Patents by Inventor Jonas Dahl
Jonas Dahl has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11972466Abstract: 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.Type: GrantFiled: May 20, 2019Date of Patent: April 30, 2024Assignee: ADOBE INCInventors: Jonas Dahl, Mausoom Sarkar, Hiresh Gupta, Balaji Krishnamurthy, Ayush Chopra, Abhishek Sinha
-
Patent number: 11734337Abstract: 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).Type: GrantFiled: June 14, 2022Date of Patent: August 22, 2023Assignee: Adobe Inc.Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
-
Patent number: 11593438Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for clustering media items in a semantic space to generate theme-based folders that organize media items by content theme. In particular, the disclosed systems can access media items that are stored in an original folder structure. The disclosed systems can generate content-based tags for each media item in a collection of media items. Based on the generated tags, the disclosed systems can map the collection of media items to a semantic space and cluster the collection of media items. The disclosed systems determine themes for the clusters based on the generated tags. The disclosed systems can present a media item navigation graphical user interface comprising the collection of media items organized by themes. The disclosed system can present the media item navigation graphical user interface without altering the original folder structure.Type: GrantFiled: May 7, 2021Date of Patent: February 28, 2023Assignee: Adobe Inc.Inventors: Jonas Dahl, Sudheer Tumu, Nithyanand Kota, Mihir Naware, Maneesh Dewan, Jatin Chhugani, Ganesh Satish Mallya
-
Publication number: 20220309093Abstract: 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).Type: ApplicationFiled: June 14, 2022Publication date: September 29, 2022Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
-
Patent number: 11386144Abstract: 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).Type: GrantFiled: September 9, 2019Date of Patent: July 12, 2022Assignee: Adobe Inc.Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
-
Patent number: 11367271Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for one-shot and few-shot image segmentation on classes of objects that were not represented during training. In some embodiments, a dual prediction scheme may be applied in which query and support masks are jointly predicted using a shared decoder, which aids in similarity propagation between the query and support features. Additionally or alternatively, foreground and background attentive fusion may be applied to utilize cues from foreground and background feature similarities between the query and support images. Finally, to prevent overfitting on class-conditional similarities across training classes, input channel averaging may be applied for the query image during training. Accordingly, the techniques described herein may be used to achieve state-of-the-art performance for both one-shot and few-shot segmentation tasks.Type: GrantFiled: June 19, 2020Date of Patent: June 21, 2022Assignee: Adobe Inc.Inventors: Mayur Hemani, Siddhartha Gairola, Ayush Chopra, Balaji Krishnamurthy, Jonas Dahl
-
Publication number: 20210397876Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for one-shot and few-shot image segmentation on classes of objects that were not represented during training. In some embodiments, a dual prediction scheme may be applied in which query and support masks are jointly predicted using a shared decoder, which aids in similarity propagation between the query and support features. Additionally or alternatively, foreground and background attentive fusion may be applied to utilize cues from foreground and background feature similarities between the query and support images. Finally, to prevent overfitting on class-conditional similarities across training classes, input channel averaging may be applied for the query image during training. Accordingly, the techniques described herein may be used to achieve state-of-the-art performance for both one-shot and few-shot segmentation tasks.Type: ApplicationFiled: June 19, 2020Publication date: December 23, 2021Inventors: Mayur Hemani, Siddhartha Gairola, Ayush Chopra, Balaji Krishnamurthy, Jonas Dahl
-
Publication number: 20210263970Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for clustering media items in a semantic space to generate theme-based folders that organize media items by content theme. In particular, the disclosed systems can access media items that are stored in an original folder structure. The disclosed systems can generate content-based tags for each media item in a collection of media items. Based on the generated tags, the disclosed systems can map the collection of media items to a semantic space and cluster the collection of media items. The disclosed systems determine themes for the clusters based on the generated tags. The disclosed systems can present a media item navigation graphical user interface comprising the collection of media items organized by themes. The disclosed system can present the media item navigation graphical user interface without altering the original folder structure.Type: ApplicationFiled: May 7, 2021Publication date: August 26, 2021Inventors: Jonas Dahl, Sudheer Tumu, Nithyanand Kota, Mihir Naware, Maneesh Dewan, Jatin Chhugani, Ganesh Satish Mallya
-
