Amrita Paper on Extracting Content Descriptive Metadata Published in International Journal of Intelligent Information Systems
A paper authored by Dr. Vidhya Balasubramanian, Associate Professor of the department of Computer Science and Engineering at the Amrita School of Engineering, Coimbatore was recently published in the international Journal of Intelligent Information Systems.
The Journal of Intelligent Information Systems: Integrating Artificial Intelligence and Database Technologies (JIIS) focuses on the integration of artificial intelligence and database technologies to create next generation information systems. JIIS provides a forum wherein academics, researchers and practitioners may publish high-quality, original and state-of-the-art papers describing theoretical aspects, systems architectures, analysis and design tools and techniques, and implementation experiences in intelligent information systems.
Dr. Vidhya’s paper titled, A multimodal approach for extracting content descriptive metadata from lecture videos addressed the problem of extracting content descriptive metadata for the purpose of supporting content based video lecture retrieval.
“The rise of modern learning methods, such as E-Learning, Open Course-wares and other distant learning programs, has led to an unprecedented increase in lecture videos and their usage. Lecture browsing systems, that aim to help users explore and access lecture videos, lack the support of a sophisticated information retrieval system,” explained Dr. Vidhya.
Most open courseware systems such as Berkeley webcasts (2013), MIT OCW 2013, NPTEL 2013 and Open Yale Courses 2013 are dependent largely on tags, annotations and limited user provided data for video retrieval.
“This paper aims at automatically extracting content descriptive metadata from spoken lecture videos so that this metadata can be used to support retrieval of both relevant documents and the segments that correlate best with the query. This can also help provide a better summarization of the video,” she stated.
Dr. Vidhya Balasubramanian’s paper proposed a multimodal metadata extraction system which extracts an optimal set of key phrases and topic based segments that effectively summarize the content of a lecture video.
The co-authors of the paper include Sooryanarayan Gobu Doraisamy and Navaneeth Kumar Kanakarajan, Research Associates at Amrita E-learning Research Center, and currently pursuing their masters. Sooryanarayan is pursuing his MBA from Amrita School of Business, Coimbatore campus and Navaneeth Kumar is pursuing his M. Tech. in Cyber Security, Coimbatore Campus.