In this paper, we will propose a novel semi-automatic annotation scheme for video semantic classification. It is well known that the large gap between high-level semantics and low...
Social tagging can provide rich semantic information for largescale retrieval in music discovery. Such collaborative intelligence, however, also generates a high degree of tags un...
Zhendong Zhao, Xinxi Wang, Qiaoliang Xiang, Andy M...
We investigate methods of segmenting, visualizing, and indexing presentation videos by both audio and visual data. The audio track is segmented by speaker, and augmented with key ...
In order to solve medical multimodal queries, we propose to split the queries in different dimensions using ontology. We extract both textual and visual terms depending on the ont...
Cataloging a large, multi-media collection of traditional song and drama in preparation for online presentation highlights issues of song identity and access in the context of con...