公开(公告)号：US11886488B2

公开(公告)日：2024-01-30

申请号：US17971225

申请日：2022-10-21

申请人： YAHOO ASSETS LLC

发明人： Paloma de Juan ,  Aasish Pappu

IPC分类号： G06F16/532 ,  G06F16/583 ,  G06F18/21 ,  G06F18/231 ,  G06F18/28 ,  G06N20/00 ,  G06N3/08 ,  G06V10/74 ,  G06V10/762 ,  G06V10/82 ,  G06V20/30 ,  G06V20/70 ,  G06V30/262

CPC分类号： G06F16/532 ,  G06F16/5838 ,  G06F18/217 ,  G06F18/28 ,  G06N3/08 ,  G06N20/00 ,  G06V10/761 ,  G06V10/7625 ,  G06V10/82 ,  G06V20/30 ,  G06V20/70 ,  G06V30/268 ,  G06V30/274

摘要： The present teaching relates to method, system, and programming for responding to an image related query. Information related to each of a plurality of images is received, wherein the information represents concepts co-existing in the image. Visual semantics for each of the plurality of images are created based on the information related thereto. Representations of scenes of the plurality of images are obtained via machine learning, based on the visual semantics of the plurality of images, wherein the representations capture concepts associated with the scenes.

公开(公告)号：US11481575B2

公开(公告)日：2022-10-25

申请号：US16142155

申请日：2018-09-26

申请人： YAHOO ASSETS LLC

发明人： Paloma de Juan ,  Aasish Pappu

IPC分类号： G06F16/532 ,  G06F16/583 ,  G06K9/62 ,  G06N20/00 ,  G06N3/08 ,  G06V10/82 ,  G06V20/30 ,  G06V20/70 ,  G06V30/262

摘要： The present teaching relates to method, system, and programming for responding to an image related query. Information related to each of a plurality of images is received, wherein the information represents concepts co-existing in the image. Visual semantics for each of the plurality of images are created based on the information related thereto. Representations of scenes of the plurality of images are obtained via machine learning, based on the visual semantics of the plurality of images, wherein the representations capture concepts associated with the scenes.

公开(公告)号：US20230041472A1

公开(公告)日：2023-02-09

申请号：US17971225

申请日：2022-10-21

申请人： YAHOO ASSETS LLC

发明人： Paloma de Juan ,  Aasish Pappu

IPC分类号： G06K9/62 ,  G06N3/08 ,  G06N20/00 ,  G06F16/583 ,  G06V30/262

摘要： The present teaching relates to method, system, and programming for responding to an image related query. Information related to each of a plurality of images is received, wherein the information represents concepts co-existing in the image. Visual semantics for each of the plurality of images are created based on the information related thereto. Representations of scenes of the plurality of images are obtained via machine learning, based on the visual semantics of the plurality of images, wherein the representations capture concepts associated with the scenes.

公开(公告)号：US20240038271A1

公开(公告)日：2024-02-01

申请号：US17877561

申请日：2022-07-29

申请人： Yahoo Assets LLC

发明人： Paloma de Juan ,  Alex J. Shaw ,  Eric M. Dodds ,  Benjamin J. Culpepper ,  Kapil Raj Thadani ,  Lakshmi V. Kesiraju ,  Praveen Mareedu ,  Sanika Shirwadkar ,  Xingyue Zhou ,  Yueh-Ning Ku

IPC分类号： G11B27/031 ,  G10L21/043 ,  G10L21/055 ,  G10L25/57 ,  G06V40/16 ,  G06V20/40 ,  G10L15/26 ,  G06F40/58 ,  G10L13/08 ,  G06V40/50

CPC分类号： G11B27/031 ,  G10L21/043 ,  G10L21/055 ,  G10L25/57 ,  G06V40/161 ,  G06V20/40 ,  G10L15/26 ,  G06F40/58 ,  G10L13/08 ,  G06V40/172 ,  G06V40/50

摘要： One or more computing devices, systems, and/or methods for generating a video in a target language are provided. In an example, a first video, in which a first speaker speaks in a first language, is identified. A translated transcript in a second language is determined. The translated transcript is indicative of a translation of speech spoken by the first speaker in the first video. Based upon the translated transcript and a speaker profile associated with a second speaker, first audio, including an auditory representation of the translated transcript being spoken in a voice of the second speaker, is generated. Based upon the first video and the first audio, a second video, in which mouth movements of the first speaker are aligned with speech of the auditory representation of the first audio, is generated.