Abstract: Results of internet searches are typically presented as lists. When searching for digital photos different search result presentations however offer different benefits. If users are primarily interested in the visual content of images a thumbnail grid may be more appropriate than a list. For people searching photos taken at a specific place image metadata in the result presentation is of interest too. In this paper we present an application which monitors a user's behavior while searching for digital photos and classifies the user's intention. Based on the intention, the result is adapted to support the user in an optimal way.

Abstract: Search queries are typically interpreted as specification of information need of a user. Typically the search query is either interpreted as is or based on the context of a user, being for instance a user profile, his/her previously undertaken searches or any other background information. The actual intent of the user – the goal s/he wants to achieve with information retrieval – is an important part of a user’s context. In this paper we present the results of an exploratory study on the interplay between the goals of users and their search behavior in multimedia retrieval.

Abstract: Planning Video-on-Demand (VoD) services based on the server architecture and the available equipment is always a challenging task. We created a formal model to support the design of distributed video servers that adapt dynamically and automatically to the changing client demands, network and host parameters. The model makes giving estimations about the available throughput possible, and defines evaluation criteria for VoD services relating to utilization and load balance, video usage, client satisfaction and costs. The dynamism of the frame model originates from the possible state transitions which have to be defined in a core model. The core model is responsible for configuration recommendation which determines how clients are served depending on the properties of their requests, system configuration and system load. Furthermore, it decides on the optimal placement of the server components in the network. The usability of the model is illustrated on examples.

Abstract: In this thesis I give an overview of current research done in the fields of video abstraction, video browsing and interactive video retrieval. In these research fields, which are summarized under the term video exploration, new concepts and solutions are developed that should help the users to get more control over video content again. Furthermore, I am going to introduce "FVET", the Flexible Video Exploration Toolkit. This is a platform that has been developed in the scope of this thesis, to be able to experiment with different approaches of video exploration. As it can be extend with plug-ins, it is very flexible regarding future developments. For this purpose an own plug-in architecture has been implemented that addresses especially the needs of video exploration applications.

Abstract: This paper presents an image retrieval suite called img(Rummager) which brings into effect a number of new as well as state of the art descriptors. The application can execute an image search based on a query image, either from XML-based index files, or directly from a folder containing image files, extracting the comparison features in real time. In addition the img(Rummager) application can execute a hybrid search of images from the application server, combining keyword information and visual similarity. Also img(Rummager) supports easy retrieval evaluation based on the normalized modified retrieval rank (NMRR) and average precision (AP).

Abstract: Compact Composite Descriptors (CCD) are global image features capturing both, color and texture characteristics, at the same time in a very compact representation. In this paper we propose a combination of two recently introduced CCDs (CEDD and FCTH) into a Joint Composite Descriptor (JCD). We further present a method for descriptor selection to approach the best ANMRR that would result from CEDD and FCTH. With our approach the most appropriate descriptor in terms of maximization of information content can be found on a per image basis without knowledge of the data set as a whole. Experiments conducted on three known benchmarking image databases demonstrate the effectiveness of the proposed technique.

Abstract: We plan to setup a VoD service built on an innovative multimedia server architecture which enables dynamic adaptation to the changing circumstances. The adaptation happens by replicating the server components and the stored videos based on real-time host and network monitoring and resource constraint analysis. In addition, the terminal capabilities and client preferences are considered. The paper focuses on the challenge of the optimal placement of storage components and the videos in the network. We compare three implemented optimisation algorithms (so called simple, incremental and complex incremental); the latter one can be calibrated against different preferences. We examine the effect of changing weights of the algorithm onto the recommendation.

Abstract: On the web, search engines represent a primary instrument through which users exercise their intent. Understanding the specific goals users express in search queries could improve our theoretical knowledge about strategies for search goal formulation and search behavior, and could equip search engine providers with better descriptions of users’ information needs. However, the degree to which goals are explicitly expressed in search queries can be suspected to exhibit considerable variety, which poses a series of challenges for researchers and search engine providers. This paper introduces a novel perspective on analyzing user goals in search query logs by proposing to study different degrees of intentional explicitness. To explore the implications of this perspective, we studied two different degrees of explicitness of user goals in the AOL search query log containing more than 20 million queries. Our results suggest that different degrees of intentional explicitness represent an orthogonal dimension to existing search query categories and that understanding these different degrees is essential for effective search. The overall contribution of this paper is the elaboration of a set of theoretical arguments and empirical evidence that makes a strong case for further studies of different degrees of intentional explicitness in search query logs.

Abstract: On the web, search engines represent a primary instrument through which users exercise their intent. Understanding the specific goals users express in search queries could improve our theoretical knowledge about strategies for search goal formulation and search behavior, and could equip search engine providers with better descriptions of users’ information needs. However, the degree to which goals are explicitly expressed in search queries can be suspected to exhibit considerable variety, which poses a series of challenges for researchers and search engine providers. This paper introduces a novel perspective on analyzing user goals in search query logs by proposing to study different degrees of intentional explicitness. To explore the implications of this perspective, we studied two different degrees of explicitness of user goals in the AOL search query log containing more than 20 million queries. Our results suggest that different degrees of intentional explicitness represent an orthogonal dimension to existing search query categories and that understanding these different degrees is essential for effective search. The overall contribution of this paper is the elaboration of a set of theoretical arguments and empirical evidence that makes a strong case for further studies of different degrees of intentional explicitness in search query logs.

Abstract: We present a video content browsing tool which is supposed to be used for two purposes: (1) efficiently searching a certain scene within a long video sequence and (2) quickly identifying videos out of interest. Instead of a complex user interface with many features we rather use a simple but flexible player-like interface which can, however, support the user on taking advantage of his/her knowledge about the content semantics. The content analysis is based on some simple features which can be extracted from compressed data of H264/AVC and, thus, allow very fast analysis. An early user study has shown encouraging results.

Abstract: Video summarization methods need fast segmentation of a video into smaller units as a first step, especially if used in an on-demand fashion. We propose an efficient segmentation algorithm for H.264/AVC bitstreams that is able to segment a video in appr. 10% of the time required to decode the video. This is possible because our approach uses features available after entropy-decoding (which is the very first stage of the decoding process) only. More precisely, we use a combination of two features, especially appropriate to H.264/AVC, with different characteristics in order to decide if a new segment starts or not: (1) L1-Distance based partition histograms and (2) ratio of intra-coded macroblocks on a per-frame basis. Our results show that this approach performs well and works for several different encoders used in practice today.

Abstract: Self-organized criticality (SOC) is a measure to identify if complex systems have the potential to build out emergent behavior. This phenomenon is known in many different areas of physics, biology, ecology, economy and social systems. Its core assertion is that an over critical energy input can lead to spontaneous, self-enforcing and unpredictable self-organization. In such a process new structures and orders emerge. “Online Crowds” are masses of internet users who behave and act collectively on the web. They tend to follow specific online trends and can generate tremendous online traffic and attention (cp. Social software like YouTube.com, MySpace.com, Friendster.com, etc.). “Online Crowds” are observed rarely, are hard to predict and even harder to generate artificially. So it is essential for online business ideas to foster and facilitate these “Online Crowds” to reach a critical mass of online users to grow continuously and to produce profit. The paper in hand introduces the “Online Crowds” model (OCM) in context of web information systems employing the concepts of self organization theory and self organization criticality. Furthermore a statistical approach for detection of indicators of self organized criticality is presented along with experiments and preliminary results showing the applicability of the approach.

Abstract: The talk will address a number of problematic issues in current multimedia technology and try to give some positive answers. The term multimedia is used for a mixture of modalities, at least one of them being continuous. In the center of interest are “natural” videos, taken by cameras.