Supervised multimedia categorization

Abstract

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.

Advanced Semantic Management of Digital Resources

“…This classification mapping produced effective indexes used by search engines and retrieval systems over bibliographical archives or digital databases. Among the research results in this area, Frank Aldershoff et al [1] showed that categories help the users to navigate inside the digital data collections. By grouping the data via comprehensible categories, the users can quickly eliminate the non-relevant or non-interesting data.…”

Digital Resource Semantic Management of Islamic Buildings Case Study on Isfahan Islamic Architecture Digital Collection

“…The multifaceted metadata has been created by mapping the attributes in the AAT hierarchy avoiding overlapping similar attributes. As part of the IIAD collection, we selecting mosque collection for this study to point out and to address three issues related to the usage of attributes from multiple metadata sets: (1) Similarity between attributes, (2) Specialization between attributes, and (3) Attributes categorization by subject.…”

“…They are used for effective classification and searching for digital resources in bibliographical, digital databases and visual archives. Categories help the users to navigate inside the digital data collections [1]. By grouping the data by comprehensible categories, the users can quickly eliminate what is not relevant or not interesting, and just look at the subject related to their interest.…”

Digital Resource Semantic Management of Islamic Buildings Case Study on Isfahan Islamic Architecture Digital Collection

“…The Resource Categorisation Path is denoted RCP. Each node of the path (denoted α i ) is associated with a topic name and a list of descriptors (denoted δ), we defined RCP as (1) where δ i,j represents the j th descriptor of the ith node, n is the number of nodes and p the number of descriptors in the ith node.…”