An adaptive technique for content-based image retrieval

We discuss an adaptive approach towards Content-Based Image Retrieval. It is based on the Ostensive Model of developing information needs—a special kind of relevance feedback model that learns from implicit user feedback and adds a temporal notion to relevance. The ostensive approach supports content-assisted browsing through visualising the interaction by adding user-selected images to a browsing path, which ends with a set of system recommendations. The suggestions are based on an adaptive query learning scheme, in which the query is learnt from previously selected images. Our approach is an adaptation of the original Ostensive Model based on textual features only, to include content-based features to characterise images. In the proposed scheme textual and colour features are combined using the Dempster-Shafer theory of evidence combination. Results from a user-centred, work-task oriented evaluation show that the ostensive interface is preferred over a traditional interface with manual query facilities. This is due to its ability to adapt to the user's need, its intuitiveness and the fluid way in which it operates. Studying and comparing the nature of the underlying information need, it emerges that our approach elicits changes in the user's need based on the interaction, and is successful in adapting the retrieval to match the changes. In addition, a preliminary study of the retrieval performance of the ostensive relevance feedback scheme shows that it can outperform a standard relevance feedback strategy in terms of image recall in category search.     

Hypadapter: An adaptive hypertext system for exploratory learning and programming

We have developed an adaptive hypertext system designed to individually support exploratory learning and programming activities in the domain of Common Lisp. Endowed with domain-specific knowledge represented in a hyperspace of topics, the system builds up a detailed model of the user's expertise which it utilizes to provide personalized assistance. Unlike other work emerging in the field of adaptive hypertext systems, our approach exploits domain and user modelling techniques to support individuals in different ways. The system not only generates individualized presentations of topic nodes, but also provides adaptive navigational assistance for link-based browsing. By identifying and suggesting useful hyperlinks according to the user's knowledge state and preferences, the system encourages and guides exploration. While browsing through the hyperspace of topics, the system analyses the user's navigational behaviour to infer the user's learning progress and to dynamically adapt presentations of topics and links accordingly.     

A user model neural network for a personal news service

User modelling has been widely applied to pedantic situations, where we are attempting to infer the user's knowledge. In teaching it is important to know that the user has mastered the elementary concepts before proceeding with the advanced topics. However, the application of user modelling to information retrieval demands a quite different type of user model. Here we construct a user model for browsing, where the user is uncertain of exactly which information he desires. This requires a more inexact and robust user model, that can quickly give guidance to the system. We propose a user model based on neural networks that can be constructed incrementally. Performance of the model shows some promise for this approach. We discuss the advantages and limitations of the approach and its implications for user modelling.     

Information Filtering Using User's Context on Browsing in Hypertext

Browsing is one of the most popular ways to gather information in database with hypertext structure. In order to support a user to browse, modeling of the user's interests is one of the most important issues. Although there are several promising methods to infer the interests from the user's browsing behavior, they assume that the interests are consistent during the browsing. However, the user's interests are often strongly dependent on the local context of the browsing. This paper describes a method to model the user's shifting interests from the browsing history. An information filtering method using the model of the interests has been implemented. We call it ‘context-sensitive filtering’. The results of an experimental evaluation, by real users' browsing for an encyclopedia in CD-ROM format, are also reported. This revised version was published online in July 2006 with corrections to the Cover Date.     

Using hypertext for college course information

A hypertext browsing system was compared with a linearly based command-line system for accessing information concerning college transfer courses. Usability engineering guidelines were used in ascertaining student expectations and in designing the hypertext system. A prototype was tested against a linearly based command-line system. Performance in completing two tasks was significantly faster using the hypertext system. User perceptions of the hypertext system were more favorable than those of the linearly based system. These results are discussed relative to other studies which have not found a preference for hypertext systems. Differences in the type of task used as well as the need for incorporating usability engineering guidelines are emphasized.     

