Machine-learning system tackles speech and object recognition, all at once
Computer scientists have developed a system that learns to identify objects within an image, based on a spoken description of the image. Given an image and an audio caption, the model will highlight in real-time the relevant regions of the image being described.from Latest Science News -- ScienceDaily https://ift.tt/2xuomZr
Subscribe to:
Post Comments (Atom)
0 comments: