Whereas most existing action recognition methods require computationally demanding feature extraction and/or classification, this paper presents a novel real-time solution that ut...
Efficient multimodal fusion is a key feature of future video indexing systems. Hidden Markov Models provide a powerful framework for video structure analysis but they require all...
We propose using truncated object-object similarity matrix as an access structure for interactive video retrieval. The proposed approach offers a scalable solution to retrieval an...
The identification and analysis of the knowledge available in document form is a key element of corporate knowledge management. In engineering-intensive organizations, it involves...
This paper presents techniques for multimedia annotation and their application to video summarization and translation. Our tool for annotation allows users to easily create annota...