Hypertext Access and the New Oxford English Dictionary

While hypertext access to the New Oxford English Dictionary would seem to be potentially beneficial, the conversion of such a text to a hypertext document and the generation of semantic links may not be feasible. Rather than attempting either the conversion of the text or the designation and storage of specific hypertext links, a prototype frontend called READER has been developed that provides hypertext access to the Dictionary. The emphasis in this work has been to provide the user with the browsing approach typical of hypertext rather than the more traditional query-oriented approach to accessing full-texts. The prototype is based on a dynamic hypertext model which facilitates browsing through the dynamic instantiation of implicit links existing in the text of the Dictionary.     

HyperFile: A data and query model for documents

Non-quantitative information such as documents and pictures pose interesting new problems in the database world. Traditional data models and query languages do not provide appropriate support for this information. Such data are typically stored in file systems, which do not provide the security, integrity, or query features of database management systems. The hypertext model has emerged as a good interface to this information; however,finding information using hypertext browsing does not scale well. We developed a query interface that serves as an extension of the browsing model of hypertext systems. These queries minimize the repeated user interactions required to locate data in a standard hypertext system. HyperFile is a prototype data server interface. In this article, we describe HyperFile, including a number of issues such as query generation, query processing, and indexing.     

A task-centered approach for user modeling in a hypermedia office documentation system

The development of user-adaptive systems is of increasing importance for industrial applications. User modeling emerged from the need to represent in the system knowledge about the user in order to allow informed decisions on how to adapt to match the user's needs. Most of the research in this field, however, has been theoretical, top-down. Our approach, in contrast, was driven by the needs of the application and shows features of bottom-up, user-centered design.We have implemented a user modeling component supporting a task-based interface to a hypermedia information system for hospitals and tested it under realistic conditions. A new architecture for user modeling has been developed which focuses on the tasks performed by users. It allows adaptive browsing support for users with different level of experience, and a level of adaptability. The requirements analysis shows that the differences in the information needs of users with different levels of experience are not only quantitative, but qualitative. Experienced users are not only able to cope with a wider browsing space, but sometimes prefer to organize their search in a different way. That is why the user model and the interface of the system are designed to support a smooth transition in the access options provided to novice users and to expert users.     

Visual guided navigation for image retrieval

In this work, we are interested in technologies that will allow users to actively browse and navigate large image databases and to retrieve images through interactive fast browsing and navigation. The development of a browsing/navigation-based image retrieval system has at least two challenges. The first is that the system's graphical user interface (GUI) should intuitively reflect the distribution of the images in the database in order to provide the users with a mental picture of the database content and a sense of orientation during the course of browsing/navigation. The second is that it has to be fast and responsive, and be able to respond to users actions at an interactive speed in order to engage the users. We have developed a method that attempts to address these challenges of a browsing/navigation based image retrieval systems. The unique feature of the method is that we take an integrated approach to the design of the browsing/navigation GUI and the indexing and organization of the images in the database. The GUI is tightly coupled with the algorithms that run in the background. The visual cues of the GUI are logically linked with various parts of the repository (image clusters of various particular visual themes) thus providing intuitive correspondences between the GUI and the database contents. In the backend, the images are organized into a binary tree data structure using a sequential maximal information coding algorithm and each image is indexed by an n-bit binary index thus making response to users’ action very fast. We present experimental results to demonstrate the usefulness of our method both as a pre-filtering tool and for developing browsing/navigation systems for fast image retrieval from large image databases.     

Interactive information services using World-Wide Web hypertext

Most World-Wide Web information servers provide simple browsing access to collections of static text or hypertext files. This paper describes some interactive World-Wide Web servers that produce information displays and documents dynamically rather than just providing access to static files. The PARC Map Viewer uses a geographic database to create and display maps of any part of the world on demand. The Digital Tradition folk music server provides access to a large database of song lyrics and melodies. These applications take advantage of the multimedia capabilities of World-Wide Web to deliver graphical and audio content as well as formatted text. Hypertext links are used not only for navigation, but also for setting search and presentation parameters. In these applications the HTML format and the HTTP protocol are used like a user interface tool kit to provide not only document retrieval but a complete custom user interface specialized for the application.     

