In this paper we formulate image retrieval by text query as a vector space classification problem. This is achieved by creating a high-dimensional visual vocabulary that represents the image documents in great detail. We show how the representation of these image documents enables the application of well known text retrieval techniques such as Rocchio tf-idf and naïve Bayes to the semantic image retrieval problem. We tested these methods on a Corel images subset and achieve state-of-the-art retrieval performance using the proposed methods.

No abstract

The research aims to develop novel techniques able to recognise different sequential gestures, to the level where they will describe and compute articulated movements in real time. In the context of live media arts, the research outcomes would change the paradigm of creating, learning, performing, designing for live media arts, by giving feedback on performance after analysing, in real time, the streaming video of the performance.Understanding how we recognise and respond to rhythm patterns kinaesthetically, may support the development of movement description and gesture recognition in real time [5].One of the main problems in computer vision is defining and describing movement [6]. Traditional approaches mainly rely either on different body-mounted sensors or marker-oriented approaches [2]. Here, the performers have to adapt their natural performance or require substantial training to adopt the tools in their performance. Our principal focus is the development of a system that will free performers from constraints of wearable technology, and allow them to perform in a natural way, without movement and coordination restrictions. Secondly, this will also allow greater precision in analysing the movements while tracking the performance, thus obtaining higher levels of details of movement, allowing in turn the performers to track their performance with greater ease.Key problems in computer vision for the live media arts include the lack of realtime feedback on performance, the inability to seamlessly control body movement in response to audio and visual output, and the unavailability of consistent feedback and evaluation to the performers on their practice in real time. The main goals of our work are:Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. 1. To make an analytical tool for performers that will act as a real-time evaluator and assessor by providing generative feedback on their performance. Expert performers are involved in the training of the evaluation system in order to generate valid ground truth-data. Our research in computer vision and information retrieval algorithms provides an algorithmic chain capable of [1]: (i) analysing shapes in sequential video-frames, (ii) extracting vision based features that will be then used to detect the performers' gestures and movements. Here, the input and feedback of expert performers will be used in order to build a vocabulary of gestures and to validate the results. This will create a feedback loop between performer and the system that will also be ...

The International Workshop on Recommendation and Collaboration (ReColl 2008) aims to identify emerging trends in recommendation technology and collaborative environments in the context of intelligent user interfaces. We explore these two topics separately and the synergies between them. RecommendationIn recent years, recommender technology has become a popular component of web-based commerce sites. With the growth of the social web, increasing mobility, and the rise of software as a service, a variety of new opportunities are opening for the application of recommender technology. These, and other trends, are driving a number of advances in this area.The ReColl workshop gives researchers in the area of recommender technology an opportunity to come together and discuss the "next generation" of research problems to be addressed. Emphasis of the workshop is on both the collaborative aspects of recommender systems, as well as other appropriate technologies, such as knowledge-based systems. The workshop aims to address following topics of interest:• Applications of recommender technology • Hybrid recommender technologies • Combining social networking systems and recommenders • Knowledge-based recommenders • Evaluation approaches • Intelligent and adaptive interfaces • Semantic web technologies and recommender systems • User intent and preference modeling • Recommendation as a service • Mathematical validity vs. scalability of algorithms • Explanations and other mechanisms to increase user confidence Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee.Modern collaborative environments enable large groups of users to share data and memories, different views about events, ratings about web sites or products, and models of user behavior. The internet, the World Wide Web (WWW) and modern peer-to-peer technology provide an infrastructure on top of which a variety of communication channels and collaborative environments have been established. Successful examples of collaborative environments include Web 2.0 content sharing systems (such as Flickr, YouTube and Del.icio.us), recommender systems for products or other resources, peer-to-peer content sharing systems, and collaborative assistance systems. Design of novel interfaces for better supporting collaboration scenarios has been intensively studied in the recent research. The ReColl workshop reverses the common problem definition and poses the novel question: how can intelligent user interfaces benefit from user collaboration? Topics of discussion include:• Combination and representation of content from different sources • Evidence combination for assistance interfaces • Interface personalization in collaborative environmen...