A Multidisciplinary Approach to Unlocking Television Broadcast Archives

Abstract

Audiovisual material is a vital component of the world's heritage but it remains diffi cult to access. With the Netherlands Institute for Sound and Vision as one of its partners, the MuNCH project aims to investigate new methods for improving access to a wide range of audiovisual documents. MuNCH brings together three research fi elds: multimedia analysis, language technology and semantic technologies.Within the MuNCH project, we have investigated several combinations of these fi elds. We have compared text matching, ontology querying, and semantic visual querying as methods to translate a multimedia query to the vocabulary of the retrieval system. In addition, we have investigated how users make such a translation, and have used this as a benchmark to create automatic methods. We have used multimedia technology to automatically detect objects and scenes as they occur in video, and made use of language technology to exploit automatic transcriptions of speech. We have enriched the Sound and Vision thesaurus that is used to annotate the TV programmes in order to provide a user with a wider range of search results.In order to verify the results of the project against real user needs, MuNCH has participated in the creation of a logging system which monitors the usage of the Sound and Vision catalogue system. Insights in the needs of real users will be used as input for all three of MuNCH's research strands.keywords Multimedia, Retrieval, Content-based image retrieval, Semantic web, Language technology, User queries 254 LAURA HOLLINK et al.

La Web Semántica y los archivos de televisión: estado de la cuestión

“…Este es en realidad un tema de investigación no bien resuelto (por su complejidad) y por lo tanto todavía abierto. El ejemplo más cercano a nuestra perspectiva (la de los archivos televisivos) nos lo proporcionan Hollink et al (2009 (Polo, 2011).…”

“…Esta es una perspectiva de interés para el presente proyecto, que además se ve enriquecida por el hecho de que el NISV también da servicio a profesionales, como productores y periodistas de diversos medios Holandeses. El acceso de estos usuarios al archivo tiene básicamente los mismos objetivos (conseguir material ilustrativo e informativo) que el que tiene lugar dentro de un archivo televisivo al uso (Hollink et al 2009), por lo que el proyecto en cuestión es doblemente interesante desde nuestra perspectiva.…”

“…El proyecto VideoActive está fundamentalmente centrado en la difusión del patrimonio audiovisual europeo, por lo que su relación con este proyecto es colateral, aunque es de interés para nuestro propósito la utilización de tecnologías derivadas de la Web Semántica como parte fundamental del mismo (Oomen et al, 2009). …”

A unified approach to content-based indexing and retrieval of digital videos from television archives

“…[2] In this scenario, content-based indexing approaches have been increasingly proposed, as alternative and promising solutions, which are based on the extraction of visual signatures for the key-frames of the videos of interest. [35,36] Those visual signatures essentially serve as the index terms and are commonly composed by features such as color, texture, shape, salient points and sketch, [36] which have demonstrated to be very important cues.…”

“…[1] In this scenario, huge digital video archives have been created by television companies, supporting for example, producers to store and edit new video productions, reporters to search relevant videos to re-use as background information and media researchers to investigate aspects of what has been broadcast. [2] Those video archives represent a vital component of the world's heritage and when combined with novel computing technologies have contributed to conceive new services around television and video platforms, such as Interactive TV [3] and Internet Television. [4][5][6] Specifically, when the Internet environment is considered, some challenging aspects must be faced with respect to procedures to highlight and share program-related materials, as well as the inclusion of user-generated content.…”