公开(公告)号：US20210109956A1

公开(公告)日：2021-04-15

申请号：US16650853

申请日：2018-01-30

Applicant: INTEL CORPORATION

Inventor： Zhou Su ,  Jianguo Li ,  Yinpeng Dong ,  Yurong Chen

IPC: G06F16/332 ,  G06N3/04 ,  G06N5/02 ,  G06K9/32

Abstract: An example apparatus for visual question answering includes a receiver to receive an input image and a question. The apparatus also includes an encoder to encode the input image and the question into a query representation including visual attention features. The apparatus includes a knowledge spotter to retrieve a knowledge entry from a visual knowledge base pre-built on a set of question-answer pairs. The apparatus further includes a joint embedder to jointly embed the visual attention features and the knowledge entry to generate visual-knowledge features. The apparatus also further includes an answer generator to generate an answer based on the query representation and the visual-knowledge features.

公开(公告)号：US11663249B2

公开(公告)日：2023-05-30

申请号：US16650853

申请日：2018-01-30

Applicant: INTEL CORPORATION

Inventor： Zhou Su ,  Jianguo Li ,  Yinpeng Dong ,  Yurong Chen

IPC: G06F16/33 ,  G06F16/332 ,  G06N3/049 ,  G06N5/025 ,  G06N3/045

CPC classification number: G06F16/3329 ,  G06N3/045 ,  G06N3/049 ,  G06N5/025

Abstract: An example apparatus for visual question answering includes a receiver to receive an input image and a question. The apparatus also includes an encoder to encode the input image and the question into a query representation including visual attention features. The apparatus includes a knowledge spotter to retrieve a knowledge entry from a visual knowledge base pre-built on a set of question-answer pairs. The apparatus further includes a joint embedder to jointly embed the visual attention features and the knowledge entry to generate visual-knowledge features. The apparatus also further includes an answer generator to generate an answer based on the query representation and the visual-knowledge features.