Milind R. Naphade's Home Page

Image Formation and Processing Group Beckman Institute,

University of Illinois at Urbana-Champaign



I joined the Department of Electrical and Computer Engineering at the University of Illinois at Urbana Champaign. in Fall 96. I was a research assistant in the Image Formation and Processing group (IFP), and a fellow of the Computational Sciences and Engineering Department under the auspices of the College of Engineering. The IFP group is a part of the Human Computer Intelligent Interaction theme at the Beckman Institute for Advanced Science and Technology. My advisor is Prof. Thomas S. Huang, who directs the Human Computer Intelligent Interaction theme at the Beckman Institute. I obtained my M.S. and Ph.D. in Electrical Engineering in October 1998 March 2001 respectively. I was a summer intern with Eastman Kodak Research Labs and Intel's Microcomputer Research Labs. 

On the right is a picture of me and Deepti in the backdrop of the Taj Mahal.   

I have joined the Pervasive Media Management Group as a Research Staff Member at the IBM T J Watson Research Center in April 2001 after completing my Ph.D. I will continue to update this site till I can externalize my IBM site. My recent publications are also listed below in the Publications link. At IBM, I continue to work on semantic multimedia understanding and furthering the research that I began at UIUC.

Current Coordinates

Milind R. Naphade

Research Staff Member

Pervasive Media Management Group

IBM Thomas J. Watson Research Center

19 Skyline Drive, Hawthorne, NY 10532

Phone: 9147847032

Fax: 9147847455

My research interests include Multimedia analysis and fusion for indexing and retrieval in video databases, pattern recognition with applications to speech and video data and graphical probabilistic models for recognition. I finished my Master's degree in Electrical and Computer Engineering from the University of Illinois at Urbana- Champaign in August 1998. I also passed my preliminary research proposal examination in February 2000. At present, I am actively involved in various research issues related to the semantic indexing of video using multiple modalities in a statistical framework.  Here at Beckman, we are trying to bridge the gap between low-level physical features and high-level semantics.  For my academic and industrial background, you are welcome to take a look at my Curriculum Vitae

Cricket  is my favorite sport. I am a die-hard fan of Indian Cricket and a great fan of Sachin Tendulkar like millions of my fellow Indians. I hail from Pune, the cultural and educational capital of Western India. Apart from the Center for Development of Advanced Computing (CDAC), I have worked at the Eastman Kodak Company's Kodak Research labs in Rochester, NY and at the Intel Corporation's Microcomputer research labs in Santa Clara, CA.

Publications Talks & Patents




1.     Ph.D. Thesis:


2.     NIST TREC Video:

This is a NIST Benchmark for measuring the performance of video retrieval systems using semantic queries. This benchmark provides a good opportunity for evaluating algorithms for semantic analysis. I am applying the framework of multijects and multinets to this benchmark at IBM and our participation in the past 2 years has been full of exciting experiments. Details of these experiments have and will continue to appear in our publications some of which are listed in the Publications Section above.


3.     ICME 2003 Tutorial:

Along with Prof. Edward Chang of UCSB and John Smith, IBM Research, I will present a tutorial at the International Conference on Multimedia

2003 in Baltimore, MD. Slides from the tutorial will be available for download after the conference.


4.     My IBM Research Home Page:

Latest updates on research at IBM Research and current projects