Patents by Inventor Vlad Ion Morariu
Vlad Ion Morariu 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: 11995394Abstract: Systems and methods for document editing are provided. One aspect of the systems and methods includes obtaining a document and a natural language edit request. Another aspect of the systems and methods includes generating a structured edit command using a machine learning model based on the document and the natural language edit request. Yet another aspect of the systems and methods includes generating a modified document based on the document and the structured edit command, where the modified document includes a revision of the document that incorporates the natural language edit request.Type: GrantFiled: February 7, 2023Date of Patent: May 28, 2024Assignee: ADOBE INC.Inventors: Vlad Ion Morariu, Puneet Mathur, Rajiv Bhawanji Jain, Jiuxiang Gu, Franck Dernoncourt
-
Patent number: 11978272Abstract: 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.Type: GrantFiled: August 9, 2022Date of Patent: May 7, 2024Assignee: Adobe Inc.Inventors: Kai Li, Christopher Alan Tensmeyer, Curtis Michael Wigington, Handong Zhao, Nikolaos Barmpalios, Tong Sun, Varun Manjunatha, Vlad Ion Morariu
-
Publication number: 20240135096Abstract: Systems and methods for document classification are described. Embodiments of the present disclosure generate classification data for a plurality of samples using a neural network trained to identify a plurality of known classes; select a set of samples for annotation from the plurality of samples using an open-set metric based on the classification data, wherein the annotation includes an unknown class; and train the neural network to identify the unknown class based on the annotation of the set of samples.Type: ApplicationFiled: October 23, 2022Publication date: April 25, 2024Inventors: Rajiv Bhawanji Jain, Michelle Yuan, Vlad Ion Morariu, Ani Nenkova Nenkova, Smitha Bangalore Naresh, Nikolaos Barmpalios, Ruchi Deshpande, Ruiyi Zhang, Jiuxiang Gu, Varun Manjunatha, Nedim Lipka, Andrew Marc Greene
-
Patent number: 11922110Abstract: Systems and techniques for generating responsive documents are described. Digital content is organized into a structure that defines how content is presented when a document is displayed by a computing device. To generate the responsive document, relationships are defined among different digital content objects, such as groups of content objects to be presented together and content objects that are to be presented as alternatives of one another. Responsive patterns are assigned to grouped content objects, where each responsive pattern defines different layout configurations for displaying grouped content objects based on computing device display characteristics. In some implementations, multiple responsive patterns are assigned to a single content group and individual responsive patterns are associated with activation ranges for display characteristics that activate the responsive pattern.Type: GrantFiled: November 24, 2021Date of Patent: March 5, 2024Assignees: Adobe Inc., University of Maryland, College ParkInventors: Vlad Ion Morariu, Yuexi Chen, Christopher Alan Tensmeyer, Zhicheng Liu, Lars Niklas Emanuel Elmqvist
-
Patent number: 11880648Abstract: Embodiments provide systems, methods, and computer storage media for extracting semantic labels for field widgets of form fields in unfilled forms. In some embodiments, a processing device accesses a representation of a fillable widget of a form field of an unfilled form. The processing device generates an encoded input representing text and layout of a sequence of tokens in a neighborhood of the fillable widget. The processing device uses a machine learning model to extract a semantic label representing a field type of the fillable widget in view of the encoded input. The processing device causes execution of an action using the semantic label.Type: GrantFiled: November 22, 2021Date of Patent: January 23, 2024Assignee: Adobe Inc.Inventors: Aparna Garimella, Sumit Shekhar, Bhanu Prakash Reddy Guda, Vinay Aggarwal, Vlad Ion Morariu, Ashutosh Mehra
-
Publication number: 20230409672Abstract: 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.Type: ApplicationFiled: September 5, 2023Publication date: December 21, 2023Inventors: Rajiv Jain, Varun Manjunatha, Joseph Barrow, Vlad Ion Morariu, Franck Dernoncourt, Sasha Spala, Nicholas Miller
-
Publication number: 20230376687Abstract: Embodiments are provided for facilitating multimodal extraction across multiple granularities. In one implementation, a set of features of a document for a plurality of granularities of the document is obtained. Via a machine learning model, the set of features of the document are modified to generate a set of modified features using a set of self-attention values to determine relationships within a first type of feature and a set of cross-attention values to determine relationships between the first type of feature and a second type of feature. Thereafter, the set of modified features are provided to a second machine learning model to perform a classification task.Type: ApplicationFiled: May 17, 2022Publication date: November 23, 2023Inventors: Vlad Ion Morariu, Tong Sun, Nikolaos Barmpalios, Zilong Wang, Jiuxiang Gu, Ani Nenkova Nenkova, Christopher Tensmeyer
