REVIVE: RegionalVisualRepresentationMattersin Knowledge-BasedVisualQuestionAnswering

Neural Information Processing Systems 

This paper revisits visual representation in knowledge-based visual question answering(VQA)anddemonstrates thatusingregionalinformation inabetterway can significantly improve the performance. While visual representation is extensively studied in traditional VQA, it is under-explored in knowledge-based VQA even though these two tasks share the common spirit, i.e., rely on visual inputtoanswerthequestion.