Clement H. C. Leung

Advances in Visual Information Systems

Keynote Paper.- Visual Information Retrieval - Future Directions and Grand Challenges.- Image and Video Retrieval.- Approximation-Based Keypoints in Colour Images - A Tool for Building and Searching Visual Databases.- A Knowledge Synthesizing Approach for Classification of Visual Information.- Image Similarity - From Fuzzy Sets to Color Image Applications.- A Semi-automatic Feature Selecting Method for Sports Video Highlight Annotation.- Face Image Retrieval System Using TFV and Combination of Subimages.- Near-Duplicate Detection Using a New Framework of Constructing Accurate Affine Invariant Regions.- Where Are Focused Places of a Photo?.- Region Based Image Retrieval Incorporated with Camera Metadata.- Empirical Investigations on Benchmark Tasks for Automatic Image Annotation.- Automatic Detection and Recognition of Players in Soccer Videos.- A Temporal and Visual Analysis-Based Approach to Commercial Detection in News Video.- Salient Region Filtering for Background Subtraction.- A Novel SVM-Based Method for Moving Video Objects Recognition.- Image Classification and Indexing by EM Based Multiple-Instance Learning.- Visual Biometrics.- Palm Vein Extraction and Matching for Personal Authentication.- A SVM Face Recognition Method Based on Optimized Gabor Features.- Palmprint Identification Using Pairwise Relative Angle and EMD.- Finding Lips in Unconstrained Imagery for Improved Automatic Speech Recognition.- Intelligent Visual Information Processing.- Feature Selection for Identifying Critical Variables of Principal Components Based on K-Nearest Neighbor Rule.- Denoising Saliency Map for Region of Interest Extraction.- Cumulative Global Distance for Dimension Reduction in Handwritten Digits Database.- A New Video Compression Algorithm for Very Low Bandwidth Using Curve Fitting Method.- The Influence of Perceived Quality by Adjusting Frames Per Second and Bits Per Frame Under the Limited Bandwidth.- An Evolutionary Approach to Inverse Gray Level Quantization.- Visual Data Mining.- Mining Large-Scale News Video Database Via Knowledge Visualization.- Visualization of the Critical Patterns of Missing Values in Classification Data.- Visualizing Unstructured Text Sequences Using Iterative Visual Clustering.- Enhanced Visual Separation of Clusters by M-Mapping to Facilitate Cluster Analysis.- Multimedia Data Mining and Searching Through Dynamic Index Evolution.- Ubiquitous and Mobile Visual Information Systems.- Clustering and Visualizing Audiovisual Dataset on Mobile Devices in a Topic-Oriented Manner.- Adaptive Video Presentation for Small Display While Maximize Visual Information.- An Efficient Compression Technique for a Multi-dimensional Index in Main Memory.- RELT - Visualizing Trees on Mobile Devices.- Auto-generation of Geographic Cognitive Maps for Browsing Personal Multimedia.- Semantics.- Automatic Image Annotation for Semantic Image Retrieval.- Collaterally Cued Labelling Framework Underpinning Semantic-Level Visual Content Descriptor.- Investigating Automatic Semantic Processing Effects in Selective Attention for Just-in-Time Information Retrieval Systems.- News Video Retrieval by Learning Multimodal Semantic Information.- 2D/3D Graphical Visual Data Retrieval.- Visualization of Relational Structure Among Scientific Articles.- 3D Model Retrieval Based on Multi-Shell Extended Gaussian Image.- Neurovision with Resilient Neural Networks.- Applications of Visual Information Systems.- Visual Information for Firearm Identification by Digital Holography.- GIS-Based Lunar Exploration Information System in China.- Semantic 3D CAD and Its Applications in Construction Industry - An Outlook of Construction Data Visualization.- A Fast Algorithm for License Plate Detection.- Applying Local Cooccurring Patterns for Object Detection from Aerial Images.- Enticing Sociability in an Intelligent Coffee Corner.- Geometric and Haptic Modelling of Textile Artefacts.- A Toolkit to Support Dynamic Social Network Visualization.- The Predicate Tree - A Metaphor for Visually Describing Complex Boolean Queries.- Potentialities of Chorems as Visual Summaries of Geographic Databases Contents.- Compound Geospatial Object Detection in an Aerial Image.- Texture Representation and Retrieval Using the Causal Autoregressive Model.- An Approach Based on Multiple Representations and Multiple Queries for Invariant Image Retrieval.

