Improving users' interactions with a video retrieval system requires the examination of the search behavior of real users. This paper presents a study that examines and compares the video search behavior of professional archivists and novice users. The comparison focuses on the use and effectiveness of different state-of-the-art video search methods offered by the VITALAS retrieval system, and also on the behavior of the two user groups during their interactions with the retrieval results. We conducted our experiments in the context of TRECVID's 2009 interactive search task, using the provided collection and topics for our evaluation. The findings are based on a qualitative questionnaire analysis and a quantitative examination of the logged user actions on the search interface. The experimental results indicate that today's visual search techniques have improved in effectiveness, confirming a trend found in previous user studies. To our surprise, professional archivists used visual concept search in many of their searches. Queries containing visual concepts were more effective, resulting in more relevant shots found than the alternative methods. Overall, we conclude that professional archivists are more focused on recall when carrying out their search tasks and are better at reflecting on their own search performance.

In this paper, we present our experiments in TRECVID 2008 about High-Level feature extraction task. This is the first year for our participation in TRECVID, our system adopts some popular approaches that other workgroups proposed before. We proposed 2 advanced low-level features NEW Gabor texture descriptor and the Compact-SIFT Codeword histogram. Our system applied well-known LIBSVM to train the SVM classifier for the basic classifier. In fusion step, some methods were employed such as the Voting, SVM-base, HCRF and Bootstrap Average AdaBoost(BAAB).

The paper describes the submissions of CWI and University of Twente to the efficiency and entity ranking track of INEX 2008. With the INEX participation, we demonstrate and evaluate the functionality of our open source XML retrieval system PF/Tijah.

This paper describes the participation of VITALAS in the TRECVID-2009 evaluation where we submitted runs for the High-Level Feature Extraction (HLFE) and Interactive Search tasks. For the HLFE task, we focus on the evaluation of low-level feature sets and fusion methods. The runs employ multiple low-level features based on all available modalities (visual, audio and text) and the results show that use of such features improves the retrieval eectiveness

In this paper we describe our experiments performed for TRECVID 2008. We participated in the High Level Feature extraction and the Search task. For the High Level Feature extraction task we mainly installed our detection environment. In the Search task we applied our new PRFUBE ranking model together with an estimation method which estimates a vital parameter of the model, the probability of a concept occurring in relevant shots. The PRFUBE model has similarities to the well known Probabilistic Text Information Retrieval methodology and follows the Probability Ranking Principle.

We propose an expert finding method based on assumption of sequential dependence between a candidate expert and the query terms in the scope of a document. We assume that the strength of relation of a candidate to the document's content depends on its position in this document with respect to the positions of the query terms. The experiments on the official Enterprise TREC data demonstrate the advantage of our method over the method based on independence of query terms and persons in a document.

An expert finding system allows a user to type a simple text query and retrieve names and contact information of individuals that possess the expertise expressed in the query. This paper proposes a novel approach to expert finding in large enterprises or intranets by modeling candidate experts (persons), web documents and various relations among them with so-called expertise graphs. As distinct from the state of-the-art approaches estimating personal expertise through one-step propagation of relevance probability from documents to the related candidates, our methods are based on the principle of multi-step relevance propagation in topic specific expertise graphs. We model the process of expert finding by probabilistic random walks of three kinds: finite, infinite and absorbing. Experiments on TREC Enterprise Track data originating from two large organizations show that our methods using multi-step relevance propagation improve over the baseline one-step propagation based method in almost all cases.

We argue that ranking algorithms for XML should reflect the actual combined content and structure constraints of queries, while at the same time producing equal rankings for queries that are semantically equal. Ranking algorithms that produce different rankings for queries that are semantically equal are easily detected by tests on large databases: We call such algorithms not sound. We report the behaviour of different approaches to ranking contentand-structure queries on pairs of queries for which we expect equal ranking results from the query semantics. We show that most of these approaches are not sound. Of the remaining approaches, only 3 adhere to the W3C XQuery Full-Text standard.

CWI used PF/Tijah, a flexible XML retrieval system, to evaluate image retrieval based on textual evidence in the context of the wikipediaMM task at ImageCLEF 2008. We employed a language modelling framework and found that the text associated with the Wikipedia images is a good source of evidence. We also investigated a length prior and found that biasing towards images with longer descriptions than the ones retrieved by our language modelling approach is not beneficial.

We study entity ranking on the INEX entity track and propose a simple graph-based ranking approach that enables to combine scores on document and paragraph level. The combined approach improves the retrieval results not only on the INEX testset, but similarly on TREC's expert finding task.

We introduce a novel approach to expert finding based on multi-step relevance propagation from documents to related candidates. Relevance propagation is modeled with an absorbing random walk. The evaluation on the two official Enterprise TREC data sets demonstrates the advantage of our method over the state-of-the-art method based on one-step propagation.

A mask of insulating material is formed on the major surface of a semiconductor wafer, the mask including apertures to the wafer surface. A layer of monocrystalline silicon is then formed through the apertures and over the mask. The silicon within each aperture is next replaced with an insulating plug and epitaxial silicon is grown from the remaining portions of the monocrystalline silicon layer so as to form a continuous monocrystalline silicon sheet overlying the mask and plug.

