No abstract

An aggregated search interface is designed to integrate search results from different sources (web, image, video, blog, etc) into a single result page. This paper presents two user studies investigating factors affecting users click-through behavior on aggregated search interfaces. We tested two aggregated search interfaces: one where results from the different sources are blended into a single list (called blended ), and another, where results from each source are presented in a separate panel (called non-blended ). A total of 1,296 search sessions performed by 48 participants were analysed in our study. Our results suggest that 1) the position of search results is significant only in the blended and not in the nonblended design; 2) participants' click-through behavior on videos is different from other sources; and finally 3) capturing a task's orientation towards particular sources is an important factor for further investigation and research.

[2,3]. In and implicit retrieval cycles. Our model seems to enhance re-this paper we analyse a model of implicit feedback. In our trieval results. Results are presented and discussed in the final experiment we look at the advantages the use of implicit feedsection. back can possibly give in retrieval performance, by simulating users based on the collection relevance information. The results were then analysed to investigate the assumptions on 1. INTRODUCTION which the model of implicit information is based. This paper is organised as follows: It gives a short survey With the improving capabilities of current hardware systems, of existing video retrieval systems in section 2 and presents there are ever growing possibilities to store and manipulate their inadequacies, which motivated our work. We implevideos in a digital format, leading to a growing number of mented a video retrieval system which can be used to give video archives. People build their own digital libraries from explicit and implicit relevance feedback. In section 3, we inmaterials created through digital cameras and camcorders, and troduce this system and outline the model of implicit inforuse systems such as YouTube. and Google Video2 to place mation which is built into the system. Four simulated user this material on the web. Unfortunately, this data creation studies were performed (section 4) to investigate the type of prowess is not matched by any comparable tools to organise performance improvement we might hope to gain given the and retrieve video information, use of the implicit model. In the remainder of this paper, weThere is a need to create new retrieval engines to assist the discuss our simulation results, draw conclusions and focus on user in searching and finding video scenes he/she would like our future work. Hauptmann et al. (2004) [8] developed and compared two relevance feedback model which fits best the weighting bevideo retrieval systems using visual and textual data versus a tween explicit and implicit feedback. We assume that the visual-only system as part of the Informedia project. In addiinformation given implicitly by a user can be used in video tion, they compared expert and naive users.retrieval to enhance search results. For testing this, we deHauptmann et al. (2005) [9] evaluated the system in lowveloped a retrieval system which can make use of implicit level feature extraction, semantic concept feature extraction relevance feedback. Our second objective was to provide reand searching. Their interface visualised a list of results which trieval results handling these implicit features. We developed are associated with text terms. The retrieval results are not dea first feedback model where we assumed some features as pendent on relevance feedback. Their main focus is on combeing important for implicit feedback. Based on that, we ran paring the evolution of topics and data set through the years a simulated study to get data for our objective.and measuring novice and expert users. Foley et al. (2005) [10] experimented ...

With the rapid increase in online video services, video retrieval systems are becoming increasingly important search tools to many users in many different fields. In this poster we present a novel video retrieval interface, which supports the creation of multiple search "facets", to aid users carrying out complex, multi-faceted search tasks. The interface allows multiple searches to be executed and viewed simultaneously, and allows material to be reorganized between the facets. An experiment is presented which compares the faceted interface to a tabbed interface similar to that on modern web browsers, and some preliminary results are given.

In this paper we present a novel filtering system, based on a new model which reshapes the aims of content-based filtering. The filtering system has been developed within the EC project PENG [3], aimed at providing news professionals, such as journalists, with a system supporting both filtering and retrieval capabilities. In particular, we suggest that in tackling the problem of information overload, it is necessary for filtering systems to take into account multiple aspects of incoming documents in order to estimate their relevance to a user's profile, and in order to help users better understand documents, as distinct from solely attempting to either select relevant material from a stream, or block inappropriate material. Aiming to so this, a filtering model based on multiple criteria has been defined, based on the ideas gleamed in the project requirements stage. The filtering model is briefly described in this paper.