Publications Data Analytics & CS

Tamr, a start-up founded in 2013, is based on technology developed at QCRI that allows for scalable data curation and integration by deduplicating the resulting dataset composite. Link to the paper here.

AIDR is one of QCRI’s flagship projects that aims to enable humanitarian organizations, government, NGOs, and affected communities to improve the effectiveness of humanitarian strategies such as preparedness, mitigation, and response during humanitarian crises and emergencies. AIDR platform employs state-of-the-art machine learning and computer vision techniques to process information communicated via social media to gain situational awareness and actionable insights for humanitarian response. 
 

Planetary Response Network (Crowdsourcing Satellite Imagery Analysis for Humanitarian Response). In collaboration with Planet Labs and Zooniverse.

Hot Summer Cool Research - The Arabic Language Technologies team worked with undergraduate students during QCRI's summer internship program on a number of projects.

gCloud: System for On-demand Sharing of GPUs in Clouds:  This project develops novel methods to efficiently share GPUs among different applications in fine-grain and on-demand manner, yielding high utilization of GPUs and reduction in the execution times of applications. The developed methods and algorithms have been integrated in the popular OpenStack cloud management software system, which is backed up and used by many companies worldwide.

More info can be found in our HPGC 2013 paper.

Web Data Integration. Web data is a great opportunity, but using it in analytics requires new solution to overcome the variety and volatility. In this project we exploit web data for data integration tasks.

TweetCred (Automatically Predicting Credibility of Tweets). In collaboration with Indraprastha Institute of Information Technology (IIIT), Delhi.

Twitter Analytics (Capturing Real-Time Socio-Economic Trends). In collaboration with the United Nations Development Program (UNDP) in Egypt.

cSpider:  Cloud-based System for Multimedia Content Protection:  We designed a cloud-based video copy detection system for large-scale 3D video collections, called cSpider. The system creates compact signatures from videos that are fast to compute and compare, small to store, and robust against video modifications. The system maintains a large-scale distributed index of signatures on a cloud infrastructure. Utilizing the cloud, the system can scale (up and down) to different number of videos.

cSpider is currently running on the Amazon cloud and on our own local cloud. See a demo of cSpider.