UCSB ECE Ph.D Candidate
Advisor: B. S. Manjunath
Research Interests
Multimedia, multimedia information retrieval, computer vision, object detection, object tracking, video summarization, data mining, machine learning, multimodal fusion, image & signal processing and analysis.
Background
I completed a B.S.E.E.(1998) and M.S.E.E.(2000) at Rutgers University in my home state of New Jersey. As a graduate assistant at Rutgers I worked on speech and microphone arrays in Jim Flanagan's lab. My master's thesis addressed the topic of how to incorporate face detection with speaker location estimates for automatic hands-free videoconferencing.
In 2000, I took a position at Intel in Chandler, Arizona, in a DSP apps and architecture group. My job entailed writing IPP libraries for the jointly developed Analog Devices/Intel Micro Signal Architecture chip. Machine level opcodes haunt me in my sleep.
I spent the years 2002 to 2004 in the wild on an around the world journey :>.
In Fall of '05, I reemerged at Santa Barbara, California, where I accepted a NSF fellowship in digital multimedia and began my Ph.D. studies.
In Fall 2007, I worked as an intern at Microsoft Research Asia in Beijing in Wei Ying Ma's Web Search and Mining group. I passed my qualifier exam in July 2008. My thesis contributes methods for improving bag-of-local-feature methods for image retrieval, fast indexing, and georeferenced image annotation.
Publications at UCSB
- J. Kleban, E. Moxley, J. Xu, and B. S. Manjunath, "Global Annotation of Georeferenced Photographs." In Proceedings of ACM Conference on Image and Video Retrieval, Greece, 2009.pdf
- E. Moxley, J. Kleban, J. Xu, and B. S. Manjunath, "Not All Tags Are Created Equal: Learning Flickr Tag Semantics for Global Annotation." In Proceedings of IEEE International Conference on Multimedia and Expo, New York, 2009. pdf
- J. Kleban, E. Moxley, B. S. Manjunath, "SpiritTagger: A Location-Aware Interactive Web Tool for Annotating Your Photo Collection." The Future of Interactive Media: Workshop on Media Arts, Science, and Technology (MAST), Santa Barbara CA, Jan 2009.
- Dan Overholt, John Thompson, Lance Putnam, Bo Bell, Jim Kleban, Bob Sturm, and JoAnn Kuchera-Morin, "A Multimodal System for Gesture Recognition in Interactive Music Performance." To appear in Computer Music Journal 33:4 (Winter 2009).
- E. Moxley, J. Kleban, B. S. Manjunath, "SpiritTagger: A Geo-Aware Tag Suggestion Tool Mined from Flickr." In Proceedings of ACM International Conference on Multimedia Information Retrieval (MIR2008), Vancouver, Canada, Oct. 2008.pdf
- J. Kleban, X. Xie, and W. Y. Ma, "Spatial Pyramid Mining for Logo Detection in Natural Scenes." In Proceedings of the International Conference on Multimedia and Expo (2008), Hannover, Germany. pdf
- E. D. Gelasca, S. Joshi, J. Kleban, S. Mangiat, B.S. Manjunath, E. Moxley, A. Sarkar, and J. Xu, "The Vision Research Lab of UCSB at TRECVID 2007", in NIST TRECVID-2007 Workshop, Gaithersburg, MD, November 2007. pdf
- J. Kleban, A. Sarkar, E. Moxley, S. Mangiat, S. Joshi, T. Kuo, and B. S. Manjunath, "Feature fusion and redundancy pruning for rush video summarization." In Proceedings of the International Workshop on TRECVID Video Summarization - ACM-MM, Augsburg, Germany, 2007. pdf
- B. Bell, J. Kleban, D. Overholt, L. Putnam, J. Thompson, and J. Kuchera-Morin, "The multimodal music stand." In Proceedings of the 7th international Conference on New interfaces For Musical Expression (NIME), New York, 2007. pdf