Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Article

INESC TEC honoured at ICMV session on neural network applications and image processing

A presentation about automatic sign language recognition by Diogo Pernes, researcher at INESCT TEC’s Centre for Telecommunications and Multimedia (CTM), was awarded “Best Oral Presentation” at the session on neural networks application and image processing – part of the latest edition of the International Conference on Machine Vision (ICMV).

14th January 2020

A presentation about automatic sign language recognition by Diogo Pernes, researcher at INESCT TEC’s Centre for Telecommunications and Multimedia (CTM), was awarded Best Oral Presentation” at the session on neural networks application and image processing – part of the latest edition of the International Conference on Machine Vision (ICMV).

The article by Pedro M. Ferreira (a CTM researcher at the time), Diogo Pernes, Ana Rebelo and Jaime S. Cardoso proposes a technique to improve the algorithm performance for unobserved speakers during the training phase (also called learning phase) of said algorithm. The proposed method is based on adversarial neural networks.

ICMV is an annual international conference dedicated to the work developed in the field of computer vision. In addition to the distinction at the last edition of the event – held in Amsterdam between November 16 and 18, 2019 – the research team responsible for the article was invited to publish an extended version in the International Journal of Machine Learning and Computing (IJMLC), an open-access magazine that publishes relevant work in the field of machine learning and computing.

The IJMLC magazine publishes original, unpublished, experimental or theoretical research results that are appropriately reviewed by peers.

 

The researchers mentioned in this news piece are associated with UP-FEUP and Universidade Portucalense.