Apart from linguistic transformations, synthesizing among statements usually requires specific synthesis rulesofstatements.

To address these challenges, we propose the instance-level adaptive propulsion of external knowledge (IAPEK), where we only conduct the retrieval when necessary.

Humans are great observers who can learn by aggregating external knowledge from various sources, including observations from others' policies of attempting a task.

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.