people

Eric Zavesky

Zavesky, Eric
9505 Arboretum Blvd #3S05B
Austin, TX
Subject matter expert in interactive video indexing and retrieval, multimedia content processing, multimodal interfaces, machine learning, biometrics, data mining, and natural language processing.

Eric Zavesky joined AT&T Labs Research in October 2009 as a Principle Member of Technical Staff.  At AT&T, he has collaborated on several projects to bring alternative query and retrieval representations to multimedia indexing systems including object-based query, biometric representations for personal authentication, and work to incorporate spatio-temporal information into near-duplicate copy detection.  His prior work at Columbia University studied semantic visual representations of content and low-latency, high-accuracy interactive search. 

Projects
Assistive Technology, At AT&T Labs - Research, we apply our speech, language and media technologies to give people with disabilities more independence, privacy and autonomy.

Connecting Your World, The need to be connected is greater than ever, and AT&T Researchers are creating new ways for people to connect with one another and with their environments, whether it's their home, office, or car.

Content Analytics - distill content into visual and statistical representations, Content analytics break down audio and video content into smaller visual or statistical representations for easier detection of anomalies, trends, and patterns.

Content Augmenting Media (CAM), Leverage multimedia metadata to provide live alerts and intelligent content consumption.

Content-Based Copy Detection, Content-based Copy Detection is an enabling technology to discover repeated content and events in a large-scale content database.

Enhanced Indexing and Representation with Vision-Based Biometrics, Leveraging visual biometrics for indexing and representations of content for retrieval and verification.

iMIRACLE - Content Retrieval on Mobile Devices with Speech, iMIRACLE uses large vocabulary speech recognition for content retrieval with metadata words (titles, genre, channels, etc.) and content words that occur in recorded programs.

MIRACLE and the Content Analysis Engine (CAE), The Multimedia Information Retrieval by Content (MIRACLE) project encompasses the technologies for video indexing, analysis, and retrieval with audio, textual, and visual content information.

VidCat - Simplified Personal Photo and Video Managmenet, VidCat permits simplified personal photo and video management (i.e. a Video Catalog) from a webpage or your favorite mobile device.

Video - Analytics and Indexing, A background on analytics and indexing (i.e. metadata), their production, and use. Links to projects within the AT&T Video and Multimedia Technologies and Research Department.

Video - Content Delivery and Consumption, A background on the delivery and consumption of video and multimedia and references to projects within the AT&T Video and Multimedia Technologies and Services Research Department.

Video and Multimedia Technologies Research, The AT&T Video and Multimedia Technologies Research Department strives to acquire multimedia and video for indexing,retrieval,and consumption with textual,semantic,and visual modalities.

Visual API - Visual Intelligence for your Applications, The Visual API provides Visual Intelligence to applications and developers through REST-based APIs powered by the AT&T Developer Program.

Visual Semantics for Intuitive Mid-Level Representations, Represent content with mid-level visual semantics for retrieval, filtering, and tagging.

Technical Documents

Appearance, Visual and Social Ensembles for Face Recognition in Personal Photo Collections
Eric Zavesky, Raghuraman Gopalan, Archana Sapkota
IEEE International Conference on Biometrics: Theory, Applications and Systems,  2013.  [PDF]  [BIB]

IEEE Copyright

AN AUGMENTED MULTI-TIERED CLASSIFIER FOR INSTANTANEOUS MULTI-MODAL VOICE ACTIVITY DETECTION
Dimitrios Dimitriadis, Eric Zavesky, Stevens Institute of Technology Matthew Burlick
Annual Conference of International Speech Communication Association (Interspeech) ,  2013.  [PDF]  [BIB]

International Speech Communication Association Copyright

Large-Scale Analysis for Interactive Media Consumption
David Gibbon, Andrea Basso, Lee Begeja, Zhu Liu, Bernard Renger, Behzad Shahraray, Eric Zavesky
TV Content Analysis,  TV Content Analysis,  CRC Press,  2012.  [PDF]  [BIB]

CRC Press, Taylor Francis LLC Copyright

Combining Content Analysis of Television Programs with Audience Measurement
David Gibbon, Zhu Liu, Eric Zavesky, DeDe Paul, Deborah Swayne, Rittwik Jana, Behzad Shahraray
IEEE Consumer Communication and Networking Conference, (CCNC),  2012.  [PDF]  [BIB]