Visual Information Systems

A visual information system includes an array of light emitting elements located at the side of a train track. The elements are individually energizable by a controller in response to a predetermined program stored in a memory and representative of a predetermined visual image. The controller causes selected elements to be turned ON and OFF, some repetitively, in a predetermined sequence as dictated by the program with a time span of 0.015 seconds. A sensor activates the controller upon the approach of a train so that a passenger gazing at the array as the train passes will perceive the image apparently extending over an area substantially greater than the area of said array.

Benchmarking for Content-Based Visual Information Search

The importance of the visual information search problem has given rise to a large number of systems and prototypes being built to perform such search. While different systems clearly have their particular strengths, they tend to use different collections to highlight the advantages of their algorithms. Consequently, a degree of bias may exist, and it also makes it difficult to make comparisons concerning the relative superiority of different algorithms. In order for the field of visual information search to make further progress, a need therefore exists for a standardised benchmark suite to be developed. By having a uniform measure of search performance, research progress can be more easily recognised and charted, and the resultant synergy will be essential to further development of the field. This paper presents concrete proposals concerning the development of such a benchmark, and by adopting an extensible framework, it is able to cater for a wide variety of applications paradigms and to lend itself to incremental refinement.

Intelligent Social Media Indexing and Sharing Using an Adaptive Indexing Search Engine

Effective sharing of diverse social media is often inhibited by limitations in their search and discovery mechanisms, which are particularly restrictive for media that do not lend themselves to automatic processing or indexing. Here, we present the structure and mechanism of an adaptive search engine which is designed to overcome such limitations. The basic framework of the adaptive search engine is to capture human judgment in the course of normal usage from user queries in order to develop semantic indexes which link search terms to media objects semantics. This approach is particularly effective for the retrieval of multimedia objects, such as images, sounds, and videos, where a direct analysis of the object features does not allow them to be linked to search terms, for example, nontextual/icon-based search, deep semantic search, or when search terms are unknown at the time the media repository is built. An adaptive search architecture is presented to enable the index to evolve with respect to user feedback, while a randomized query-processing technique guarantees avoiding local minima and allows the meaningful indexing of new media objects and new terms. The present adaptive search engine allows for the efficient community creation and updating of social media indexes, which is able to instill and propagate deep knowledge into social media concerning the advanced search and usage of media resources. Experiments with various relevance distribution settings have shown efficient convergence of such indexes, which enable intelligent search and sharing of social media resources that are otherwise hard to discover.

Comparative evaluation of Web image search engines for multimedia applications

While text-oriented document searching are relatively mature on the Internet, image searching, which requires much more than text matching, significantly lags behind. The use of image search engines significantly enlarges the scope of images to users accessibility. This paper provides an understanding of current technologies in image searching on the Internet, and points to future areas of improvement for multimedia applications. We develop a systematic set of image queries to assess the competence and performance of the major image search engines. We find that current technology is only able to deliver an average precision of around 42% and an average recall of around 12%, while the best performers are capable of producing over 70% for precision and around 27% for recall. The reasons for such differences, and mechanisms for search improvement, are also indicated.