Patent number: 11030257Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for clustering media items in a semantic space to generate theme-based folders that organize media items by content theme. In particular, the disclosed systems can access media items that are stored in an original folder structure. The disclosed systems can generate content-based tags for each media item in a collection of media items. Based on the generated tags, the disclosed systems can map the collection of media items to a semantic space and cluster the collection of media items. The disclosed systems determine themes for the clusters based on the generated tags. The disclosed systems can present a media item navigation graphical user interface comprising the collection of media items organized by themes. The disclosed system can present the media item navigation graphical user interface without altering the original folder structure.Type: GrantFiled: May 20, 2019Date of Patent: June 8, 2021Assignee: ADOBE INC.Inventors: Jonas Dahl, Sudheer Tumu, Nithyanand Kota, Mihir Naware, Maneesh Dewan, Jatin Chhugani, Ganesh Satish Mallya
-
Publication number: 20210150593Abstract: Methods and systems for creation of reviews are described. In some examples, an affinity between a reviewer and a customer is determined. A question is received from the customer, related to a merchant offering. The reviewer is provided with an option to create a new review based on the question, the option being provided to the reviewer based on the determined affinity.Type: ApplicationFiled: November 15, 2019Publication date: May 20, 2021Inventors: Siavash GHORBANI, Valerie TÖRNBLOM, Birk JERNSTRÖM, Jona DAHL, Petter NILSSON, Anders BERNTSSON, Anton REIMERTZ, Carl RIVERA
-
Publication number: 20210150604Abstract: Methods and systems for presenting a review are described. A set of reviews is presented in response to a first event associated with a first merchant offering. The set of reviews include a plurality of selected reviews associated with the first merchant offering. At least a first review in the plurality of selected reviews is selected, from a plurality of stored reviews, based on a match of one or more attributes between a profile of the first customer and a profile of a first reviewer associated with the first review.Type: ApplicationFiled: November 15, 2019Publication date: May 20, 2021Inventors: Siavash GHORBANI, Valerie TÖRNBLOM, Birk JERNSTRÖM, Jona DAHL, Petter NILSSON, Anders BERNTSSON, Anton REIMERTZ, Carl RIVERA
-
Publication number: 20210073267Abstract: 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).Type: ApplicationFiled: September 9, 2019Publication date: March 11, 2021Applicant: Adobe, Inc.Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
-
Publication number: 20200372560Abstract: 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.Type: ApplicationFiled: May 20, 2019Publication date: November 26, 2020Inventors: Jonas Dahl, Mausoom Sarkar, Hiresh Gupta, Balaji Krishnamurthy, Ayush Chopra, Abhishek Sinha
-
Publication number: 20200372073Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for clustering media items in a semantic space to generate theme-based folders that organize media items by content theme. In particular, the disclosed systems can access media items that are stored in an original folder structure. The disclosed systems can generate content-based tags for each media item in a collection of media items. Based on the generated tags, the disclosed systems can map the collection of media items to a semantic space and cluster the collection of media items. The disclosed systems determine themes for the clusters based on the generated tags. The disclosed systems can present a media item navigation graphical user interface comprising the collection of media items organized by themes. The disclosed system can present the media item navigation graphical user interface without altering the original folder structure.Type: ApplicationFiled: May 20, 2019Publication date: November 26, 2020Inventors: Jonas Dahl, Sudheer Tumu, Nithyanand Kota, Mihir Naware, Maneesh Dewan, Jatin Chhugani, Ganesh Satish Mallya
-
Patent number: 10628474Abstract: A method for generating summaries includes selecting a first subset of text units of a text composition to incorporate into a first summary of the text composition using a weighting of the text units that indicates for each text unit a relative importance of including the text unit in summaries of the text composition. The weighting of the text units is modified to reduce the relative importance of each text unit in the first subset based on the text unit having been selected for the first subset. A second subset of the text units is selected to incorporate into a second summary of the text composition using the modified weighting of the text units. At least one of the first summary and the second summary are provided to a user device.Type: GrantFiled: July 6, 2016Date of Patent: April 21, 2020Assignee: ADOBE INC.Inventors: Natwar Modani, Jonas Dahl, Harsh Jhamtani, Balaji Vasan Srinivasan
-
Publication number: 20180011931Abstract: A method for generating summaries includes selecting a first subset of text units of a text composition to incorporate into a first summary of the text composition using a weighting of the text units that indicates for each text unit a relative importance of including the text unit in summaries of the text composition. The weighting of the text units is modified to reduce the relative importance of each text unit in the first subset based on the text unit having been selected for the first subset. A second subset of the text units is selected to incorporate into a second summary of the text composition using the modified weighting of the text units. At least one of the first summary and the second summary are provided to a user device.Type: ApplicationFiled: July 6, 2016Publication date: January 11, 2018Inventors: NATWAR MODANI, Jonas Dahl, Harsh Jhamtani, Balaji Vasan Srinivasan