公开(公告)号：US20210141867A1

公开(公告)日：2021-05-13

申请号：US16678378

申请日：2019-11-08

Applicant: Adobe Inc.

Inventor： Mahika Wason ,  Amol Jindal ,  Ajay Bedi

IPC: G06F17/28 ,  G06K9/00 ,  G06N3/04 ,  G06N3/08

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods that can generate contextual identifiers indicating context for frames of a video and utilize those contextual identifiers to generate translations of text corresponding to such video frames. By analyzing a digital video file, the disclosed systems can identify video frames corresponding to a scene and a term sequence corresponding to a subset of the video frames. Based on images features of the video frames corresponding to the scene, the disclosed systems can utilize a contextual neural network to generate a contextual identifier (e.g. a contextual tag) indicating context for the video frames. Based on the contextual identifier, the disclosed systems can subsequently apply a translation neural network to generate a translation of the term sequence from a source language to a target language. In some cases, the translation neural network also generates affinity scores for the translation.

公开(公告)号：US20230102217A1

公开(公告)日：2023-03-30

申请号：US18049185

申请日：2022-10-24

Applicant: Adobe Inc.

Inventor： Mahika Wason ,  Amol Jindal ,  Ajay Bedi

IPC: G06F40/58 ,  G06N3/04 ,  G06N3/08 ,  G06V20/40

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods that can generate contextual identifiers indicating context for frames of a video and utilize those contextual identifiers to generate translations of text corresponding to such video frames. By analyzing a digital video file, the disclosed systems can identify video frames corresponding to a scene and a term sequence corresponding to a subset of the video frames. Based on images features of the video frames corresponding to the scene, the disclosed systems can utilize a contextual neural network to generate a contextual identifier (e.g. a contextual tag) indicating context for the video frames. Based on the contextual identifier, the disclosed systems can subsequently apply a translation neural network to generate a translation of the term sequence from a source language to a target language. In some cases, the translation neural network also generates affinity scores for the translation.

公开(公告)号：US11481563B2

公开(公告)日：2022-10-25

申请号：US16678378

申请日：2019-11-08

Applicant: Adobe Inc.

Inventor： Mahika Wason ,  Amol Jindal ,  Ajay Bedi

IPC: G06F40/58 ,  G06V20/40 ,  G06N3/08 ,  G06N3/04

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods that can generate contextual identifiers indicating context for frames of a video and utilize those contextual identifiers to generate translations of text corresponding to such video frames. By analyzing a digital video file, the disclosed systems can identify video frames corresponding to a scene and a term sequence corresponding to a subset of the video frames. Based on images features of the video frames corresponding to the scene, the disclosed systems can utilize a contextual neural network to generate a contextual identifier (e.g. a contextual tag) indicating context for the video frames. Based on the contextual identifier, the disclosed systems can subsequently apply a translation neural network to generate a translation of the term sequence from a source language to a target language. In some cases, the translation neural network also generates affinity scores for the translation.

公开(公告)号：US12299408B2

公开(公告)日：2025-05-13

申请号：US18049185

申请日：2022-10-24

Applicant: Adobe Inc.

Inventor： Mahika Wason ,  Amol Jindal ,  Ajay Bedi

IPC: G06F40/58 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06V10/44 ,  G06V10/82 ,  G06V20/40

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods that can generate contextual identifiers indicating context for frames of a video and utilize those contextual identifiers to generate translations of text corresponding to such video frames. By analyzing a digital video file, the disclosed systems can identify video frames corresponding to a scene and a term sequence corresponding to a subset of the video frames. Based on images features of the video frames corresponding to the scene, the disclosed systems can utilize a contextual neural network to generate a contextual identifier (e.g. a contextual tag) indicating context for the video frames. Based on the contextual identifier, the disclosed systems can subsequently apply a translation neural network to generate a translation of the term sequence from a source language to a target language. In some cases, the translation neural network also generates affinity scores for the translation.