Technical Committee News

Google recently announced a new labeled dataset of human actions taking place in videos, named Atomic Visual Actions (AVA). It densely annotates 80 atomic visual actions in 57.6k movie clips with actions localized in space and time, resulting in 210k action labels with multiple labels per human occurring frequently. Compared with existing datasets, AVA possesses the following main characteristics:

For our October 2017 issue, we cover recent patents granted in the area of compressed sensing.
Patent no. 9,755,714 proposes methods and systems for performing compressed time domain joint channel estimation in a multi-user MIMO LTE wireless network include receiving training signals from a plurality of users, estimating a maximum delay spread for the received data according to a coherence bandwidth...

Researchers from University of California, Berkeley have developed an AI that turns a horse video into a zebra video.

The following is from the abstract of the authors' paper, titled "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks".

The Signal Processing Society (SPS) has 12 Technical Committees and 3 Special Interest Groups (SIGs) that support a broad selection of signal processing-related activities defined by the scope of the Society.