CycleMatch: a new approach for matching images and text

Researchers at Leiden University and the National University of Defense Technology (NUDT), in China, have recently developed a new approach for image-text matching, called CycleMatch. Their approach, presented in a paper published in Elsevier's Pattern Recognition journal, is based on cycle-consistent learning, a technique that is sometimes used to train artificial neural networks on image-to-image translation tasks. The general idea behind cycle-consistency is that when transforming source data into target data and then vice versa, one should finally obtain the original source samples.

* This article was originally published here

Gold-coated fungi are the new gold diggers

The thread-like fungi attach gold to their strands by dissolving and precipitating particles from their surroundings, in a process that could offer clues for finding new gold deposits.

* This article was originally published here

Google Glass struck out for masses but enterprise class has takers

My, have we grown. All eyes are on the Glass Enterprise Edition 2. with its hardware update and new frames. Google Glass has come a long way since its debut in 2013. As Scott Stein in CNET quipped, "You might remember Glass as a strange 2013 footnote."

* This article was originally published here