method, apparatus, computer equipment, computer readable storage medium and computer program for visual qustion answering

摘要

The present invention includes obtaining an input image and an input question, detecting visual information and position information of each of at least one text region of an input image, based on the visual information and position information, the at least one text region determining each semantic information and attribute information; determining a global characteristic of the input image based on the visual information, location information, semantic information and attribute information; determining a question characteristic according to an input question; , and generating an input image and a predictive answer to the input question based on the global feature and the question feature. The present invention also provides an image question-and-answer device, computer equipment, a computer-readable storage medium, and a computer program.