CWI and University of Twente used PF/Tijah, a flexible XML retrieval system, to evaluate structured document retrieval, multimedia retrieval, and entity ranking tasks in the context of INEX 2007. For the retrieval of textual and multimedia elements in the Wikipedia data, we investigated various length priors and found that biasing towards longer elements than the ones retrieved by our language modelling approach can be useful. For retrieving images in isolation, we found that their associated text is a very good source of evidence in the Wikipedia collection. For the entity ranking task, we used random walks to model multi-step relevance propagation from the articles describing entities to all related entities and further, and obtained promising results.

Text retrieval is an active area of research since decades. Several issues have been studied over the entire period, like the development of statistical models for the estimation of relevance, or the challenge to keep retrieval tasks efficient with ever growing text collections. Especially in the last decade, we have also seen a diversification of retrieval tasks. Passage or XML retrieval systems allow a more focused search. Question answering or expert search systems do not even return a ranked list of text units, but for instance persons with expertise on a given topic. The sketched situation forms the starting point of this thesis, which presents a number of task-specific search solutions and tries to set them into more generic frameworks. In particular, we take a look at the three areas (1) context adaptivity of search, (2) efficient XML retrieval, and (3) entity ranking. In the first case, we show how different types of context information can be incorporated in the retrieval of documents. When users are searching for information, the search task is typically part of a wider working process. This search context, however, is often not reflected by the few search keywords stated to the retrieval system, though it can contain valuable information for query refinement. We address with this work two research questions related to the aim of developing context-aware retrieval systems. First, we show how already available information about the user’s context can be employed effectively to gain highly precise search results. Second, we investigate how such meta-data about the search context can be gathered. The proposed “query profiles” have a central role in the query refinement process. They automatically detect necessary context information and help the user to explicitly express context-dependent search constraints. The effectiveness of the approach is tested with retrieval experiments on newspaper data. When documents are not regarded as a simple sequence of words, but their content is structured in a machine readable form, it is attractive to try to develop retrieval systems that make use of the additional structure information. Structured retrieval first asks for the design of a suitable language that enables the user to express queries on content and structure. We investigate here existing query languages, whether and how they support the basic needs of structured querying. However, our main focus lies on the efficiency of structured retrieval systems. Conventional inverted indices for document retrieval systems are not suitable for maintaining structure indices. We identify base operations involved in the execution of structured queries and show how they can be supported by new indices and algorithms on a database system. Efficient query processing has to be concerned with the optimization of query plans as well. We investigate low-level query plans of physical database operators for the execution of simple query patterns. Furthermore, It is demonstrated how complex queries benefit from higher level query optimization. New search tasks and interfaces for the presentation of search results, like faceted search applications, question answering, expert search, and automatic timeline construction, come with the need to rank entities instead of documents. By entities we mean unique (named) existences, such as persons, organizations or dates. Modern language processing tools are able to automatically detect and categorize named entities in large text collections. In order to estimate their relevance to a given search topic, we develop retrieval models for entities which are based on the relevance of texts that mention the entity. A graph-based relevance propagation framework is introduced for this purpose that enables to derive the relevance of entities. Several options for the modeling of entity containment graphs and different relevance propagation approaches are tested, demonstrating the usefulness of the graph-based ranking framework.

We used a flexible XML retrieval system for evaluating structured document retrieval and multimedia retrieval tasks in the context of the INEX 2006 benchmarks. We investigated the differences between article and element retrieval for Wikipedia data as well as the influence of an elements context on its ranking. We found that article retrieval performed well on many tasks and that pinpointing the relevant passages inside an article may hurt more than it helps. We found that for finding images in isolation the associated text is a very good descriptor in the Wikipedia collection, but we were not very succesful at identifying relevant multimedia fragments consisting of a combination of text and images.

This paper describes the approach of the University of Twente at its first participation in GeoCLEF. A large effort went into the construction of a geographic thesaurus which was utilized to add geographic knowledge to the documents and queries. Geographic filtering was applied to the results returned from a retrieval by content run. Employing such a geographic knowledge base however showed no added value - the content-only baseline outperformed all geographically filtered runs.

This paper describes several approaches which we used for the expert search task of the TREC 2007 Enterprise track. We studied several methods of relevance propagation from documents to related candidate experts. Instead of one-step propagation from documents to directly related candidates, used by many systems in the previous years, we do not limit the relevance flow and disseminate it further through mutual documents-candidates connections. We model relevance propagation using random walk principles, or in formal terms, discrete Markov processes. We experiment with innite and nite number of propagation steps. We also demonstrate how additional information, namely hyperlinks among documents, organizational structure of the enterprise and relevance feedback may be utilized by the presented techniques.

PF/Tijah (Pathfinder/Tijah, pronounce as Pee Ef Teeja) is a flexible open source text search system developed at the University of Twente in cooperation with CWI Amsterdam and TU Munchen. The system is integrated in the Pathfinder XQuery database system and can be downloaded as part of MonetDB/XQuery. This report contains user documentation of PF/Tijah, including example usage in three show cases.