Microsoft Research's new tech can detect what's around you, and answer questions about them

Reading time icon 1 min. read

Readers help support MSPoweruser. When you make a purchase using links on our site, we may earn an affiliate commission. Tooltip Icon

Read the affiliate disclosure page to find out how can you help MSPoweruser effortlessly and without spending any money. Read more


Microsoft researchers are always working fascinating new technologies. Today, the company published a blog post in which the company gave a sneak peak at the company’s new system that can analyze images and answer questions just like humans. A team of researchers at Microsoft teamed up with Carnegie Mellon University to build this new system which uses computer vision, deep learning, and language understanding to analyze images.

Here are some examples of how the tech would work:


The system apparently works just like a set of human eyes would. The system uses deep learning “to extract visual information, to represent the meaning of the question  in natural language, and to focus the attention onto narrower regions of the image in two separate steps in order to seek the precise answer.”

Microsoft Research has published a research paper, where you can find a lot more (technical) details about this new tech — head over to this link to find it.  Nonetheless, what do you think of this new tech? Let us know in the comment section below.

More about the topics: microsoft, microsoft research