Book contents' browsing and retrieval have been greatly facilitated by its Table-of-contents (ToC) and Index, respectively. Unfortunately, today's video lacks such powerful mechanisms. In this paper, we explor...
详细信息
Book contents' browsing and retrieval have been greatly facilitated by its Table-of-contents (ToC) and Index, respectively. Unfortunately, today's video lacks such powerful mechanisms. In this paper, we explore and present novel techniques for constructing video ToC and Index. Furthermore, we explore the relationship between video browsing and retrieval and propose a unified framework to incorporate both entities in a seamless way. Experimental results on real-world video clips justify our proposed framework for providing efficient access to video content.
Users of browsing applications often have vague information needs which can only be described in conceptual terms. Therefore, a video browsing system must accept conceptual queries for preselection and offer mechanism...
详细信息
Users of browsing applications often have vague information needs which can only be described in conceptual terms. Therefore, a video browsing system must accept conceptual queries for preselection and offer mechanisms for interactive inspection of the result set by the user. In this paper, we describe a MM-DBMS that we extended with the following components: The retrieval engine calculates relevance values for the results of a conceptual query by feature aggregation on video shot granularity to offer conceptual, content-based access. An intelligent client buffer strategy employs these relevance values to enable flexible user interactions during browsing. The admission control module admits whole browsing sessions by predicting required resources from query results to reduce startup delays within a session.
An audio-visual content analysis method is presented, which analyzes both auditory and visual information sources and accounts for their inter-relations and coincidence to extract high-level semantic information. Both...
详细信息
An audio-visual content analysis method is presented, which analyzes both auditory and visual information sources and accounts for their inter-relations and coincidence to extract high-level semantic information. Both shot-based and object-based access to the visual information is employed. Due to the temporal nature of video, time has to be accounted for. Thus, time-constrained video labelling functions are generated. Audio source parsing leads to the extraction of a speaker identity mapping function over time. Visual source parsing results in the extraction of a talking face shot mapping function over time. Integration of the audio and visual mappings constrained by interaction rules leads to more detailed video content descriptions and even partial detection of its context.
The Integrated multimedia Project (IMMP) studies interactive multimedia services and network technologies addressing both residential and business users, focusing on the overlaps and synergy between the two. For this ...
详细信息
The Integrated multimedia Project (IMMP) studies interactive multimedia services and network technologies addressing both residential and business users, focusing on the overlaps and synergy between the two. For this purpose, IMMP has set up and conducted a considerable number of trials with varying user profiles, network technologies, middleware components and applications. The trial network utilises multiple existing access networks such as Cable-TV and ISDN and connects to European ATM networks through the National Hosts. The IMMP consortium covers the complete interactive multimedia value chain by including network operators, service providers, equipment manufacturers, application developers and content providers. This paper presents project results with regard to market potential of interactive multimedia services, evaluation of different middleware technologies and end user feedback on the applications developed by IMMP.
Increasing use of multimedia data makes it crucial to use intelligent search mechanisms for retrieving multimedia data by content. Digital video requires the incorporation of temporal information for any effective con...
详细信息
Increasing use of multimedia data makes it crucial to use intelligent search mechanisms for retrieving multimedia data by content. Digital video requires the incorporation of temporal information for any effective content-based retrieval scheme. We present a trail-based model which uses the object motion information in order to characterize the events for subsequent searches for "similar" clips. algorithms for different spatio-temporal search modes using various digital signal processing techniques are also introduced. We implemented the proposed methods and demonstrated that high-level query formulation can be achieved for the aforementioned purpose.
This paper addresses the dual problem of audio coding for compression and retrieval. Because of the sheer volume of multimedia data, much research effort has focused on coding techniques for the compression of this da...
详细信息
This paper addresses the dual problem of audio coding for compression and retrieval. Because of the sheer volume of multimedia data, much research effort has focused on coding techniques for the compression of this data. However, being able to store large amounts of data in a compact fashion has limited application if there is no meaningful way to access and interact with them. Traditionally, these two issues have been treated separately resulting in many problems for multimedia data management. The authors have proposed a solution to these problems for audio by developing a compact, perceptually based, structured audio representation that provides explicit support for content based retrieval, browsing and other interactions. In addition, the representation offers potential for compressed data storage. This paper outlines a coding scheme based on the representation and reports the compression results.
This paper presents principles and algorithms for the management of a network of media servers. Such a server network allows the online delivery of broadband multimedia data, e.g. audio and video streams, to a large n...
详细信息
This paper presents principles and algorithms for the management of a network of media servers. Such a server network allows the online delivery of broadband multimedia data, e.g. audio and video streams, to a large number of widely distributed clients. Thus, the implementation of large scale distributed broadband media information services is possible if such networks can be handled efficiently. In the paper two new combinatorial optimization problems are defined that have to be solved for an efficient management of the distributed media servers connected by a high-bandwidth communication network. The algorithms consider the case of a static mapping of media assets onto the server network as well as the dynamic migration of media assets on such a network. The first scenario is used in the case that all media assets are loaded for the first time onto the server network. The second scenario is applied dynamically during run-time of an information service taking the varying user access pattern and changing media content of the server network into account. In this paper the algorithms are presented and their efficiency is demonstrated using some benchmark instances. The algorithms are part of a larger distributed system that allows the management of a network of distributed media servers. The principles of this system are presented as well as some applications that have been developed and are supported by this distributed server management system (DSMS).
Book contents' browsing and retrieval have been greatly facilitated by its Table-of-contents (ToC) and Index, respectively. Unfortunately, today's video lacks such powerful mechanisms. In this paper, we explor...
详细信息
Book contents' browsing and retrieval have been greatly facilitated by its Table-of-contents (ToC) and Index, respectively. Unfortunately, today's video lacks such powerful mechanisms. In this paper, we explore and present novel techniques for constructing video ToC and Index. Furthermore, we explore the relationship between video browsing and retrieval and propose a unified framework: to incorporate both entities in a seamless way. Experimental results on real-world video clips justify our proposed framework for providing efficient access to video content.
This paper presents an integrated framework for interactive content-based retrieval in video databases by means of visual queries. The proposed system incorporates algorithms for video shot detection, key-frame and sh...
详细信息
This paper presents an integrated framework for interactive content-based retrieval in video databases by means of visual queries. The proposed system incorporates algorithms for video shot detection, key-frame and shot selection, automated video object segmentation and tracking, and construction of multidimensional feature vectors using fuzzy classification of color, motion or texture segment properties. Retrieval is then performed in an interactive way by employing a parametric distance between feature vectors and updating distance parameters according to user requirements using relevance feedback. Experimental results demonstrate increased performance and flexibility according to user information needs.
Users of browsing applications often have vague information needs which can only be described in conceptual terms. Therefore, a video browsing system must accept conceptual queries for preselection and offer mechanism...
详细信息
Users of browsing applications often have vague information needs which can only be described in conceptual terms. Therefore, a video browsing system must accept conceptual queries for preselection and offer mechanisms for interactive inspection of the result set by the user. We describe a MM-DBMS that we extended with the following components. The retrieval engine calculates relevance values for the results of a conceptual query by feature aggregation on video shot granularity to offer conceptual, content based access. An intelligent client buffer strategy employs these relevance values to enable flexible user interactions during browsing. The admission control module admits whole browsing sessions by predicting required resources from query results to reduce startup delays within a session.
暂无评论