579 Hits in 2.9 sec

Columbia University's semantic video search engine

Shih-Fu Chang, Lyndon S. Kennedy, Eric Zavesky
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
We briefly describe "CuVid," Columbia University's video search engine, a system that enables semantic multimodal search over video broadcast news collections.  ...  Our focus is on comparative studies of pros and cons of search methods built on various individual modalities (keyword, image, near-duplicate, and semantic concept) and combinations, without requiring  ...  INTRODUCTION The Columbia video search system provides a platform for users to semantically search and browse broadcast news video corpora through a simple interface which can be accessed with any modern  ... 
doi:10.1145/1282280.1282371 dblp:conf/civr/ChangKZ07 fatcat:qysqx5tckvfa7chbd55h5egunu

Eval-ware: digital video retrieval

P. Over, A. Smeaton, A. Docef
2006 IEEE Signal Processing Magazine  
Among the online demos from Columbia University's Digital Video Multimedia Lab, the CuVid system is an interactive search engine for broadcast news video that has been developed for TRECVID 2005.  ...  s major Web search engines have started to provide video search capabilities as part of their services, it is of particular interest to revisit the topic of video retrieval.  ... 
doi:10.1109/msp.2006.1708421 fatcat:k52moyxj2vf7rdtel5gogrg4jq

Improving Discovery of and Access to Digital Repository Contents Using Semantic Web Standards: Columbia University's Academic Commons

Robert J. Hilliker, Melanie Wacker, Amy L. Nurnberger
2013 Journal of Library Metadata  
34 This article describes the progress made towards developing Academic Commons (AC), Columbia University's digital repository, as an interoperable repository through the use of RDF and non-RDF Semantic  ...  Approaches taken include the implementation of microdata to add semantic markup to HTML content; a collaboration with Oregon State University's (OSU) digital repository, ScholarsArchive@OSU (SA@OSU), to  ...  Improving Discovery of and Access to Digital Repository Contents Using Semantic Web Standards: Columbia University's Academic Commons. Journal of Library Metadata, 13(2-3), 80-94.  ... 
doi:10.1080/19386389.2013.826036 fatcat:5bntapfu3vbflhvqly62jel3qa

Microdata in the IR: A Low-Barrier Approach to Enhancing Discovery of Institutional Repository Materials in Google

Shayna Pekala
2018 Code4Lib Journal  
Over the last several years, the Library has experimented with methods for making these items increasingly visible in search engine search results.  ...  The effects of the application of microdata to DigitalGeorgetown on Google search results were tracked over time using three different metrics, providing new insights about its impact.  ...  Improving discovery of and access to digital repository contents using semantic web standards: Columbia University’s Academic Commons. Journal of Library Metadata [Internet].  ... 
doaj:7ee67e7cd03b412c8a871108aefafa50 fatcat:hgamc6spyrcc7lacwpbl3nymdi

Content-Based Information Retrieval and Digital Libraries

Gary (Gang) Wan, Zao Liu
2008 Information Technology and Libraries  
Content-based information retrieval has been shown to be an effective way to search for the type of multimedia documents that are increasingly stored in digital libraries.  ...  The information retrieval system for these collections includes both a traditional text-based search engine and a CBIR system called SIMPLIcity (Semantics-sensitive Integrated Matching for Picture Libraries  ...  One of the earliest examples is the VideoQ system developed by Chang et al. (1997) of Columbia University (, which allows a user to search video based on a rich set of visual  ... 
doi:10.6017/ital.v27i1.3262 fatcat:i2vcfkeewbge7dxg5jelkvzv7y

Masoud Mazloom

2017 ACM SIGMultimedia Records  
We demonstrate a capability to yield semantic signature in a video search engine. We show how the semantic signatures provide a crude interpretation on why a certain video has been retrieved.  ...  Leading to the question: How to search events with concepts? To address this question we propose a search engine for video events in Chapter 4.  ... 
doi:10.1145/3129151.3129158 fatcat:dy52usoz5bdjjczt63x2gxpl34

Efficient Tracking of News Topics Based on Chronological Semantic Structures in a Large-Scale News Video Archive

Ichiro IDE, Tomoyoshi KINOSHITA, Tomokazu TAKAHASHI, Hiroshi MO, Norio KATAYAMA, Shin'ichi SATOH, Hiroshi MURASE
2012 IEICE transactions on information and systems  
Fig. 1 1 Semantic structure in a news video archive.  ...  the video as thumbnail images, for example in Carnegie Mellon University's original Informadia News-on-Demand system [3] , and Dublin City University's Físchlár News interface [23] .  ...  He had been a researcher at NTT from 1980 to 2003, and also a Visiting Researcher at Columbia University in 1992. Since 2003, he has been a Professor at Nagoya University.  ... 
doi:10.1587/transinf.e95.d.1288 fatcat:pwoh3lrv5fesnppgn23inhpmfm

