News – Page 5 – Visual Computing Lab

MaTHiSiS project on Greek TV

December 12, 2018

On November 20th CERTH conducted some successful pilots in Greece. The pilots were partly recorded for a show of the national broadcaster ERT3 and the show is now available on stream video! In the premise of this show, the technical manager Dr. Nicholas Vretos presented MaTHiSiS while the children were piloting, and also gave an in-depth interview regarding the project. In addition, the speech therapist that supervised the children spoke on the benefits and added value that the MaTHiSiS platform…

MaTHiSiS project on the EC Digital Education meeting

December 12, 2018

Dr. Nicholas Vretos represented the MaTHiSiS project on the EC Digital Education meeting, that took place on December 10th and 11th in Luxembourg.

NADINE Kick-off Meeting

November 7, 2018

NADINE Kick-off Meeting The NADINE European Project kick-off meeting took place in Rennes on 5 and 6 November 2018. This event brought together all the thirteen partners of its multidisciplinary Consortium, representing academia, industry, SMEs and NGO’s groups. During the meeting, NADINE partners shared their expertise and ideas on the project, discussed the details of the implementation of the work plan for the following three years and coordinated their work on the activities to be take place in the…

VCL PARTICIPATES IN TWO NEW H2020 PROJECTS: PROTEIN & NADINE

October 18, 2018

VCL participates in two new H2020 projects: PROTEIN & NADINE

International Conference on Industrial Internet of Things and Smart Manufacturing (IoTsm 2018)

September 10, 2018

Our paper “Adaptive web-based tools for capability-driven workforce management and task sequencing optimization” was presented at International Conference on Industrial Internet of Things and Smart Manufacturing (IoTsm 2018). G. Albanis, K. Apostolakis, C. Öztürk, D. Zarpalas, P. Daras, “Adaptive web-based tools for capability-driven workforce management and task sequencing optimization”, International Conference on Industrial Internet of Things and Smart Manufacturing (IoTsm 2018), London, UK, 5-6 Sep. 2018. View Publication

A dataset of omnidirectional (360 – spherical panoramas) images with their corresponding ground truth depths.

July 26, 2018

The 360 dataset provides 360° color images of indoor scenes along with their corresponding ground truth depth annotations. This dataset is composed from renders of other publicly available textured 3D datasets of indoor scenes. Specifically, it contains renders from two Computer Generated (CG) datasets, SunCG, SceneNet, and two realistic ones, acquired by scanning indoor building, Stanford2D3D, and Matterport3D. The 360° renders are produced by utilizing a path-tracing renderer and placing a spherical camera and a uniform light source at…

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB 2018)

June 14, 2018

Our paper “A System Architecture for Live Immersive 3D-Media Transcoding over 5G Networks” was presented at IEEE BMSB 2018. A. Doumanoglou, N. Zioulis, D. Griffin, J. Serrano, T. Khoa Phan, D. Jimenez, D. Zarpalas, F. Alvarez, M. Rio, P. Daras, “A System Architecture for Live Immersive 3D-Media Transcoding over 5G Networks”, Workshop on Media delivery innovations using flexible network models in 5G, IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB18), Valencia, Spain, 6th – 8th June 2018…

IEEE International Conference on Quality of Multimedia Experience (QoMEX 2018)

June 14, 2018

Our paper “Subjective Quality Assessment of Textured Human Full-Body 3D Reconstructions” was presented at IEEE QoMEX 2018. A. Doumanoglou, N. Zioulis, E. Christakis, D. Zarpalas, P. Daras, “Subjective quality assessment of textured human full-body 3D-reconstructions”, International Conference on Quality of Multimedia Experience (QoMEX 2018), Sardinia, Italy, 29 May – 1 June 2018 View Publication

Fake news and misinformation – FANDANGO article in CNN Greece

April 7, 2021

Η πληροφόρηση ήταν και είναι ζωτικής σημασίας για τη διαμόρφωση άποψης και λήψης αποφάσεων σε προσωπικό αλλά και σε κοινωνικό επίπεδο. Το Διαδίκτυο και τα κοινωνικά δίκτυα άλλαξαν τον τρόπο και χρόνο μετάδοσης ειδήσεων, ενώ την ίδια στιγμή το πλήθος των καναλιών πληροφόρησης αυξήθηκε ραγδαία. Στο νέο αυτό σκηνικό, η αξιολόγηση της είδησης ως αληθούς ή ψευδούς καθίσταται πολύ πιο δύσκολη αλλά και πολύ πιο σημαντική. Μεγάλος αριθμός καναλιών και χρηστών των κοινωνικών δικτύων, διαμοιράζουν εσκεμμένα ψευδείς ειδήσεις, κάποιες μάλιστα κατασκευασμένες με προηγμένα τεχνολογικά εργαλεία (π.χ. deep-fakes), οι οποίες και διαταράσσουν την κοινωνική συνοχή, επηρεάζουν ψηφοφόρους και χειραγωγούν τις αγορές. Το έργο FANDANGO, το οποίο χρηματοδοτείται από την Ευρωπαϊκή Ένωση μέσω του προγράμματος Horizon 2020, παρέχει ένα σύνολο εργαλείων που στοχεύουν στο πρόβλημα των ψευδών ειδήσεων. Το FANDANGO αποτελεί ουσιαστικά μία πλατφόρμα λογισμικού, που συλλέγει και αναλύει αυτόματα ειδήσεις, οι οποίες εμφανίζονται σε μια λίστα μέσων (domains, news sites) ενώ στη συνέχεια, παρουσιάζονται τα αποτελέσματα σε μια διεπαφή web για τους επαγγελματίες. Μπορείτε να διαβάσετε ολόκληρο το άρθρο εδώ.

