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.