Event Location: NSH 1305
Bio: Ajay Divakaran (SM’00) received the B.E. (with Hons.) degree in
Electronics and Communication Engineering from the University of Jodhpur,
Jodhpur, India, in 1985, and the M.S. and Ph.D. degrees from Rensselaer
Polytechnic Institute, Troy, NY in 1988 and 1993 respectively. He was an
Assistant Professor with the Department of Electronics and Communications
Engineering, University of Jodhpur, India, in 1985-86. He was a Research
Associate at the Department of Electrical Communication Engineering,
Indian Institute of Science, in Bangalore, India in 1994-95. He was a
Scientist with Iterated Systems Inc., Atlanta, GA from 1995 to 1998. He
joined MERL in 1998 and is now a Senior Team Leader – Senior Principal
Member of Technical Staff. He leads the Data and Sensor Systems Group at
MERL-TL. He has been an active contributor to the MPEG-7 video standard.
His current research interests include video and audio analysis,
summarization, indexing and compression, and equipment condition
monitoring. He has published several journal and conference papers, as
well as six invited book chapters on video indexing and summarization. He
has co-supervised four doctoral theses. He currently serves on program
committees of key conferences in the area of multimedia content analysis.
He has also coauthored a book titled “A Unified Framework for Video
Summarization, Browsing and Retrieval” (Elsevier Academic Press).

Abstract: We present the world’s first highlights-playback-capable Hard Disk Drive
(HDD)-enhanced DVD recorder. It automatically detects highlights in sports
video by detecting portions with a mixture of the commentator’s excited
speech and cheering, using Gaussian Mixture Models (GMM’s) trained using
the MDL criterion. Our computation is carried out directly on the MDCT
coefficients from the AC-3 coefficients thus giving us a tremendous speed
advantage. Our accuracy of detection of sports highlights is high across a
variety of sports. Our user-study shows that viewers like the new
functionality even if it makes mistakes. Finally, we propose
genre-independent temporal segmentation of non-sports content using
computationally inexpensive audio-visual features. Such segmentation
enables “smart skipping,” from one semantic unit to another.