IEEE Copyright

AT&T Research at TRECVID 2011
Eric Zavesky, Zhu Liu, Behzad Shahraray, Ning Zhou
TRECVID Workshop,  2011.  [PDF]  [BIB]

NIST Copyright

LipActs: Efficient Representations For Visual Speakers
Eric Zavesky
IEEE ICME,  2011.  [PDF]  [BIB]

IEEE Copyright

AT&T RESEARCH AT TRECVID 2010
Eric Zavesky, Behzad Shahraray, Zhu Liu, Neela Sawant
TRECVID 2010 Workshop,  2010.  [PDF]  [BIB]

NIST Copyright

Patents

Telepresence Simulation With Multiple Interconnected Devices, October 21, 2014
Calibrating Vision Systems, October 14, 2014
Method And Apparatus For Automated Analysis And Identification Of A Person In Image And Video Content, July 29, 2014
Brief And High-Interest Video Summary Generation, June 5, 2012

Publications

TV Content Analysis for Multiscreen Interactive Browsing and Retrieval
David Gibbon, Andrea Basso, Lee Begeja, Zhu Liu, Bernard Renger, Behzad Shahraray, Eric Zavesky
TV Content Analysis,  CRC Press,  2011.  [BIB]

Columbia University TRECVID2007 High-Level Feature Extraction
Shih-Fu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang Columbia University TRECVID2007 HighLevel Feature Extraction NIST TRECVID Workshop November  CUNIST_2007.xml  (0k)

Unsupervised Event Segmentation of News Content with Multimodal Cues
Mattia Broilo, Eric Zavesky, Andrea Basso, Francesco G. B. De Natale
AIEMPro’10 at ACM Multimedia,  2010.  [BIB]

Columbia University/VIREO-CityU/IRIT TRECVID2008 High-Level Feature Extraction and Interactive Video Search
Shih-Fu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang Columbia UniversityVIREOCityUIRIT TRECVID2008 HighLevel Feature Extraction and Interactive Video Search NIST TRECVID Workshop November  CUNIST_2008.xml  (0k)

AT&T RESEARCH AT TRECVID 2010
Zhu Liu, Eric Zavesky, Behzad Shahraray, Neela Sawant
2010.  [BIB]

Columbia University TRECVID-2006 Video Search and High-Level Feature Extraction
Shih-Fu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang Columbia University TRECVID2006 Video Search and HighLevel Feature Extraction NIST TRECVID Workshop November  CUTV_2006.xml  (0k)

A Guided, Low-Latency, and Relevance Propagation Framework for Interactive Multimedia Search
Zavesky, Eric
Graduate School of Arts and Sciences, Columbia University,  2010.  [BIB]

Columbia University's Semantic Video Search Engine
Shih-Fu Chang, ShihFu Chang, ShihFu Chang Columbia Universitys Semantic Video Search Engine ACM International Conference on Image and Video Retrieval July  ChangVideoSearch_2007.xml  (0k)

A Fast, Comprehensive Shot Boundary Determination System
Zhu Liu, Zhu Liu, Zhu Liu, Zhu Liu, Zhu Liu A Fast Comprehensive Shot Boundary Determination System IEEE International Conference on Multimedia and Expo July 1487--1490  EZ_ICME_2007.xml  (0k)

Visual Islands: Intuitive Browsing of Visual Search Results
Eric Zavesky, Shih-Fu Chang, Cheng-Chih Yang
ACM International Conference on Image and Video Retrieval,  pp 617--626,  2008.  [BIB]

Searching Visual Semantic Spaces with Concept Filters
Eric Zavesky, Eric Zavesky, Eric Zavesky, Eric Zavesky Searching Visual Semantic Spaces with Concept Filters IEEE International Conference on Semantic Computing September  EZ_icsc_2007.xml  (0k)

CuZero: Embracing the Frontier of Interactive Visual Search for Informed Users
Eric Zavesky, Shih-Fu Chang
ACM Multimedia Information Retrieval,  2008.  [BIB]

Unsupervised Event Segmentation of News Content with Multimodal Cues
Mattia Broilo, Mattia Broilo, Mattia Broilo, Mattia Broilo Unsupervised Event Segmentation of News Content with Multimodal Cues AIEMPro10 at ACM Multimedia October  TD-100119.xml  (0k)

