-
公开(公告)号：US20210073267A1
公开(公告)日：2021-03-11
申请号：US16564831
申请日：2019-09-09
Applicant: Adobe, Inc.
Inventor： Ayush Chopra , Mausoom Sarkar , Jonas Dahl , Hiresh Gupta , Balaji Krishnamurthy , Abhishek Sinha
IPC: G06F16/535 , G06K9/62 , G06F16/55 , G06N3/04 , G06F17/15
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group). Based on the generated tags, the disclosed systems can respond to tag queries and search queries.
-
公开(公告)号：US20200134056A1
公开(公告)日：2020-04-30
申请号：US16177243
申请日：2018-10-31
Applicant: Adobe Inc.
Inventor： Mausoom Sarkar , Hiresh Gupta , Abhishek Sinha
Abstract: Digital image search training techniques and machine-learning architectures are described. In one example, a query digital image is received by service provider system, which is then used to select at least one positive sample digital image, e.g., having a same product ID. A plurality of negative sample digital images is also selected by the service provider system based on the query digital image, e.g., having different product IDs. The at least one positive sample digital image and the plurality of negative samples are then aggregated by the service provider system into a single aggregated digital image. At least one neural network is then trained by the service provider system using a loss function based on a feature comparison between the query digital image and samples from the aggregated digital image in a single pass.
-
公开(公告)号：US11983946B2
公开(公告)日：2024-05-14
申请号：US17517434
申请日：2021-11-02
Applicant: Adobe Inc.
Inventor： Shripad Deshmukh , Milan Aggarwal , Mausoom Sarkar , Hiresh Gupta
IPC: G06V30/414 , G06F18/21 , G06N3/08 , G06V10/94 , G06V30/18 , G06V30/262
CPC classification number: G06V30/414 , G06F18/21 , G06N3/08 , G06V10/95 , G06V30/18 , G06V30/274
Abstract: In implementations of refining element associations for form structure extraction, a computing device implements a structure system to receive estimate data describing estimated associations of elements included in a form and a digital image depicting the form. An image patch is extracted from the digital image, and the image patch depicts a pair of elements of the elements included in the form. The structure system encodes an indication of whether the pair of elements have an association of the estimated associations. An indication is generated that the pair of elements have a particular association based at least partially on the encoded indication, bounding boxes of the pair of elements, and text depicted in the image patch.
-
公开(公告)号：US11386144B2
公开(公告)日：2022-07-12
申请号：US16564831
申请日：2019-09-09
Applicant: Adobe, Inc.
Inventor： Ayush Chopra , Mausoom Sarkar , Jonas Dahl , Hiresh Gupta , Balaji Krishnamurthy , Abhishek Sinha
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group). Based on the generated tags, the disclosed systems can respond to tag queries and search queries.
-
公开(公告)号：US11734337B2
公开(公告)日：2023-08-22
申请号：US17806922
申请日：2022-06-14
Applicant: Adobe Inc.
Inventor： Ayush Chopra , Mausoom Sarkar , Jonas Dahl , Hiresh Gupta , Balaji Krishnamurthy , Abhishek Sinha
IPC: G06F16/532 , G06F16/535 , G06F17/15 , G06N3/04 , G06F16/55 , G06F18/22 , G06F18/24 , G06V10/764 , G06V10/82 , G06V10/44
CPC classification number: G06F16/532 , G06F16/535 , G06F16/55 , G06F17/15 , G06F18/22 , G06F18/24 , G06N3/04 , G06V10/454 , G06V10/764 , G06V10/82
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group). Based on the generated tags, the disclosed systems can respond to tag queries and search queries.
-
Patent Agency Ranking
公开(公告)号：US20230134460A1
公开(公告)日：2023-05-04
申请号：US17517434
申请日：2021-11-02
Applicant: Adobe Inc.
Inventor： Shripad Deshmukh , Milan Aggarwal , Mausoom Sarkar , Hiresh Gupta
Abstract: In implementations of refining element associations for form structure extraction, a computing device implements a structure system to receive estimate data describing estimated associations of elements included in a form and a digital image depicting the form. An image patch is extracted from the digital image, and the image patch depicts a pair of elements of the elements included in the form. The structure system encodes an indication of whether the pair of elements have an association of the estimated associations. An indication is generated that the pair of elements have a particular association based at least partially on the encoded indication, bounding boxes of the pair of elements, and text depicted in the image patch.
-
公开(公告)号：US11972466B2
公开(公告)日：2024-04-30
申请号：US16417373
申请日：2019-05-20
Applicant: ADOBE INC.
Inventor： Jonas Dahl , Mausoom Sarkar , Hiresh Gupta , Balaji Krishnamurthy , Ayush Chopra , Abhishek Sinha
IPC: G06Q30/0601 , G06F16/583
CPC classification number: G06Q30/0625 , G06F16/5854
Abstract: A search system provides search results with images of products based on associations of primary products and secondary products from product image sets. The search system analyzes a product image set containing multiple images to determine a primary product and secondary products. Information associating the primary and secondary products are stored in a search index. When the search system receives a query image containing a search product, the search index is queried using the search product to identify search result images based on associations of products in the search index, and the result images are provided as a response to the query image.
-
公开(公告)号：US20220309093A1
公开(公告)日：2022-09-29
申请号：US17806922
申请日：2022-06-14
Applicant: Adobe Inc.
Inventor： Ayush Chopra , Mausoom Sarkar , Jonas Dahl , Hiresh Gupta , Balaji Krishnamurthy , Abhishek Sinha
IPC: G06F16/535 , G06K9/62 , G06F17/15 , G06N3/04 , G06F16/55
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group). Based on the generated tags, the disclosed systems can respond to tag queries and search queries.
-
公开(公告)号：US20200372560A1
公开(公告)日：2020-11-26
申请号：US16417373
申请日：2019-05-20
Applicant: ADOBE INC.
Inventor： Jonas Dahl , Mausoom Sarkar , Hiresh Gupta , Balaji Krishnamurthy , Ayush Chopra , Abhishek Sinha
Abstract: A search system provides search results with images of products based on associations of primary products and secondary products from product image sets. The search system analyzes a product image set containing multiple images to determine a primary product and secondary products. Information associating the primary and secondary products are stored in a search index. When the search system receives a query image containing a search product, the search index is queried using the search product to identify search result images based on associations of products in the search index, and the result images are provided as a response to the query image.
-
公开(公告)号：US10831818B2
公开(公告)日：2020-11-10
申请号：US16177243
申请日：2018-10-31
Applicant: Adobe Inc.
Inventor： Mausoom Sarkar , Hiresh Gupta , Abhishek Sinha
IPC: G06K9/54 , G06F16/58 , G06N3/08 , G06F16/56 , G06F16/583
Abstract: Digital image search training techniques and machine-learning architectures are described. In one example, a query digital image is received by service provider system, which is then used to select at least one positive sample digital image, e.g., having a same product ID. A plurality of negative sample digital images is also selected by the service provider system based on the query digital image, e.g., having different product IDs. The at least one positive sample digital image and the plurality of negative samples are then aggregated by the service provider system into a single aggregated digital image. At least one neural network is then trained by the service provider system using a loss function based on a feature comparison between the query digital image and samples from the aggregated digital image in a single pass.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.014 seconds)
