公开(公告)号：US12293577B2

公开(公告)日：2025-05-06

申请号：US17651771

申请日：2022-02-18

Applicant: Adobe Inc.

Inventor： Seunghyun Yoon ,  Trung Huu Bui ,  Franck Dernoncourt ,  Hyounghun Kim ,  Doo Soon Kim

IPC: G06V10/86 ,  G06F40/284 ,  G06N3/044 ,  G06N3/088 ,  G06V10/77 ,  G06V10/80 ,  G06V10/82

Abstract: Embodiments of the disclosure provide a machine learning model for generating a predicted executable command for an image. The learning model includes an interface configured to obtain an utterance indicating a request associated with the image, an utterance sub-model, a visual sub-model, an attention network, and a selection gate. The machine learning model generates a segment of the predicted executable command from weighted probabilities of each candidate token in a predetermined vocabulary determined based on the visual features, the concept features, current command features, and the utterance features extracted from the utterance or the image.

公开(公告)号：US20230267726A1

公开(公告)日：2023-08-24

申请号：US17651771

申请日：2022-02-18

Applicant: Adobe Inc.

Inventor： Seunghyun Yoon ,  Trung Huu Bui ,  Franck Dernoncourt ,  Hyounghun Kim ,  Doo Soon Kim

IPC: G06V10/86 ,  G06V10/82 ,  G06V10/80 ,  G06V10/77 ,  G06N3/08 ,  G06N3/04 ,  G06F40/284

CPC classification number: G06V10/86 ,  G06V10/82 ,  G06V10/806 ,  G06V10/7715 ,  G06N3/088 ,  G06N3/0445 ,  G06F40/284

Abstract: Embodiments of the disclosure provide a machine learning model for generating a predicted executable command for an image. The learning model includes an interface configured to obtain an utterance indicating a request associated with the image, an utterance sub-model, a visual sub-model, an attention network, and a selection gate. The machine learning model generates a segment of the predicted executable command from weighted probabilities of each candidate token in a predetermined vocabulary determined based on the visual features, the concept features, current command features, and the utterance features extracted from the utterance or the image.