公开(公告)号：US20240037939A1

公开(公告)日：2024-02-01

申请号：US18487183

申请日：2023-10-16

Applicant: ADOBE INC.

Inventor： Quan Hung TRAN ,  Long Thanh MAI ,  Zhe LIN ,  Zhuowan LI

IPC: G06V20/30 ,  G06F16/55 ,  G06F16/535 ,  G06F40/205 ,  G06V10/75 ,  G06F18/214 ,  G06V10/82

CPC classification number: G06V20/30 ,  G06F16/55 ,  G06F16/535 ,  G06F40/205 ,  G06V10/751 ,  G06F18/214 ,  G06V10/82

Abstract: A group captioning system includes computing hardware, software, and/or firmware components in support of the enhanced group captioning contemplated herein. In operation, the system generates a target embedding for a group of target images, as well as a reference embedding for a group of reference images. The system identifies information in-common between the group of target images and the group of reference images and removes the joint information from the target embedding and the reference embedding. The result is a contrastive group embedding that includes a contrastive target embedding and a contrastive reference embedding with which to construct a contrastive group embedding, which is then input to a model to obtain a group caption for the target group of images.

公开(公告)号：US20210375277A1

公开(公告)日：2021-12-02

申请号：US16889669

申请日：2020-06-01

Applicant: Adobe Inc.

Inventor： Tuan Manh LAI ,  Trung BUI ,  Quan Hung TRAN

IPC: G10L15/22 ,  G10L15/02

Abstract: A computer-implemented method is disclosed for determining one or more characteristics of a dialog between a computer system and user. The method may comprise receiving a system utterance comprising one or more tokens defining one or more words generated by the computer system; receiving a user utterance comprising one or more tokens defining one or more words uttered by a user in response to the system utterance, the system utterance and the user utterance forming a dialog context; receiving one or more utterance candidates comprising one or more tokens; for each utterance candidate, generating an input sequence combining the one or more tokens of each of the system utterance, the user utterance, and the utterance candidate; and for each utterance candidate, evaluating the generated input sequence with a model to determine a probability that the utterance candidate is relevant to the dialog context.