such as the people, things, and acts depicted. This is called indexing. After this processing, the shots can be searched and just their highlights extracted. I'm studying technologies for having computers handle this indexing to achieve high speed and high precision.


Human and Knowledge Media


Using information systems to support intellectual environments

My basic research seeks to create useful things based on information systems. In my research, I'm trying to determine what kind of technology will further creative activity from a human-oriented viewpoint. There are many things that computers cannot help with, at least not at present―not just mental images, which are often indistinct, but also things like scenery viewed and sounds and conversations heard. Unfortunately, these things fade from memory unless they are recorded. I think the ability to retain this everyday information would help further creativity for lots of people. My research focuses on fundamentaltechnologies that can be used to convert this information into various digital formats like images and video and audio data, then store this information to enable effective use.

Communicating with children around the world through a topic map
ANDRES Frederic

My specialty is databases, but I'm currently working on research related to multimedia data management integrated with still images, sound, and moving pictures and on semantics (assigning meaning to data). One specific research area is related to a technical standard for advanced semantic indexing called a "topic map." Using a topic map, it is possible to classify automatically words based on related topics.

Utilizing the next-generation Web for enhanced communication

The Web was created about 15 or 16 years ago. Today, blogs and SNS (social networking services) have expanded widely, making everyone a transmitter of information and changing the way people communicate. When everyone makes information available to others, many things that weren't possible before become possible. I'd like to explore the potential of information exchange methods based on such personal networks.

Pursuing enhanced communication with users

My research involves making computers easier to use. Communicating with a present-day PC still requires the user to interact with a machine. No personal computer offers users a natural mode of communication. Today's computers lack a certain something that makes communication natural to users.

Breaking through the conventional wisdom of language, from the field of communication
BONO Mayumi

How can human beings communicate so well? Even though everyday conversation is often full of grammatical errors, the listener usually correctly understands what the speaker wants to say. I would like to gain a deeper understanding of the structures of the Japanese conversation and of Japanese sign language conversation through a close analysis of interactions, including speech and gestures.

Seeking "just the right relationship" between humans and machines

The advancement of science and technology brought us sophisticated machines capable of complex movements and processing huge amounts of information. Studies have now been conducted to support human activities by using machines such as robots. However, it is not certain exactly what function makes humans feel as if they are being helped while there are always needs for convenient machines.But a machine that automatically performs tasks is not necessarily convenient and if it even slightly fails to match humans' intent, users feel stressed and find the machine hard to use. Therefore, a machine should not be designed alone, but as part of the system that incorporates the person. I believe it is important that machines and people share roles wisely. This is why my research focuses on interactions between humans and machines.

Mining Valuable Knowledge about People Activities

The advancement of mobile devices has enabled people to readily create and share large volumes of multimedia data anywhere and anytime, using their mobile devices to take photos and post comments, record location information, and share with their friends. On the one hand, by analyzing the social multimedia information and data generated by an individual user, we can learn what content an individual user is interested in. On the other hand, diverse data are aggregated over the Internet as more users interact with various online platforms. In this sense, users themselves act as sensors and form a participatory sensing to gain insights of a society. By analyzing these data, it is possible to learn the characteristics of people daily life all over the world. Here, my research focuses on data mining and knowledge discovery from individual level to society level and creating intelligent systems and applications that felicitously support people daily life. I am working on algorithms that analyze, understand, and model the interesting things around people.