Review: An information management system for informal design data

Engineering information management may be divided into formal information management, which involves data modelling, data exchange and transaction handling, and informal information management, which is concerned with the organisation and delivery of design advice and design parameter data. This paper describes a system, called Review, which has been developed for the management of informal design information from multiple sources. The system uses a hybrid hypertext/database approach to provide for the indexing and viewing of information sources using arbitrary attribute sets, and for the establishment of relationships between information entities using both static and dynamic links in a hypertext framework. Information may be accessed both by query and by browsing along relationships in the hypertext network. The paper presents an overview of the system design, and examples of its application to design advisory systems and documentation.     

Retrieving information from hypertext: issues and problems

One of the most important developments in information science and in information systems in recent years has been the emergence of hypertext as a way of organizing information. Hypertext uses a browsing rather than a searching strategy and hypertext systems have found applications in a number of diverse areas. One of the strengths of using a hypertext system is the freedom it gives to users in the choice of information they wish to see, but this is also one of its drawbacks. This paper examines the effectiveness of hypertext as a way of retrieving information and reviews conventional information retrieval techniques which are the alternative strategy. Previous attempts at combining information retrieval and hypertext are considered and a prototype system outlined which has been developed to generate guided tours for users, to direct them through a hypertext to information they have requested. Finally, how adding this kind of intelligent guidance to a hypertext system would affect its usability as an information system is discussed.     

A Lattice Conceptual Clustering System and Its Application to Browsing Retrieval

The theory of concept (or Galois) lattices provides a simple and formal approach to conceptual clustering. In this paper we present GALOIS, a system that automates and applies this theory. The algorithm utilized by GALOIS to build a concept lattice is incremental and efficient, each update being done in time at most quadratic in the number of objects in the lattice. Also, the algorithm may incorporate background information into the lattice, and through clustering, extend the scope of the theory. The application we present is concerned with information retrieval via browsing, for which we argue that concept lattices may represent major support structures. We describe a prototype user interface for browsing through the concept lattice of a document-term relation, possibly enriched with a thesaurus of terms. An experimental evaluation of the system performed on a medium-sized bibliographic database shows good retrieval performance and a significant improvement after the introduction of background knowledge.     

User-Tailored Planning of Mixed Initiative Information-Seeking Dialogues

Intelligent dialogue systems usually concentrate on user support at the level of the domain of discourse, following a plan-based approach. Whereas this is appropriate for collaborative planning tasks, the situation in interactive information retrieval systems is quite different: there is no inherent plan-goal hierarchy, and users are known to often opportunistically change their goals and strategies during and through interaction. We need to allow for mixed-initiative retrieval dialogues, where the system evaluates the user's individual dialogue behavior and performs situation-dependent interpretation of user goals, to determine when to take the initiative and to change the control of the dialogue, e.g., to propose (new) problem-solving strategies to the user. In this article, we present the dialogue planning component of a concept- oriented, logic-based retrieval system (MIRACLE). Users are guided through the global stages of the retrieval interaction but may depart, at any time, from this guidance and change the direction of the dialogue. When users submit ambiguous queries or enter unexpected dialogue control acts, abductive reasoning is used to generate interpretations of these user inputs in light of the dialogue history and other internal knowledge sources. Based on these interpretations, the system initiates a short dialogue offering the user suitable options and strategies for proceeding with the retrieval dialogue. Depending on the user's choice and constraints resulting from the history, the system adapts its strategy accordingly.     