AIs 10 to Watch: The Future of AI

2018 IEEE Intelligent Systems  
The aforementioned paradigms have fostered several key AI techniques that use deep learning, including image and video editing, image and video content-based recommendation, video summarization, and video  ...  ERIK CAMBRIA Nanyang Technological University Erik Cambria is an assistant professor in Nanyang Technological University's School of Computer Science and Engineering.  ... 
doi:10.1109/mis.2018.012001549 fatcat:mfx4dnb5lrgjbizilzh2anbcz4

TRECVID 2005 - An Overview

Paul Over, Tzveta Ianeva, Wessel Kraaij, Alan F. Smeaton
2005 TREC Video Retrieval Evaluation  
Richard Wright at the BBC Archive made the rushes data available and Gary Marchionini and the Open Video Project at the University of North Carolina at Chapel Hill helped us get the NASA videos in MPEG  ...  Columbia University donated story boundaries. Werner Bailer at Joanneum Research developed a tool for annotation of camera motion and made it available to participants in the low-level feature task.  ...  The Lowlands (CWI, Twente, University of Amsterdam) team submitted manual and automatic search runs using visual and text searching -first steps towards developing parameterized search engines for each  ... 
dblp:conf/trecvid/OverIKS05 fatcat:czlfoelhrnaxnnhwr74antamqi

Teaching Parallelism without Programming: A Data Science Curriculum for Non-CS Students

Yolanda Gil
2014 2014 Workshop on Education for High Performance Computing  
For example, Columbia University's Journalism School offers a set of courses to introduce students to data practices 2 that starts out teaching basic programming skills.  ...  metadata What is metadata; basic metadata vs semantic metadata; metadata about data collection; metadata about data processing; metadata for search and retrieval; metadata standards; domain metadata and  ... 
doi:10.1109/eduhpc.2014.12 dblp:conf/sc/Gil14 fatcat:govj2asp4reblkdodiw5fwzcny

Development of Columbia's video on demand testbed

Shih-Fu Chang, Alexandros Eleftheriadis, Dimitris Anastassiou
1996 Signal processing. Image communication  
(MR) video coding, efficient manipulation of compressed video, and advanced user interfaces.  ...  Video Course Network, and Digital Libraries.  ...  Javier Zamora is working on packet video over ATM networks and is the author of the MPEG-2/ATM AAL5 adaptation program. Steve Jacobs is responsible for the real-time Video Pump software.  ... 
doi:10.1016/0923-5965(95)00047-x fatcat:jzvbt7sjsneylaw3mku3vpm4da

Surveying the Expanding Cyberscape of New and Evolving Digital Learning Technologies —A Review of Recent Advances in Three Creative Focus Areas of Digital Learning Design and Development Impacting the Field of Education

Joseph G. Claudet
2017 Creative Education  
techniques for semantically annotating (using concept-based hyperlinking) the wealth of motion video-both full-length videos and segments of video-that is now ubiquitously available on the World Wide  ...  Web information search and data alignment/retrieval applications.  ... 
doi:10.4236/ce.2017.810110 fatcat:5u3mfhtkgva4dfbgly37ypr3bq

Teaching Big Data Analytics Skills with Intelligent Workflow Systems

Yolanda Gil
In addition, students learn about a range of topics in AI, including semantic representations and ontologies, machine learning, natural language processing, and image analysis.  ...  A key aspect of this work is the use of semantic workflows to capture and reuse end-to-end analytic methods that experts would use to analyze big data, and the use of an intelligent workflow system to  ...  For example, Columbia University's Journalism School offers a set of courses to introduce students to data practices [Columbia 2015 ] that starts out teaching basic programming skills.  ... 
doi:10.1609/aaai.v30i1.9860 fatcat:xpqbzbecprbafhr6wwcytsijlq

An overview of the NFAIS 2019 Annual Conference: Creating strategic solutions in a technology-driven marketplace

Bonnie Lawlor, Bonnie Lawlor
2019 Information Services and Use  
Unlocking the benefits of semantic search The remainder of the afternoon focused on the value of semantic search.  ...  In addition, he looked at the steps an organization can take to better understand how far they should dip their toe into semantical waters when it comes to their own internal search engines, including  ... 
doi:10.3233/isu-190051 fatcat:zrbosmbd2rdkrmg6yo2kmhri5y

AT&T Research at TRECVID 2006

Zhu Liu, David C. Gibbon, Eric Zavesky, Behzad Shahraray, Patrick Haffner
2006 TREC Video Retrieval Evaluation  
AT&T collaborated with Columbia University in the search and rushes exploitation tasks.  ...  TRECVID (TREC Video Retrieval Evaluation) is sponsored by NIST to encourage research in digital video indexing and retrieval.  ...  Please refer to Columbia University's TRECVID 2006 report for specific details. Keyframes for the BBC data were derived from the MIRACLE's shot segmentation engine [11] .  ... 
dblp:conf/trecvid/0001GZSH06 fatcat:z55nnyar7bcfbo7sjdpqhrgjte
« Previous Showing results 1 — 15 out of 579 results