Visual Question Answering is a term from the fields of Artificial Intelligence, Digital Transformation, and Big Data. It is a technology that enables computers to answer complex questions about images. This means: an AI can not only recognise what is shown in a photo, but also answer targeted questions about it.
For example, you can show an AI an image of a living room and ask, „How many people are sitting on the sofa?“ or „What colour is the rug?“ The AI analyses the image and provides a suitable answer.
Visual question answering is already used in many areas. In online shops, it can help to better recognise products in photos and answer customer questions. In industry, it helps to automatically find errors in machine photos. Even in healthcare, this technology assists doctors by, for example, describing changes in X-ray images.
By combining image analysis and language, visual question answering offers new possibilities for making image information even more usable – thereby creating important advantages for businesses of all sizes.
Deutsch 
English (UK)