Collective evolutionary concept distance based query expansion for effective web document retrieval

In this work several semantic approaches to concept-based query expansion and re-ranking schemes are studied and compared with different ontology-based expansion methods in web document search and retrieval. In particular, we focus on concept-based query expansion schemes where, in order to effectively increase the precision of web document retrieval and to decrease the users’ browsing time, the main goal is to quickly provide users with the most suitable query expansion. Two key tasks for query expansion in web document retrieval are to find the expansion candidates, as the closest concepts in web document domain, and to rank the expanded queries properly. The approach we propose aims at improving the expansion phase for better web document retrieval and precision. The basic idea is to measure the distance between candidate concepts using the PMING distance, a collaborative semantic proximity measure, i.e. a measure which can be computed using statistical results from a web search engine. Experiments show that the proposed technique can provide users with more satisfying expansion results and improve the quality of web document retrieval.

Image data modeling for efficient content indexing

A data model is presented for the systematic representation of image content. The basic building block of the data model consists of facts, which may be modified and linked together in different ways to express the subject matter of an image. From the data model, a canonical image description may be automatically built, which can capture a rich content semantics. The canonical description may be used to construct a content-based index using a relational database structure. The database structure uses four tables which can be indexed and searched rapidly to provide fast image identification and retrieval. It is expected that the proposed approach may work in conjunction with picture keys, which are a pictorial summary of the underlying images, to provide a flexible scheme for building a powerful query model for the efficient retrieval of images by content for a variety of image database applications.

Probabilistic Aspect Mining Model for Drug Reviews

Recent findings show that online reviews, blogs, and discussion forums on chronic diseases and drugs are becoming important supporting resources for patients. Extracting information from these substantial bodies of texts is useful and challenging. We developed a generative probabilistic aspect mining model (PAMM) for identifying the aspects/topics relating to class labels or categorical meta-information of a corpus. Unlike many other unsupervised approaches or supervised approaches, PAMM has a unique feature in that it focuses on finding aspects relating to one class only rather than finding aspects for all classes simultaneously in each execution. This reduces the chance of having aspects formed from mixing concepts of different classes; hence the identified aspects are easier to be interpreted by people. The aspects found also have the property that they are class distinguishing: They can be used to distinguish a class from other classes. An efficient EM-algorithm is developed for parameter estimation. Experimental results on reviews of four different drugs show that PAMM is able to find better aspects than other common approaches, when measured with mean pointwise mutual information and classification accuracy. In addition, the derived aspects were also assessed by humans based on different specified perspectives, and PAMM was found to be rated highest.

Set Similarity Measures for Images Based on Collective Knowledge

This work introduces a new class of group similarity where different measures are parameterized with respect to a basic similarity defined on the elements of the sets. Group similarity measures are of great interest for many application domains, since they can be used to evaluate similarity of objects in term of the similarity of the associated sets, for example in multimedia collaborative repositories where images, videos and other multimedia are annotated with meaningful tags whose semantics reflects the collective knowledge of a community of users. The group similarity classes are formally defined and their properties are described and discussed. Experimental results, obtained in the domain of images semantic similarity by using search engine based tag similarity, show the adequacy of the proposed approach in order to reflect the collective notion of semantic similarity.

Topological analysis of AOCD-based agent networks and experimental results

Topological analysis of intelligent agent networks provides crucial information about the structure of agent distribution over a network. Performance analysis of agent network topologies helps multi-agent system developers to understand the impact of topology on system efficiency and effectiveness. Appropriate topology analysis enables the adoption of suitable frameworks for specific multi-agent systems. In this paper, we systematically classify agent network topologies and propose a novel hybrid topology for distributed multi-agent systems. We compare the performance of this topology with two other common agent network topologies-centralised and decentralised topologies-within a new multi-agent framework, called Agent-based Open Connectivity for DSS (AOCD). Three major aspects are studied for estimating topology performance, which include (i) transmission time for a set of requests; (ii) waiting time for processing requests; and (iii) memory consumption for storing agent information. We also conduct a set of AOCD topological experiments to compare the performance of hybrid and centralised agent network topologies and illustrate our experimental results in this paper.