Thebottom layer of the semantic inference framework extracts low level features at the frame level with a semantic clipsegmentationalgorithm based on the acceleration of the global motion.
Finally, there's a new best shot mode called Slow View, which captures a full-res ultra slow-motion video clip of your subject and then plays it back on the LCD.
When you go to view your photo, that video clip plays in slow motion (one second becomes two), along with the audio theme you selected before you hit the shutter release.