InsightVideo: toward hierarchical video content organization for efficient browsing, summarization and retrieval

Hierarchical video browsing and feature-based video retrieval are two standard methods for accessing video content. Very little research, however, has addressed the benefits of integrating these two methods for more effective and efficient video content access. In this paper, we introduce InsightVideo, a video analysis and retrieval system, which joins video content hierarchy, hierarchical browsing and retrieval for efficient video access. We propose several video processing techniques to organize the content hierarchy of the video. We first apply a camera motion classification and key-frame extraction strategy that operates in the compressed domain to extract video features. Then, shot grouping, scene detection and pairwise scene clustering strategies are applied to construct the video content hierarchy. We introduce a video similarity evaluation scheme at different levels (key-frame, shot, group, scene, and video.) By integrating the video content hierarchy and the video similarity evaluation scheme, hierarchical video browsing and retrieval are seamlessly integrated for efficient content access. We construct a progressive video retrieval scheme to refine user queries through the interactions of browsing and retrieval. Experimental results and comparisons of camera motion classification, key-frame extraction, scene detection, and video retrieval are presented to validate the effectiveness and efficiency of the proposed algorithms and the performance of the system.     

User-centered indexing for adaptive information access

We are focusing on information access tasks characterized by large volume of hypermedia connected technical documents, a need for rapid and effective access to familiar information, and long-term interaction with evolving information. The problem for technical users is to build and maintain a personalized task-oriented model of the information to quickly access relevant information. We propose a solution which provides user-centered adaptive information retrieval and navigation. This solution supports users in customizing information access over time. It is complementary to information discovery methods which provide access to new information, since it lets users customize future access to previously found information. It relies on a technique, called Adaptive Relevance Network, which creates and maintains a complex indexing structure to represent personal user's information access maps organized by concepts. This technique is integrated within the Adaptive HyperMan system, which helps NASA Space Shuttle flight controllers organize and access large amount of information. It allows users to select and mark any part of a document as interesting, and to index that part with user-defined concepts. Users can then do subsequent retrieval of marked portions of documents. This functionality allows users to define and access personal collections of information, which are dynamically computed. The system also supports collaborative review by letting users share group access maps. The adaptive relevance network provides long-term adaptation based both on usage and on explicit user input. The indexing structure is dynamic and evolves over time. Learning and generalization support flexible retrieval of information under similar concepts. The network is geared towards more recent information access, and automatically manages its size in order to maintain rapid access when scaling up to large hypermedia space. We present results of simulated learning experiments.Dr. Mathé and Dr. Chen are contractors with Recom Technologies, Inc.     

Mining User Preferences,Page Content and Usage to Personalize Website Navigation

The growing availability of information on the Web has raised a challenging problem: can a Web-based information system tailor itself to different user requirements with the ultimate goal of personalizing and improving the users' experience in accessing the contents of a website? This paper proposes a new approach to website personalization based on the exploitation of user browsing interests together with content and usage similarities among Web pages. The outcome is the delivery of page recommendations which are strictly related to the navigational purposes of visitors and their actual location within the cyberspace of the website. Our approach has been used effectively for developing a non-invasive system which allows Web users to navigate through potentially interesting pages without having a basic knowledge of the website structure.     

Semantic Extraction and Semantics-Based Annotation and Retrieval for Video Databases

Digital video databases have become more pervasive and finding video clips quickly in large databases becomes a major challenge. Due to the nature of video, accessing contents of video is difficult and time-consuming. With content-based video systems today, there exists a significant gap between the user's information and what the system can deliver. Therefore, enabling intelligent means of interpretation on visual content, semantics annotation and retrieval are important topics of research. In this paper, we consider semantic interpretation of the contents as annotation tags for video clips, giving a retrieval-driven and application-oriented semantics extraction, annotation and retrieval model for video database management system. This system design employs an algorithm on objects' relation and it can reveal the semantics defined with fast real-time computation.     

An Experiment on the Integration of Hypertext within a Multi-User Text Retrieval System

Currently, few hypertext systems allow an author to incorporate electronic textual information into a hyperdocument without first copying it from the environment in which it is stored. In order to extend a hyperdocument, an author must either manually type in the new information or import a copy of the text. To avoid this inconvenience and thus improve the user's efficiency of operation, hypertext systems must be integrated into other environments so that an author can incorporate existing text into a hyperdocument without the necessity of duplicating the text. This paper presents the results of an investigation into how hypertext could be integrated within a multi user text retrieval system and describes the design and implementation of a prototype system called Hyperbrowser.