-
公开(公告)号：US11468298B2
公开(公告)日：2022-10-11
申请号：US16573342
申请日：2019-09-17
Applicant: Adobe Inc.
Inventor： Scott Cohen , Curtis Wigington , Brian Price
Abstract: Described techniques for multi-label classification, in which sequential data includes characters that have two or more aspects that require classification, are capable of providing separate classifications for different categories of components. Using an appropriately-trained neural network, the described techniques perform aligning and otherwise combining two or more classifications (e.g., categories, or types of labels) to obtain multi-label characters.
-
公开(公告)号：US11709915B2
公开(公告)日：2023-07-25
申请号：US17003149
申请日：2020-08-26
Applicant: Adobe Inc.
Inventor： Pramuditha Perera , Vlad Morariu , Rajiv Jain , Varun Manjunatha , Curtis Wigington
IPC: G06F18/21 , G06F18/214 , G06F18/241 , G06F11/32 , G06N3/045
CPC classification number: G06F18/2185 , G06F11/327 , G06F18/214 , G06F18/241 , G06N3/045
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for classifying an input image utilizing a classification model conditioned by a generative model and/or self-supervision. For example, the disclosed systems can utilize a generative model to generate a reconstructed image from an input image to be classified. In turn, the disclosed systems can combine the reconstructed image with the input image itself. Using the combination of the input image and the reconstructed image, the disclosed systems utilize a classification model to determine a classification for the input image. Furthermore, the disclosed systems can employ self-supervised learning to cause the classification model to learn discriminative features for better classifying images of both known classes and open-set categories.
-
公开(公告)号：US20230281463A1
公开(公告)日：2023-09-07
申请号：US17684680
申请日：2022-03-02
Applicant: Adobe Inc.
Inventor： Priyanka Kulkarni , Laurie Byrum , Curtis Wigington , Matthew Crosby , Pallav Vyas
CPC classification number: G06N3/10 , G06N3/0454
Abstract: Certain aspects and features of this disclosure relate to partitioning machine learning models. For example, a method includes accessing a machine learning model configured for processing a data object and partitioning the machine learning model into a number of partitions. Each of the partitions of the machine learning model is characterized with respect to runtime requirements. Each of the partitions of the machine learning model is executed using a runtime environment corresponding to runtime requirements of the respective partition to process the data object. Output can be rendered based on the processing of the data object.
-
公开(公告)号：US20210312232A1
公开(公告)日：2021-10-07
申请号：US16885168
申请日：2020-05-27
Applicant: Adobe Inc.
Inventor： Christopher Tensmeyer , Vlad Ion Morariu , Varun Manjunatha , Tong Sun , Nikolaos Barmpalios , Kai Li , Handong Zhao , Curtis Wigington
Abstract: A domain alignment technique for cross-domain object detection tasks is introduced. During a preliminary pretraining phase, an object detection model is pretrained to detect objects in images associated with a source domain using a source dataset of images associated with the source domain. After completing the pretraining phase, a domain adaptation phase is performed using the source dataset and a target dataset to adapt the pretrained object detection model to detect objects in images associated with the target domain. The domain adaptation phase may involve the use of various domain alignment modules that, for example, perform multi-scale pixel/path alignment based on input feature maps or perform instance-level alignment based on input region proposals.
-
Patent Agency Ranking
公开(公告)号：US20240386675A1
公开(公告)日：2024-11-21
申请号：US18317851
申请日：2023-05-15
Applicant: Adobe Inc.
Inventor： Jennifer Healey , Tong Sun , Nicholas Rewkowski , Nedim Lipka , Curtis Wigington , Alexa Siu
Abstract: A computing system captures image data using a camera and captures spatial information using one or more sensors. The computing system receives voice data using a microphone. The computing system analyzes the voice data to identify a keyword. The computing system analyzes the image data and the spatial information to identify an object corresponding to the keyword. The computing system generates text based on the voice data and the keyword. The computing system stores the text in association with the object. The computing system generates and provides output comprising the text linked to the object or a derivative thereof.
-
公开(公告)号：US20220067449A1
公开(公告)日：2022-03-03
申请号：US17003149
申请日：2020-08-26
Applicant: Adobe Inc.
Inventor： Pramuditha Perera , Vlad Morariu , Rajiv Jain , Varun Manjunatha , Curtis Wigington
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for classifying an input image utilizing a classification model conditioned by a generative model and/or self-supervision. For example, the disclosed systems can utilize a generative model to generate a reconstructed image from an input image to be classified. In turn, the disclosed systems can combine the reconstructed image with the input image itself. Using the combination of the input image and the reconstructed image, the disclosed systems utilize a classification model to determine a classification for the input image. Furthermore, the disclosed systems can employ self-supervised learning to cause the classification model to learn discriminative features for better classifying images of both known classes and open-set categories.
-
7.发明公开公开(公告)号：US20240056309A1
公开(公告)日：2024-02-15
申请号：US17819540
申请日：2022-08-12
Applicant: Adobe Inc.
Inventor： Songlin He , Tong Sun , Nedim Lipka , Curtis Wigington , Rajiv Jain , Anindo Roy
IPC: H04L9/32 , G06F21/31 , G06F40/174
CPC classification number: H04L9/3247 , G06F21/31 , G06F40/174
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that fill in digital documents using user identity models of client devices. For instance, in one or more embodiments, the disclosed systems receive a digital document comprising a digital fillable field. The disclosed systems further retrieve, for a client device associated with the digital document, a decentralized identity credential comprising a user attribute established under a decentralized identity framework. Using the user attribute of the decentralized identity credential, the disclosed systems modify the digital document by filling in the digital fillable field.
-
公开(公告)号：US11544503B2
公开(公告)日：2023-01-03
申请号：US16885168
申请日：2020-05-27
Applicant: Adobe Inc.
Inventor： Christopher Tensmeyer , Vlad Ion Morariu , Varun Manjunatha , Tong Sun , Nikolaos Barmpalios , Kai Li , Handong Zhao , Curtis Wigington
Abstract: A domain alignment technique for cross-domain object detection tasks is introduced. During a preliminary pretraining phase, an object detection model is pretrained to detect objects in images associated with a source domain using a source dataset of images associated with the source domain. After completing the pretraining phase, a domain adaptation phase is performed using the source dataset and a target dataset to adapt the pretrained object detection model to detect objects in images associated with the target domain. The domain adaptation phase may involve the use of various domain alignment modules that, for example, perform multi-scale pixel/path alignment based on input feature maps or perform instance-level alignment based on input region proposals.
-
公开(公告)号：US20210081766A1
公开(公告)日：2021-03-18
申请号：US16573342
申请日：2019-09-17
Applicant: Adobe Inc.
Inventor： Scott Cohen , Curtis Wigington , Brian Price
Abstract: Described techniques for multi-label classification, in which sequential data includes characters that have two or more aspects that require classification, are capable of providing separate classifications for different categories of components. Using an appropriately-trained neural network, the described techniques perform aligning and otherwise combining two or more classifications (e.g., categories, or types of labels) to obtain multi-label characters.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.015 seconds)
