International Journal of Multimedia Technology Sep 2012, Vol. 2 Iss. 3, PP. 89-97 - 89 - Reusing a Compound-Based Infrastructure for Searching and Annotating Video Stories Nádia P. Kozievitch 1 , Jurandy Almeida 2 , Ricardo da S. Torres 3 , André Santanchè 4 , Neucimar J.Leite 5 Uma Murthy 6 , Edward A. Fox 7 1 Department of Computer Science, Federal University of Technology 85503-390, Pato Branco, PR- Brazil 2, 3, 4, 5 Institute of Computing, University of Campinas – UNICAMP 13083-852, Campinas, SP- Brazil 6, 7 Department of Computer Science, Virginia Polytechnic Institute and State University Blacksburg, VA, 24061-010 – USA 1 nadiap@.utfpr.edu.br; 2 jurandy.almeida.ic.unicamp.br; 3 rtorres.ic.unicamp.br; 4 santanche.ic.unicamp.br; 5 neucimar.ic.unicamp.br; 6 umurthy.vt.edu; 7 fox.vt.edu Abstract-The fast evolution of technology has led to a growing demand for multimedia data, increasing the amount of research into efficient systems to manage those materials. Significant in those efforts is the work being done by the Content-Based Image Retrieval (CBIR) community in processing and retrieving images, along with their further combination with annotations. Nowadays, images play a key role in digital applications. Contextual integration of images with different sources is vital – it involves reusing and aggregating a large amount of information with other media types. In particular, if we consider video data, annotations can be used to summarize textual descriptions and metadata, while images can be used to summarize videos into storyboards, providing an easy way to navigate and to browse large video collections. This has been the goal of a rapidly evolving research area known as video summarization. In this paper, we present a novel approach to reuse a CBIR infrastructure for searching, annotating and publishing video stories, taking advantage of the complex object (CO) concept to integrate resources. Our approach relies on a specific component technology (Digital Content Component - DCC) to encapsulate the CBIR-annotation related tasks and integrate them with video summarization techniques. Such a strategy provides an effective way to reuse, compose, and aggregate both content and processing software. Keywords- Complex Object; CBIR; Video Stories; Annotation; Reuse I. INTRODUCTION Recent advances in technology have facilitated the creation, storage, and distribution of digital resources. It led to an increase in the amount of multimedia data deployed and used in many applications, such as search engines and digital libraries. In order to deal with those data and to efficiently manage their collections, it is necessary to develop appropriate information systems. For over two decades, significant research efforts have been spent by the Content-Based Image Retrieval (CBIR) community, focusing on image retrieval and annotation. Currently, they are the basic units of many digital applications. Annotation has been recognized as one of the most important services in digital library systems to foster cooperation among users and the integration of heterogeneous information resources [2] . Contextual integration of images with different sources is vital. In particular, if we consider video data, images can be used to summarize videos into storyboards, providing an easy way to understand a video content, without having to watch it entirely, so that a user can quickly judge whether a video story is relevant or not. In order to reuse and aggregate different resources, complex objects (COs) have emerged, motivating solutions for integration and interoperability. Such objects are aggregations of different information combined together to shape a unique logical object [19, 36] . Particularly, Complex Image Objects (ICO) are a representative example of a data source which is generally integrated with different components, such as links and metadata. Recently, we developed a component-based CBIR infrastructure aiming to process and encapsulate ICOs. Our contribution relies on the reuse of two basic digital library services (annotation and CBIR) in a compound-based infrastructure to integrate, annotate, search, retrieve, and publish video stories. Our solution is the Digital Content Component (DCC) [38] , a self-descriptive unit, which converges the complex object and the software component models in a unified model, to encapsulate content and executable software, and to correlate both. Those properties of DCCs are exploited by our infrastructure to encapsulate several aspects of annotations and CBIR for a further integration with video material. This framework provides an effective way to reuse, compose, and aggregate both content and processing software. We demonstrate these benefits in a case study with a sample of 50 videos. A preliminary version of this work was presented at IEEE IRI 2011 [20] . Here, we introduce several innovations.