Continue Reading...
Algorithms and TETRIS for migrant skill assessment – NADINE article in AMNA

April 7, 2021

Στο ταξίδι από τη Συρία προς την Ευρώπη τα «χαρτιά» που πιστοποιούν την εκπαίδευση και την επαγγελματική πορεία κάποιου πρόσφυγα μπορεί να χαθούν. Αλλά ακόμα και όταν υπάρχουν, δεν είναι ασύνηθες να μην αναγνωρίζονται στη χώρα υποδοχής. Επιπλέον, δεξιότητες που στη Συρία ή το Ιράκ αναγνωρίζονται ως πολύτιμες, στη δυτική Ευρώπη μπορεί να μην έχουν ζήτηση. Αδυνατώντας να καταγράψουν και να πιστοποιήσουν τις δεξιότητες των προσφύγων, οι υποψήφιοι εργοδότες, φορείς και χώρες υποδοχής συχνά δεν μπορούν ν’ αντιληφθούν πάνω σε ποια αντικείμενα θα μπορούσαν να αξιοποιήσουν ή να εκπαιδεύσουν εργαζόμενους προερχόμενους από άλλες περιοχές του πλανήτη και άλλες κουλτούρες. Ως αποτέλεσμα, πολλοί πρόσφυγες δυσκολεύονται να βρουν δουλειά, ακόμα και στις περιπτώσεις που μια θέση εργασίας δεν έχει καλυφθεί και θα ταίριαζε στα προσόντα τους. Λύσεις σε αυτό το πρόβλημα επιδιώκει να δώσει, μέσω της τεχνολογίας και ιδίως της Τεχνητής Νοημοσύνης, το ευρωπαϊκό πρόγραμμα NADINE, το 90% των αλγορίθμων του οποίου αναπτύχθηκε στη Θεσσαλονίκη και συγκεκριμένα στο Εργαστήριο Οπτικής Υπολογιστικής του Εθνικού Κέντρου Έρευνας και Τεχνολογικής Ανάπτυξης (ΕΚΕΤΑ)/Ινστιτούτου Τεχνολογιών Πληροφορικής και Επικοινωνιών (ΙΠΤΗΛ). Μπορείτε να διαβάσετε ολόκληρο το άρθρο εδώ.

Continue Reading...
FANDANGO Project Featured in ICWA Article “Can AI change the game for fake news?”

July 23, 2019

Can AI change the game for fake news? The Institute of Current World Affairs (ICWA) has published an article, written by Amanda Mikesell, regarding fake news. The article features the FANDANGO Project, the goal of which is to help journalists in the verification and fact-checking process of news pieces. Read the full article here.

Continue Reading...
FORENSOR – Results in Brief article on CORDIS

July 10, 2019

Set-and-forget surveillance cameras wake themselves up and call for help Despite their advantages, digital security cameras are inconvenient. A new surveillance model reports on crime by itself. Digital surveillance cameras have come a long way in a short time. They now combine very-high–quality images with autonomous operation and convenient sizes. Therefore, such devices are widely used in law enforcement. Nevertheless, video surveillance remains costly, power hungry and complicated. Current systems are used mainly for recording and have very little capability for real-time scene interpretation. The EU-funded FORENSOR project has developed a new sensor system that addresses these problems. The sensor is small and concealable; its low-power requirements free it from electrical infrastructure. The device can operate for months. Hence, the sensor is also capable of a degree of independent operation. You can read the full article here.

Continue Reading...
SURVANT – Results in Brief article on CORDIS

June 12, 2019

AI system finds and predicts criminal patterns in vast troves of surveillance footage Security organisations can’t keep up with the sheer volume of surveillance footage available today. The machine-learning based SURVANT system sifts through the data to find patterns of crimes and even predicts their evolution. Security organisations and agencies around the world deploy increasing amounts of video surveillance to monitor and protect people, property and public infrastructure. The amount of available footage is exploding, thanks to growing numbers of cameras operating at higher resolutions, making it difficult for human surveillance teams to analyze all of the footage – especially if they have other tasks. Automated surveillance could help but requires advanced analytics to be effective in fighting crime. Many organizations have invested heavily in surveillance systems and are keen to exploit the video footage they have collected to this end. The EU-funded SURVANT project created a system to do exactly this. “SURVANT addresses system scalability issues that emerge from the explosion in the amount of available video content,” says Mr Giuseppe Vella, SURVANT project coordinator. SURVANT analyses relevant surveillance videos to extract inter/intra-camera video analytics, before enriching this information with reasoning and inference. It then assists investigators to search efficiently and effectively through video archives, to find critical elements of criminal activity among the sea of footage. You can read the full article here.

Continue Reading...
SURVANT: An EU-Funded Project Success Story

December 13, 2018

EU Commission has published success story about the Survant project. An innovative artificial intelligence platform being developed by EU-funded researchers analyses CCTV and videos posted on social media to identify criminals, suspicious behaviour and events more quickly. Researchers in the EU-funded SURVANT project are working on an innovative system that will be able to automatically gather and analyse videos and images. Their aim is to provide a user-friendly platform with advanced visualisation tools to help users search and examine footage, ultimately improving investigators’ capacity and efficiency. ‘SURVANT offers unique flexibility,’ explains the project’s technical director, Anastasios Dimou, of the Information Technologies Institute in Greece. ‘It supports a plethora of video and image formats and allows the investigator to build complex content-based queries with a user-friendly interface.’ Read the full article...

Continue Reading...