RETIN: a smart interactive digital media retrieval system

2003

Static multimedia on the Web can already be hardly structured manually. Although unavoidable and necessary, manual annotation of dynamic multimedia becomes even less feasible when multimedia quickly changes in complexity, i.e. in volume, modality, and usage context. The latter context could be set by learning or other purposes of the multimedia material. This multimedia dynamics calls for categorisation systems that index, query and retrieve multimedia objects on the fly in a similar way as a human expert would. We present and demonstrate such a supervised dynamic multimedia object categorisation system. Our categorisation system comes about by continuously gauging it to a group of human experts who annotate raw multimedia for a certain domain ontology given a usage context. Thus effectively our system learns the categorisation behaviour of human experts. By inducing supervised multi-modal content and context-dependent potentials our categorisation system associates field strengths ...

Database Semantics, 1999

Easy access to multimedia information is important as the amount of information is exponentially growing. Content-based retrieval is a viable approach. Extensibility and flexibility of data models is another important issue as the field is constantly evolving. The ADMIRE framework applied in this paper satisfies both criteria. This we show in two practical cases, one in the field of clinical assessments of measurement data, the other in the field of video directory services. ADMIRE offers a uniform solution for structuring these data. Content disclosure is supported by labelling of these data structures. This is done by automatic, semi-automatic or manual labelling.

2003

Static multimedia on the Web can already be hardly structured manually. Although unavoidable and necessary, manual annotation of dynamic multimedia becomes even less feasible when multimedia quickly changes in complexity, i.e. in volume, modality, and usage context. The latter context could be set by learning or other purposes of the multimedia material. This multimedia dynamics calls for categorisation systems that index, query and retrieve multimedia objects on the fly in a similar way as a human expert would. We present and demonstrate such a supervised dynamic multimedia object categorisation system. Our categorisation system comes about by continuously gauging it to a group of human experts who annotate raw multimedia for a certain domain ontology given a usage context. Thus effectively our system learns the categorisation behaviour of human experts. By inducing supervised multi-modal content and context-dependent potentials our categorisation system associates field strengths of raw dynamic multimedia object categorisations with those human experts would assign. After a sufficient long period of supervised machine learning we arrive at automated robust and discriminative multimedia categorisation. We demonstrate the usefulness and effectiveness of our multimedia categorisation system in retrieving semantically meaningful soccer-video fragments, in particular by taking advantage of multimodal and domain specific information and knowledge supplied by human experts.

Storage and Retrieval for Media Databases 2003, 2003

Static multimedia on the Web can already be hardly structured manually. Although unavoidable and necessary, manual annotation of dynamic multimedia becomes even less feasible when multimedia quickly changes in complexity, i.e. in volume, modality, and usage context. The latter context could be set by learning or other purposes of the multimedia material. This multimedia dynamics calls for categorisation systems that index, query and retrieve multimedia objects on the fly in a similar way as a human expert would. We present and demonstrate such a supervised dynamic multimedia object categorisation system. Our categorisation system comes about by continuously gauging it to a group of human experts who annotate raw multimedia for a certain domain ontology given a usage context. Thus effectively our system learns the categorisation behaviour of human experts. By inducing supervised multi-modal content and context-dependent potentials our categorisation system associates field strengths of raw dynamic multimedia object categorisations with those human experts would assign. After a sufficient long period of supervised machine learning we arrive at automated robust and discriminative multimedia categorisation. We demonstrate the usefulness and effectiveness of our multimedia categorisation system in retrieving semantically meaningful soccer-video fragments, in particular by taking advantage of multimodal and domain specific information and knowledge supplied by human experts.

Methods, Standards and Tools, 2005

By the end of the last century the question was not whether digital archives are technically and economically viable, but rather how digital archives would be efficient and informative. In this framework, different scientific fields such as, on the one hand, development of database management systems, and, on the other hand, processing and analysis of multimedia data, as well as artificial and computational intelligence methods, have observed a close cooperation with each other during the past few years. The attempt has been to develop intelligent and efficient human-computer interaction systems, enabling the user to access vast amounts of heterogeneous information, stored in different sites and archives.