John R. Smith  John R. Smith photo       

contact information

IBM Fellow, Manager, Multimedia and Vision
IBM Thomas J. Watson Research Center, Yorktown Heights, NY 10598


Professional Associations

Professional Associations:  ACM  |  ACM SIGMM  |  Fellow, IEEE  |  IEEE Circuits and System Society  |  IEEE Computer Society  |  IEEE Signal Processing Society

more information

More information:  John R. Smith on Google Scholar  |  John R. Smith on DBLP  |  John R. Smith on LinkedIn  |  John R. Smith on Twitter


Dr. John R. Smith is IBM Fellow and Manager of Multimedia and Vision at IBM T. J. Watson Research Center.  He leads IBM’s Research & Development on image and video analysis and understanding including:

Dr Smith previously was Senior Manager, Intelligent Information Systems and was Principal Investigator for multiple R&D projects on multimedia and vision including:

  • IARPA ALADDIN ("Video Event Modeling and Retrieval based on Discriminative Semantic Features")
  • DTO/IARPA VACE-III ("Analyst Centric Workbench for Large Scale Cross Domain Video Intelligence")
  • DTO LSCOM ("Large Scale Concept Ontology for Multimedia")
  • ARDA VACE-II ("Reconstructing and Mining of Semantic Threads Across Multiple Video Broadcast News Sources using Multi-level Concept Modeling")

Dr. Smith was a founding participant and served on the Advisory Committee for the NIST TRECVID Video Retrieval Evaluation.  His research teams at IBM have participated in TRECVID evaluations for more than a decade.

Dr. Smith was co-General Chair of ACM Intl. Conf. on Multimedia Retrieval (ICMR-2016) in New York City. 

Previously, he was Editor-in-Chief of IEEE Multimedia from 2010 – 2014, Associate Editor-in-Chief from 2006 – 2010 and Standards Editor from 2003 – 2006.

Earlier Dr. Smith led IBM's participation in MPEG-7 / MPEG-21 standards and  was Chair of the MPEG Multimedia Description Schemes Sub-Group and co-project Editor of MPEG-7 Standard.

Historically, with Prof. Shih-Fu Chang at Columbia University, Dr. Smith developed some of the earliest approaches for content-based image and video retrieval, including:

  • VisualSEEk - content-based image retrieval system
  • WebSEEk - one of the first image and video search engines for the Web in 1995!

Ph.D. Dissertation:

Dr. Smith is a Fellow of IEEE.

Recent activities:




          - 4th Multimedia and Vision Meeting in Greater New York Area, October 2014

          - 3rd Multimedia and Vision Meeting in Greater New York Area, June 2013

          - 2nd Multimedia and Vision Meeting in Greater New York Area, June 2012

          - 1st Multimedia and Vision Meeting in Greater New York Area, February 2012

Editor-in-Chief articles for IEEE MultiMedia (2010 - 2014):