Cross-Domain Learning Methods for High-Level Visual Concept Classification
Wei Jiang, Eric Zavesky, Shih-Fu Chang, Alex Loui
IEEE International Conference on Image Processing,  2008.  [BIB]

AT&T RESEARCH AT TRECVID 2010
Zhu Liu, Zhu Liu, Zhu Liu, Zhu Liu ATT RESEARCH AT TRECVID 2010 November  TD-100255.xml  (0k)

AT&T RESEARCH AT TRECVID 2010
Zhu Liu, Zhu Liu, Zhu Liu, Zhu Liu ATT RESEARCH AT TRECVID 2010 November  TD_100255.xml  (0k)

Columbia University/VIREO-CityU/IRIT TRECVID2008 High-Level Feature Extraction and Interactive Video Search
Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky
NIST TRECVID Workshop,  2008.  [BIB]

Columbia University TRECVID-2005 Video Search and High-Level Feature Extraction
Shih-Fu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang, ShihFu Chang Columbia University TRECVID2005 Video Search and HighLevel Feature Extraction NIST TRECVID workshop November  chang_trecvid05.xml  (0k)

Searching Visual Semantic Spaces with Concept Filters
Eric Zavesky, Zhu Liu, David Gibbon, Behzad Shahraray
IEEE International Conference on Semantic Computing,  2007.  [BIB]

Cross-Domain Learning Methods for High-Level Visual Concept Classification
Wei Jiang, Wei Jiang, Wei Jiang, Wei Jiang CrossDomain Learning Methods for HighLevel Visual Concept Classification IEEE International Conference on Image Processing October  crossdomain_icip2008.xml  (0k)

Columbia University's Semantic Video Search Engine
Shih-Fu Chang, Lyndon Kennedy, Eric Zavesky
ACM International Conference on Image and Video Retrieval,  2007.  [BIB]

CuZero: Embracing the Frontier of Interactive Visual Search for Informed Users
Eric Zavesky, Eric Zavesky CuZero Embracing the Frontier of Interactive Visual Search for Informed Users ACM Multimedia Information Retrieval October  cuzero08_ez.xml  (0k)

Searching Visual Semantic Spaces with Concept Filters
Eric Zavesky, Eric Zavesky, Eric Zavesky, Eric Zavesky Searching Visual Semantic Spaces with Concept Filters September 329-336 IEEE International Conference on Semantic Computing ICSC 2007  dg20070901120000.xml  (0k)

Columbia University TRECVID2007 High-Level Feature Extraction
Shih-Fu Chang, Wei Jiang, Akira Yanagawa, Eric Zavesky
NIST TRECVID Workshop,  2007.  [BIB]

TV Content Analysis for Multiscreen Interactive Browsing and Retrieval
David Gibbon, David Gibbon, David Gibbon, David Gibbon, David Gibbon, David Gibbon, David Gibbon TV Content Analysis for Multiscreen Interactive Browsing and Retrieval TV Content Analysis June CRC Press  dg20110601120000.xml  (0k)

Columbia University TRECVID-2006 Video Search and High-Level Feature Extraction
Shih-Fu Chang, Winston, Wei Jiang, Lyndon Kennedy, Dong Xu, Akira Yanagawa, Eric Zavesky
NIST TRECVID Workshop,  2006.  [BIB]

Visual Islands: Intuitive Browsing of Visual Search Results
Eric Zavesky, Eric Zavesky, Eric Zavesky Visual Islands Intuitive Browsing of Visual Search Results ACM International Conference on Image and Video Retrieval 617--626  visisland_ez.xml  (0k)

Columbia University TRECVID-2005 Video Search and High-Level Feature Extraction
Shih-Fu Chang, Winston Hsu, Lyndon Kennedy, Lexing Xie, Akira Yanagawa, Eric Zavesky, Dongqing Zhang
NIST TRECVID workshop,  2005.  [BIB]

A Guided, Low-Latency, and Relevance Propagation Framework for Interactive Multimedia Search
Zavesky, Zavesky A Guided LowLatency and Relevance Propagation Framework for Interactive Multimedia Search Graduate School of Arts and Sciences Columbia University  zavesky_phdthesis.xml  (0k)


graphviz

Connections

Graphviz