Deep Machine Vision – From Research to Market

This is a past event

71 people went

Location image of event venue

Details

We are happy to announce a special meetup session with an invited speaker. The two-part session will be held in English and will present practical deep learning applications as well as potential future advances.

Schedule:
Workshop: 16:00 - 17:00
Main talk: 18:00 - 20:00
Socializing: 20:00 - 21:00

Workshop: Nuts and Bolts of Mobile Food Understanding
16:00 - 17:00

It is estimated that in 2014 about 39% of the world's adult population was overweight, including 13% of obese people, which justifies a large amount of food diary applications for mobile devices that have recently been developed. Research within the machine vision field has also recently been proposed to automatically classify food – and possibly estimate its amount – directly from given pictures. In this workshop, a step-by-step visual classification solution to the problem will be presented and discussed.

Main talk: Deep Machine Vision – From Research to Market
18:00 - 20:00

The recent advent of deep learning technologies has achieved successes in many visual perception tasks such as object and action recognition, image segmentation and visual question answering. The first part of the talk will discuss three successful stories about using deep learning for machine vision tasks, which might have a significant impact on daily activities. Yet, we know that the status quo of computer vision and pattern recognition is still far from matching human capabilities, hence a vision on which will be the advances in the near future will be presented. The second part of the talk will present the activities carried out by Eye-Tech Srl, a University Spin-off that takes the latest advances in deep learning, machine vision, and augmented reality research fields and carries them on to market.

Bio: Niki Martinel, Ph.D.
Niki Martinel is a tenured Assistant Professor in Computer Vision and Machine Learning at the Department of Mathematics, Computer Science and Physics, at the University of Udine. His background spans the fields of machine learning and computer vision, while his primary research interest is hierarchical learning, with particular emphasis on deep learning and neural trees. He has published over 50 papers in prestigious international peer-reviewed journals and conferences and has been part of the program committee in venues such as CVPR, ICCV and ECCV. Apart from academic work, he is actively involved in transferring the acquired research knowledge to practical applications. He is a board member of a spin-off company of the University of Udine, working in vision and multimedia-related fields. Since 2017 he is the Deputy Director of the Italian Chapter of the Neural Networks and Deep Learning Technical Committee, the International Association of Pattern Recognition, and a member of the NATO activities for Machine Learning Systems.

The event sponsor is Poligon -> kreativni center, in coproduction with the Center za kreativnost, at the MAO Slovenia, and Deep Learning Ljubljana.

Event post: https://www.facebook.com/events/2245846872299338/
Poligon -> creative centre: http://www.poligon.si/en/
Centre for Creativity: https://www.czk.si/
Niki Martinel: http://users.dimi.uniud.it/~niki.martinel/