Jun 09, 2015
We are making available a new demo for the extraction of Corporate Responsibility Metrics in companies. The tool, which has been developed in the context of the Wikirate project, exploits information extraction techniques to fetch articles and metrics from relevant websites concerning the corporate sustainability practices of thousands of companies. As many as 17,000 articles have been retrieved for 7,000 companies in the Human Rights domain, while 57,000 metrics were extracted regarding their Corporate Responsibility behaviour.
May 11, 2015
1st Workshop on Semantic Web Technologies for Video and Image Analytics, in conjunction with ISWC 2015, Bethlehem, Pennsylvania, October 11-15, 2015 (http://nerone.diem.unisa.it/swt4iva/)
- Submission deadline: July 1, 2015
- Notifications: July 31, 2015
- Camera ready version: August 21, 2015
- Workshop: October 11-12, 2015
SCOPE AND MOTIVATION In the last years, a substantial body of work has focused on the development of cognitive approaches leveraging on a symbolic model representation of the objects belonging to a scene and their relations.
May 11, 2015
Dem@Care has been accepted at the EU Project Networking Session at ESWC 2015 that will take place on June 3, 2015 in Portoroz, Slovenia. Dem@Care provides an integrated solution for personal health services to individuals with dementia, as well as medical professionals and caregivers, by using a multitude of sensors, context-aware, multi-parametric monitoring of life-style, ambient environment and health parameters. In ESWC2015, Dem@Care will present the knowledge representation and semantic reasoning features underpinning the platform, which delivers a multi-parametric monitoring framework that sustains semantic, context-aware, personalized and adaptive feedback mechanisms for the remote management of people with dementia
May 06, 2015
Researchers from Multimedia Knowledge and Social Media Analytics Laboratory collaborate with the University of Warwick and City University of London on a project where Twitter signals are leveraged to predict the outcome of the UK general election. They believe that their forecasts could be more accurate than traditional opinion polls. Together, the team is using a framework that harvests political tweets, extracts various features about every party (e.g. volume of discussions) and then injects this information into public polling reports, producing a daily prediction of voting share.
Apr 28, 2015
The H2020 project KRISTINA, started in March 1st, 2015, aims at developing a multilingual human-like socially competent agent that serves as a trusted information provision in questions related to basic care and healthcare. Read more in the new KRISTINA website here.
Mar 30, 2015
ITI and the Multimedia Knowledge and Social Media Analytics Lab have been accepted as associate member of the Big Data Value Association (http://www.bigdatavalue.eu/). The aim of the BDVA is to provide a platform for stakeholders from the Big Data Value community in Europe to easily access information, exchange ideas and respond to activities concerning a Big Data Value initiative that is currently taking form at EU level. As a member, ITI and MKLab will contribute to the different task forces and activities of the association.
Feb 20, 2015
MKLab participates in two new Horizon 2020 projects: STEP and KRISTINA, which are starting in spring 2015. STEP deals with developing a cloud eParticipation SaaS platform, enhanced with web/social media mining, gamification, machine translation, and visualisation features, which will promote the societal and political participation of young people in the decision-making process on environmental issues. KRISTINA aims at developing a human-like socially competent agent that serves for migrants with language and cultural barriers in the host country as a trusted information provision party and mediator in questions related to basic care and healthcare.
Jan 03, 2015
The 2nd International Workshop on Environmental Multimedia Retrieval (EMR2015) is organized in conjunction with the ACM Conference on Multimedia Retrieval (ICMR) 2015, Shanghai, China, June 23-26, 2015. EMR 2015 welcomes original papers relevant (but not limited) to environmental multimedia indexing and retrieval, plant and animals identification, participatory and social environmental media analysis, discovery of environmental information in the web, content extraction from environmental multimedia and underwater scene understanding.
Dec 12, 2014
MKLab participated again this year in the annual TRECVID benchmarking activity, organized by the US National Institute for Standards and Technology (NIST). MKLab participated in four TRECVID tasks: Semantic Indexing (SIN), Event Detection in Internet Multimedia (MED), Multimedia Event Recounting (MER), and Instance Search (INS). Our results in these tasks were very good, significantly improving the results we had obtained in previous years.
Particularly for our participation in the Event Detection in Internet Multimedia (MED) task, we used a new, very fast machine learning method for big data problems, which we developed.