公开(公告)号：US12210835B2

公开(公告)日：2025-01-28

申请号：US17946400

申请日：2022-09-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Peixi Xiong ,  Yilin Shen ,  Hongxia Jin

IPC: G06F40/30 ,  G06F40/284 ,  G06F40/289 ,  G06V10/40 ,  G06V10/70 ,  G06V10/80 ,  G06F16/33 ,  G06V10/426 ,  G06V10/762 ,  G06V10/764 ,  G06V10/82

Abstract: In one embodiment, a method includes accessing an image and a natural-language question regarding the image and extracting, from the image, a first set of image features at a first level of granularity and a second set of image features at a second level of granularity. The method further includes extracting, from the question, a first set of text features at the first level of granularity and a second set of text features at the second level of granularity; generating a first output representing an alignment between the first set of image features and the first set of text features; generating a second output representing an alignment between the second set of image features and the second set of text features; and determining an answer to the question based on the first output and the second output.