-
公开(公告)号：US12147499B2
公开(公告)日：2024-11-19
申请号：US18242075
申请日：2023-09-05
Applicant: Adobe Inc.
Inventor： Rajiv Jain , Varun Manjunatha , Joseph Barrow , Vlad Ion Morariu , Franck Dernoncourt , Sasha Spala , Nicholas Miller
IPC: G06F18/214 , G06F16/33 , G06F18/21 , G06F18/2415 , G06F40/117 , G06F40/30 , G06V30/413
Abstract: Certain embodiments involve using a machine-learning tool to generate metadata identifying segments and topics for text within a document. For instance, in some embodiments, a text processing system obtains input text and applies a segmentation-and-labeling model to the input text. The segmentation-and-labeling model is trained to generate a predicted segment for the input text using a segmentation network. The segmentation-and-labeling model is also trained to generate a topic for the predicted segment using a pooling network of the model to the predicted segment. The output of the model is usable for generating metadata identifying the predicted segment and the associated topic.
-
公开(公告)号：US20230409672A1
公开(公告)日：2023-12-21
申请号：US18242075
申请日：2023-09-05
Applicant: Adobe Inc.
Inventor： Rajiv Jain , Varun Manjunatha , Joseph Barrow , Vlad Ion Morariu , Franck Dernoncourt , Sasha Spala , Nicholas Miller
IPC: G06F18/214 , G06F40/30 , G06F40/117 , G06V30/413 , G06F18/21 , G06F18/2415
CPC classification number: G06F18/2148 , G06F40/30 , G06F40/117 , G06V30/413 , G06F18/217 , G06F18/2415 , G06V2201/10 , G06F16/33
Abstract: Certain embodiments involve using a machine-learning tool to generate metadata identifying segments and topics for text within a document. For instance, in some embodiments, a text processing system obtains input text and applies a segmentation-and-labeling model to the input text. The segmentation-and-labeling model is trained to generate a predicted segment for the input text using a segmentation network. The segmentation-and-labeling model is also trained to generate a topic for the predicted segment using a pooling network of the model to the predicted segment. The output of the model is usable for generating metadata identifying the predicted segment and the associated topic.
-
公开(公告)号：US20220382975A1
公开(公告)日：2022-12-01
申请号：US17333892
申请日：2021-05-28
Applicant: Adobe Inc.
Inventor： Jiuxiang Gu , Vlad Morariu , Varun Manjunatha , Tong Sun , Rajiv Jain , Peizhao Li , Jason Kuen , Handong Zhao
IPC: G06F40/279 , G06N3/04 , G06N3/08 , G06F16/93 , G06F40/30 , G06F40/205
Abstract: One example method involves operations for a processing device that include receiving, by a machine learning model trained to generate a search result, a search query for a text input. The machine learning model is trained by receiving pre-training data that includes multiple documents. Pre-training the machine learning model by generating, using an encoder, feature embeddings for each of the documents included in the pre-training data. The feature embeddings are generated by applying a masking function to visual and textual features in the documents. Training the machine learning model also includes generating, using the feature embeddings, output features for the documents by concatenating the feature embeddings and applying a non-linear mapping to the feature embeddings. Training the machine learning model further includes applying a linear classifier to the output features. Additionally, operations include generating, for display, a search result using the machine learning model based on the input.
-
公开(公告)号：US20210357644A1
公开(公告)日：2021-11-18
申请号：US16876540
申请日：2020-05-18
Applicant: Adobe Inc.
Inventor： Rajiv Bhawanji Jain , Vlad Ion Morariu , Vitali Petsiuk , Varun Manjunatha , Ashutosh Mehra , Vicente Ignacio Ordonez Roman
Abstract: Introduced here are computer programs and associated computer-implemented techniques for creating visualizations to explain the outputs produced by models designed for object detection. To accomplish this, a graphics editing platform can obtain a reference output that identifies a region of pixels in a digital image that allegedly contains an object. Then, the graphics editing platform can compute the similarity between the reference output and a series of outputs generated by a model upon being applied to masked versions of the digital image. A visualization component can be produced based on the similarity.
-
公开(公告)号：US11886815B2
公开(公告)日：2024-01-30
申请号：US17333892
申请日：2021-05-28
Applicant: Adobe Inc.
