Víctor Valdés

Binary tree based on-line video summarization

This paper describes our method for the TRECVID 2008 BBC rushes summarization task, a fully on-line video abstraction algorithm with customizable memory and computation requirements which enables the application of different abstraction criteria. The algorithm is based on the dynamic generation of binary trees which model the different choices for abstract output. In this work the generic abstraction algorithm as well as the specific abstraction criteria applied for the BBC rushes summarization task are presented together with an overview of the algorithm capabilities.

Multimedia content adaptation within the CAIN framework via constraints satisfaction and optimization

This paper presents a constraints programming based approach to decide which of a set of available content adaptation tools and parameters should be selected in order to perform the best adaptation of a media asset targeting to enhance the final users experience in a particular usage scenario. The work is within the scope of the Universal Multimedia Access (UMA) framework and makes use of MPEG standards for content and usage environment description. The proposed technique has been evaluated within the CAIN framework, a content adaptation engine that integrates different content adaptation tools, and that uses media and usage environment metadata to identify the best adaptation tool from the available ones. First, mandatory constraints are imposed. If there is more than one adaptation tool capable of adapting the content fulfilling every mandatory constraint, another group of desirable constraints are applied to reduce the solution space. If at this step there are still several adaptation tools or parameter values able to adapt the content fulfilling mandatory and desirable restrictions, a final optimization step chooses the best adaptation tool and parameters.

On-line video skimming based on histogram similarity

This paper describes the method proposed for the TRECVID 2007 BBC rushes summarization task. Such method has been developed starting from an on-line summary generation approach which provides a fast way to generate a base summary that can be later reduced with an off-line summarization technique if the target summary size is not reached. The summarization algorithms aim to reduce the visual redundancy of the video by methods based on color similarity features and targeting to the generation of connected video skims (instead of providing isolated keyframes). The on-line summarization process provides a very fast method with low memory usage for video summary creation.

Efficient video summarization and retrieval tools

In this paper we describe the video browsing and retrieval techniques included within the ASSETS project system, focused on providing enhanced access to video repositories. The proposed mechanisms aims to provide efficient and reusable techniques for browsing and retrieval, trying to minimize the computational and storage cost of the approach while offering novel functionalities such as personalized/real-time video summarization. The system is under design and development within the ASSETS project that deals with advanced tools for accessing to cultural content.

Automatic evaluation of video summaries

This article describes a method for the automatic evaluation of video summaries based on the training of individual predictors for different quality measures from the TRECVid 2008 BBC Rushes Summarization Task. The obtained results demonstrate that, with a large set of evaluation data, it is possible to train fully automatic evaluation systems based on visual features automatically extracted from the summaries. The proposed approach will enable faster and easier estimation of the results of newly developed abstraction algorithms and the study of which summary characteristics influence their perceived quality.

A framework for video abstraction systems analysis and modelling from an operational point of view

Nowadays the huge amount of video material stored in multimedia repositories makes its search and retrieval a very slow and usually difficult task. Existing video abstraction systems aim to relieve this problem by providing short versions of the original content which ease the search and navigation processes and reduce the browsing time. There are many approaches for video abstraction based on the optimal selection and presentation of a subset of fragments (keyframes, shots, etc.) from the original video attending to different criteria, usually dependent on the application scenario. Nevertheless, given the huge size and growth rate of existing video repositories there is an increasing need for providing efficient techniques. This paper presents a unified taxonomy and a generic architectural model aimed for the study of existing abstraction systems computational performance and characteristics. The taxonomy has been developed taking into account and identifying the operative characteristics of current state of the art video abstraction techniques. The proposed video abstraction architecture model characterizes the stages needed to build a generic abstraction process and establishes the basic architectural aspects and requirements for the modeling of systems with specific operative requirements.

Content adaptation capabilities description tool for supporting extensibility in the CAIN framework

This paper presents Adaptation Capabilities Description proposed for easing the extensibility within the Content Adaptation Integrator (CAIN), an extensible multi-format content adaptation module aimed to provide audiovisual content adaptation based on user, network and platform requirements. This module aims to work transparently and efficiently with several content adaptation approaches such as transcoding or scalable content adaptation.

On-line video abstract generation of multimedia news

The amount of video content available nowadays makes video abstraction techniques a necessary tool to ease the access to the already huge and ever growing video databases. Nevertheless, many of the existing video abstraction approaches have high computational requirements, complicating the integration and exploitation of current technologies in real environments. This paper presents a novel method for news bulletin abstraction which combines on-line story segmentation, on-line video skimming and layout composition techniques. The developed algorithm provides an efficient, automatic and on-line news abstraction method which takes advantage of the specific characteristics of news bulletins for obtaining representative news abstracts.

On-Line Video Summarization Based on Signature-Based Junk and Redundancy Filtering

The huge amount of video content and the increasing rate in which new content is being created makes video summarization a necessary tool for the efficient access and management of video repositories. Nevertheless, the huge amount of data and the complexity of current techniques make the implantation of the summarization systems a difficult or non practical task. This paper presents current advances in the development of a novel algorithm for on-line video summarization, which can be easily used also as a video retrieval tool, aimed to combine summarization quality with high computational efficiency providing a system that can be practical for both commercial and home environments.

Content adaptation tools in the CAIN framework

This paper presents the Content Adaptation Tools currently integrated in the CAIN framework, a content adaptation manager targeted to the integration of different metadata-driven content adaptation approaches. The CAIN system is in charge of managing the available content adaptation tools in order to perform the most appropiate adaptation modality taking account of the available content metadata. Current system architecture and adaptation process are presented detailing the decision process about adaptation parameters and adaptation tool selection taken in order to perform content adapatation. The different Content Adaptation Tools types are presented together with details of the currently integrated adaptation tools.