-
Patent Agency Ranking
公开(公告)号：US20250054322A1
公开(公告)日：2025-02-13
申请号：US18787616
申请日：2024-07-29
Applicant: Google LLC
Inventor： Keren Ye , Yicheng Zhu , Junjie Ke , Jiahui Yu , Leonidas John Guibas , Peyman Milanfar , Feng Yang
IPC: G06V20/70 , G06F40/279
Abstract: Systems and methods for attribute recognition can include obtaining an image and a text string. The text string can be processed with a language model to generate a set of candidate attributes based on sequence based prediction. The image and the candidate attributes can be processed with an image-text model to determine a likelihood that the respective candidate attribute is depicted in the image. The likelihood determination can then be utilized to determine a predicted attribute for the object of interest.
-
公开(公告)号：US11126820B2
公开(公告)日：2021-09-21
申请号：US16842920
申请日：2020-04-08
Applicant: Google LLC
Inventor： Gerhard Florian Schroff , Dmitry Kalenichenko , Keren Ye
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object embedding system. In one aspect, a method comprises providing selected images as input to the object embedding system and generating corresponding embeddings, wherein the object embedding system comprises a thumbnailing neural network and an embedding neural network. The method further comprises backpropagating gradients based on a loss function to reduce the distance between embeddings for same instances of objects, and to increase the distance between embeddings for different instances of objects.
-
公开(公告)号：US20200242333A1
公开(公告)日：2020-07-30
申请号：US16842920
申请日：2020-04-08
Applicant: Google LLC
Inventor： Gerhard Florian Schroff , Dmitry Kalenichenko , Keren Ye
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object embedding system. In one aspect, a method comprises providing selected images as input to the object embedding system and generating corresponding embeddings, wherein the object embedding system comprises a thumbnailing neural network and an embedding neural network. The method further comprises backpropagating gradients based on a loss function to reduce the distance between embeddings for same instances of objects, and to increase the distance between embeddings for different instances of objects.
-
公开(公告)号：US10657359B2
公开(公告)日：2020-05-19
申请号：US15818124
申请日：2017-11-20
Applicant: Google LLC
Inventor： Gerhard Florian Schroff , Dmitry Kalenichenko , Keren Ye
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object embedding system. In one aspect, a method comprises providing selected images as input to the object embedding system and generating corresponding embeddings, wherein the object embedding system comprises a thumbnailing neural network and an embedding neural network. The method further comprises backpropagating gradients based on a loss function to reduce the distance between embeddings for same instances of objects, and to increase the distance between embeddings for different instances of objects.
-
公开(公告)号：US20190156106A1
公开(公告)日：2019-05-23
申请号：US15818124
申请日：2017-11-20
Applicant: Google LLC
Inventor： Gerhard Florian Schroff , Dmitry Kalenichenko , Keren Ye
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object embedding system. In one aspect, a method comprises providing selected images as input to the object embedding system and generating corresponding embeddings, wherein the object embedding system comprises a thumbnailing neural network and an embedding neural network. The method further comprises backpropagating gradients based on a loss function to reduce the distance between embeddings for same instances of objects, and to increase the distance between embeddings for different instances of objects.
-
-
-
-
Search Results
5
records
(took 0.009 seconds)