Inventor： Jiuxiang Gu , Vlad Morariu , Varun Manjunatha , Tong Sun , Rajiv Jain , Peizhao Li , Jason Kuen , Handong Zhao
IPC: G06F40/279 , G06F40/205 , G06F16/93 , G06F40/30 , G06N3/088 , G06N3/045
CPC classification number: G06F40/279 , G06F16/93 , G06F40/205 , G06F40/30 , G06N3/045 , G06N3/088
Abstract: One example method involves operations for a processing device that include receiving, by a machine learning model trained to generate a search result, a search query for a text input. The machine learning model is trained by receiving pre-training data that includes multiple documents. Pre-training the machine learning model by generating, using an encoder, feature embeddings for each of the documents included in the pre-training data. The feature embeddings are generated by applying a masking function to visual and textual features in the documents. Training the machine learning model also includes generating, using the feature embeddings, output features for the documents by concatenating the feature embeddings and applying a non-linear mapping to the feature embeddings. Training the machine learning model further includes applying a linear classifier to the output features. Additionally, operations include generating, for display, a search result using the machine learning model based on the input.
-
Patent Agency Ranking
公开(公告)号：US20240028972A1
公开(公告)日：2024-01-25
申请号：US17815448
申请日：2022-07-27
Applicant: Adobe Inc.
Inventor： Christopher Tensmeyer , Nikolaos Barmpalios , Sruthi Madapoosi Ravi , Ruchi Deshpande , Varun Manjunatha , Smitha Bangalore Naresh , Priyank Mathur , Oghenetegiri Sido
CPC classification number: G06N20/20 , G06K9/6262 , G06K9/6256
Abstract: Techniques for training for and determining a confidence of an output of a machine learning model are disclosed. Such techniques include, in some embodiments, receiving, from the machine learning model configured to receive information associated with a data object, information associated with a predicted structure for the data object; encoding, using a second machine learning model, the information associated with the predicted structure for the data object to produce encoded input channels; evaluating, using the second machine learning model, the information associated with the data object with the encoded input channels; and based on the evaluating, determining, using the second machine learning model, a probability of correctness of the predicted structure for the data object.
-
公开(公告)号：US11783008B2
公开(公告)日：2023-10-10
申请号：US17091403
申请日：2020-11-06
Applicant: Adobe Inc.
Inventor： Rajiv Jain , Varun Manjunatha , Joseph Barrow , Vlad Ion Morariu , Franck Dernoncourt , Sasha Spala , Nicholas Miller
IPC: G06F18/214 , G06F40/30 , G06F40/117 , G06V30/413 , G06F18/21 , G06F18/2415 , G06F16/33
CPC classification number: G06F18/2148 , G06F18/217 , G06F18/2415 , G06F40/117 , G06F40/30 , G06V30/413 , G06F16/33 , G06V2201/10
Abstract: Certain embodiments involve using a machine-learning tool to generate metadata identifying segments and topics for text within a document. For instance, in some embodiments, a text processing system obtains input text and applies a segmentation-and-labeling model to the input text. The segmentation-and-labeling model is trained to generate a predicted segment for the input text using a segmentation network. The segmentation-and-labeling model is also trained to generate a topic for the predicted segment using a pooling network of the model to the predicted segment. The output of the model is usable for generating metadata identifying the predicted segment and the associated topic.
-
8.发明申请公开(公告)号：US20220318505A1
公开(公告)日：2022-10-06
申请号：US17223166
申请日：2021-04-06
Applicant: ADOBE INC.
Inventor： Amir Pouran Ben Veyseh , Franck Dernoncourt , Quan Tran , Varun Manjunatha , Lidan Wang , Rajiv Jain , Doo Soon Kim , Walter Chang
IPC: G06F40/284 , G06F40/211 , G06F40/30 , G06F40/126 , G06N3/04 , G06N3/08
Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure receive a document comprising a plurality of words organized into a plurality of sentences, the words comprising an event trigger word and an argument candidate word, generate word representation vectors for the words, generate a plurality of document structures including a semantic structure for the document based on the word representation vectors, a syntax structure representing dependency relationships between the words, and a discourse structure representing discourse information of the document based on the plurality of sentences, generate a relationship representation vector based on the document structures, and predict a relationship between the event trigger word and the argument candidate word based on the relationship representation vector.
-
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.
-
公开(公告)号：US11978272B2
公开(公告)日：2024-05-07
申请号：US17883811
申请日：2022-08-09
Applicant: Adobe Inc.
Inventor： Kai Li , Christopher Alan Tensmeyer , Curtis Michael Wigington , Handong Zhao , Nikolaos Barmpalios , Tong Sun , Varun Manjunatha , Vlad Ion Morariu
IPC: G06V30/413 , G06F17/18 , G06F18/213 , G06F18/2415 , G06N3/047 , G06N3/084 , G06N20/00 , G06N20/10 , G06V10/25 , G06V10/82 , G06V20/20 , G06V30/19 , G06V30/414
CPC classification number: G06V30/413 , G06F17/18 , G06F18/213 , G06F18/2415 , G06N3/047 , G06N3/084 , G06N20/00 , G06N20/10 , G06V10/25 , G06V10/82 , G06V20/20 , G06V30/19173 , G06V30/414
Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.
-
-
-
-
-
-
-
-
-
Search Results
28
records
(took 0.02 seconds)
