427 East End Ave, Pittsburgh PA, 15221
To further the science of computer vision and multimedia understanding.
Employment and Accomplishments
Informedia, Carnegie Mellon University (September 1997 – Present)
Informedia is a Digital Video Library indexing over five years of news, documentary, and personal experience video.
Named Entity Connection Graph
Designed and implemented an end to end system for summarizing large video sets using Named Entities and their implicit connections inside the text.
Designed and built the Digital Video Library Query Engine, a distributed balanced multimedia search infrastructure.
Various color and texture histogram based search engine.
Designed to abstract search engine concepts to allow quick additions of new engines.
Clients in C, Visual Basic, Perl, and Java.
Support Vector Machine classifier of News Anchors from CNN news.
Digital Human Memory
Prototype wearable computing system that combines video, audio and GPS to augment human memory.
Image Search Engines
Designed and built robust image search engine starting from image processing to indexing to searching.
General Motors Infoscout
Constructed a proof of concept of networked intelligent in car audio player with working knowledge of location.
TOM File Conversion Service
Aided in creation of the Typed Object Model (TOM) service, a networked program that knows how to convert files of some type to other types. This allows WebTV users to read Word files, Windows users to view Postscript, and Lynx user to decode Mac BinHex files.
Created early Powerpoint™ to HTML, Word™ to Postscript, Word™ to PDF, and other similar features.
Languages (from most comfortable to least)
C, C++, C#, Perl, Java, Python, Visual Basic 6, SQL, PHP, SML/CML, Matlab, csh
Oracle 8i SQLplus, ODBC (C interface)
Microsoft Visual Studios 6, Windows 95/98/NT/2000, Emacs, gccLinux
Proficient in Word, Powerpoint, and Excel. Familiar with the theory and practice of current techniques of Machine Learning.
Carnegie Mellon University, Pittsburgh, PA. May 2002
Bachelors of Science in Computer Science with a minor in Photography and Digital Imagining.
Papernick, N., Hauptmann, A., AAAI Workshop on Link Analysis (AAAI’05), Pittsburgh, PA, July 9-13, 2005.
Exploiting Multiple Modalities for Interactive Video Retrieval
Christel, M., Papernick, N., Huang, C., Moraveji, N., International Conference on Acoustics, Speech and Signal Processing (ICASSP'04), Montreal, Quebec, Canada, May 17-21, 2004.
Informedia at TRECVID 2003: Analyzing and Searching Broadcast News Video
Hauptmann, A., Ng, D., Baron, R., Chen, M-Y., Christel, M., Duygulu, Huang, C., Lin, W-H., Wactlar, H., Moraveji, N., Papernick, N., Snoek, C.G.M., Tzanetakis, G., Yang, J., Yan, R., Jin, R., Proceedings of (VIDEO) TREC 2003 (Twelfth Text Retrieval Conference), Gaithersburg, MD, November 17-21, 2003.
Duygulu, P., Ng, D., Papernick, N., Wactlar, H., Workshop on Multimedia Contents in Digital Libraries, Crete, Greece, June 2-3, 2003.
Duygulu, P., Papernick, N., Ozcanli, O., 18th International Symposium on Computer and Information Sciences (ICIS'03), Antalya, Turkey, November 3-5, 2003.
Hauptmann, A., Christel, M., Papernick, N. Proceeding of the second ACM/IEEE-CS joint conference on Digital libraries (JCDL), Portland, Oregon, July 14-19, 2002 : 376.
Hauptmann, A., Papernick, N. Proceeding of the second ACM/IEEE-CS joint conference on Digital libraries (JCDL) Portland, Oregon, July 14-19, 2002 : 156 – 157.
Hauptmann, A., Thornton, S., Houghton, R., Qi, Y., Ng, D., Papernick, N., Jin, R., Proceedings of the Tenth Text Retrieval Conference (TREC-2001), Gaithersburg, Maryland, November 13-16, 2001.
Creating an interactive map of where a person can safely bike in the city of Pittsburgh based on a bike mounted GPS receiver.
“Image Understanding: to show a computer a picture of a Doberman and picture of a German Shepherd and have it understand that they are both Dogs.”