-
公开(公告)号：US11829854B2
公开(公告)日：2023-11-28
申请号：US17403804
申请日：2021-08-16
Applicant: Google LLC
Inventor： Filip Pavetic , King Hong Thomas Leung , Dmitrii Tochilkin
IPC: G06K9/00 , G06K9/62 , G06N20/00 , G06V20/40 , G06V10/25 , G06F18/214 , G06F18/241 , G06V10/764
CPC classification number: G06N20/00 , G06F18/214 , G06F18/241 , G06V10/25 , G06V10/764 , G06V20/40 , G06V20/41
Abstract: A system and methods are disclosed for using a trained machine learning model to identify constituent images within composite images. A method may include providing pixel data of a first image as input to the trained machine learning model, obtaining one or more outputs from the trained machine learning model, and extracting, from the one or more outputs, an indication that the first image is a composite image that includes a constituent image, wherein at least a portion of the constituent image is in a spatial area of the first image.
-
Patent Agency Ranking
公开(公告)号：US11093751B2
公开(公告)日：2021-08-17
申请号：US16813686
申请日：2020-03-09
Applicant: Google LLC
Inventor： Filip Pavetic , King Hong Thomas Leung , Dmitrii Tochilkin
Abstract: A system and methods are disclosed for using a trained machine learning model to identify constituent images within composite images. A method may include providing pixel data of a first image as input to the trained machine learning model, obtaining one or more outputs from the trained machine learning model, and extracting, from the one or more outputs, a level of confidence that (i) the first image is a composite image that includes a constituent image, and (ii) at least a portion of the constituent image is in a particular spatial area of the first image.
-
公开(公告)号：US20210374418A1
公开(公告)日：2021-12-02
申请号：US17403804
申请日：2021-08-16
Applicant: Google LLC
Inventor： Filip Pavetic , King Hong Thomas Leung , Dmitrii Tochilkin
Abstract: A system and methods are disclosed for using a trained machine learning model to identify constituent images within composite images. A method may include providing pixel data of a first image as input to the trained machine learning model, obtaining one or more outputs from the trained machine learning model, and extracting, from the one or more outputs, an indication that the first image is a composite image that includes a constituent image, wherein at least a portion of the constituent image is in a spatial area of the first image.
-
公开(公告)号：US12217142B2
公开(公告)日：2025-02-04
申请号：US18520532
申请日：2023-11-27
Applicant: Google LLC
Inventor： Filip Pavetic , King Hong Thomas Leung , Dmitrii Tochilkin
IPC: G06N20/00 , G06F18/214 , G06F18/241 , G06V10/25 , G06V10/764 , G06V20/40
Abstract: A system and methods are disclosed for using a trained machine learning model to identify constituent images within composite images. A method may include providing data identifying a first image as input to a machine learning model trained using training data identifying a plurality of composite images that each include one or more constituent images, and determining, using one or more outputs of the trained machine learning model, that the first image is a composite image that includes a first constituent image, wherein at least a portion of the first constituent image is in a spatial area of the first image, and wherein the first constituent image corresponds to a frame of a video embedded into the first image.
-
5.发明公开公开(公告)号：US20240104435A1
公开(公告)日：2024-03-28
申请号：US18520532
申请日：2023-11-27
Applicant: Google LLC
Inventor： Filip Pavetic , King Hong Thomas Leung , Dmitrii Tochilkin
IPC: G06N20/00 , G06F18/214 , G06F18/241 , G06V10/25 , G06V10/764 , G06V20/40
CPC classification number: G06N20/00 , G06F18/214 , G06F18/241 , G06V10/25 , G06V10/764 , G06V20/40 , G06V20/41
Abstract: A system and methods are disclosed for using a trained machine learning model to identify constituent images within composite images. A method may include providing data identifying a first image as input to a machine learning model trained using training data identifying a plurality of composite images that each include one or more constituent images, and determining, using one or more outputs of the trained machine learning model, that the first image is a composite image that includes a first constituent image, wherein at least a portion of the first constituent image is in a spatial area of the first image, and wherein the first constituent image corresponds to a frame of a video embedded into the first image.
-
6.发明申请公开(公告)号：US20200210709A1
公开(公告)日：2020-07-02
申请号：US16813686
申请日：2020-03-09
Applicant: Google LLC
Inventor： Filip Pavetic , King Hong Thomas Leung , Dmitrii Tochilkin
Abstract: A system and methods are disclosed for using a trained machine learning model to identify constituent images within composite images. A method may include providing pixel data of a first image as input to the trained machine learning model, obtaining one or more outputs from the trained machine learning model, and extracting, from the one or more outputs, a level of confidence that (i) the first image is a composite image that includes a constituent image, and (ii) at least a portion of the constituent image is in a particular spatial area of the first image.
-
-
-
-
-
Search Results
6
records
(took 0.012 seconds)
