ICCV 2017 Best Paper Award: Mask R-CNN
Researchers from Facebook AI Research have won the Best Paper Award (Marr Prize) at the 16th International Conference on Computer vision (ICCV) 2017,…
Read moreWhat Should We Learn from IARPA’s Deep-Learning Challenge Seeks AI to Analyze Satellite Images
Spy satellites and their commercial cousins orbit Earth like a swarm of space paparazzi, capturing tens of terabytes of images every day. The deluge…
Read moreRecent Patents in Signal Processing (December 2017) – Active Contours
For our December 2017 issue, we cover recent patents granted in the area of applications of active contours.
Read moreGet Involved with Technical Committees via the Affiliate TC Membership
The Signal Processing Society (SPS) has 12 Technical Committees and 3 Special Interest Groups (SIGs) that support a broad selection of signal…
Read moreSignal Processing in Action: Georgia Tech Professor David Citrin is Revealing the Secrets of 17th Century Artists, thanks to 21st Century Signal Processing
Georgia Tech professor David Citrin is revealing the secrets of 17th century artists thanks to 21st century signal processing.
Read moreSignal Processing in Action: An Old Technique Could Put Artificial Intelligence in Your Hearing Aid
How can we use modern signal processing and artificial intelligence to enhance medical devices such as hearing aids? A new startup called Mythic in a…
Read moreHumanoid Robot Can Backflip
Boston Dynamics, a leading developer of advanced dynamic robots, recently released a video showing that their humanoid robot Atlas can do…
Read moreActivity Update from the IVMSP TC
Image, Video, and Multidimensional Signal Processing Technical Committee (IVMSP TC) promotes and guides the advancement of the field of…
Read moreRecent Patents in Signal Processing (November 2017) – Image and audio inpainting
For our November 2017 issue, we cover recent patents granted in the area of image and audio inpainting
Read moreGoogle Announces AVA: A Finely Labeled Video Dataset for Human Action Understanding
Google recently announced a new labeled dataset of human actions taking place in videos, named Atomic Visual Actions (AVA). It densely annotates 80…
Read more