-
Publication number: 20230368003Abstract: The technology described herein is directed to an adaptive sparse attention pattern that is learned during fine-tuning and deployed in a machine-learning model. In aspects, a row or a column in an attention matrix with an importance score for a task that is above a threshold importance score is identified. The important row or the column is included in an adaptive attention pattern used with a machine-learning model having a self-attention operation. In response to an input, a task-specific inference is generated for the input using the machine-learning model with the adaptive attention pattern.Type: ApplicationFiled: May 10, 2022Publication date: November 16, 2023Inventors: Jiuxiang Gu, Zihan Wang, Jason Wen Yong Kuen, Handong Zhao, Vlad Ion Morariu, Ruiyi Zhang, Ani Nenkova Nenkova, Tong Sun
-
Patent number: 11783008Abstract: 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.Type: GrantFiled: November 6, 2020Date of Patent: October 10, 2023Assignee: Adobe Inc.Inventors: Rajiv Jain, Varun Manjunatha, Joseph Barrow, Vlad Ion Morariu, Franck Dernoncourt, Sasha Spala, Nicholas Miller
-
Publication number: 20230230406Abstract: Methods and systems are provided for facilitating identification of fillable regions and/or data associated therewith. In embodiments, a candidate fillable region indicating a region in a form that is a candidate for being fillable is obtained. Textual context indicating text from the form and spatial context indicating positions of the text within the form are also obtained. Fillable region data associated with the candidate fillable region is generated, via a machine learning model, using the candidate fillable region, the textual context, and the spatial context. Thereafter, a fillable form is generated using the fillable region data, the fillable form having one or more fillable regions for accepting input.Type: ApplicationFiled: January 18, 2022Publication date: July 20, 2023Inventors: Ashutosh Mehra, Christopher Alan Tensmeyer, Vlad Ion Morariu, Jiuxiang Gu
-
Publication number: 20230154221Abstract: The technology described includes methods for pretraining a document encoder model based on multimodal self cross-attention. One method includes receiving image data that encodes a set of pretraining documents. A set of sentences is extracted from the image data. A bounding box for each sentence is generated. For each sentence, a set of predicted features is generated by using an encoder machine-learning model. The encoder model performs cross-attention between a set of masked-textual features for the sentence and a set of masked-visual features for the sentence. The set of masked-textual features is based on a masking function and the sentence. The set of masked-visual features is based on the masking function and the corresponding bounding box. A document-encoder model is pretrained based on the set of predicted features for each sentence and pretraining tasks. The pretraining tasks includes masked sentence modeling, visual contrastive learning, or visual-language alignment.Type: ApplicationFiled: November 16, 2021Publication date: May 18, 2023Inventors: Jiuxiang Gu, Ani Nenkova Nenkova, Nikolaos Barmpalios, Vlad Ion Morariu, Tong Sun, Rajiv Bhawanji Jain, Jason wen yong Kuen, Handong Zhao
-
Publication number: 20230085687Abstract: Various disclosed embodiments can resolve output inaccuracies produced by many machine learning models. Embodiments use content order as input to machine learning model systems so that they can process documents according to the position or rank of instances in a document or image. In this way, the model is less likely to misclassify or incorrectly detect instances or the ordering between predicted instances. The content order in various embodiments can be used as an additional signal to classify or make predictions.Type: ApplicationFiled: November 21, 2022Publication date: March 23, 2023Inventors: Ashutosh MEHRA, Vlad Ion MORARIU, Kajal GUPTA, Jayant Vaibhav SRIVASTAVA, Curtis Michael WIGINGTON, Tushar TIWARI
-
Publication number: 20230033114Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure identify a claim from a document, wherein the claim corresponds to a topic, create a graph comprising a plurality of nodes having a plurality of node types and a plurality of edges having a plurality of edge types, wherein one of the nodes represents the claim, and wherein each of the edges represents a relationship between a corresponding pair of the nodes, encode the claim based on the graph using a graph convolutional network (GCN) to obtain an encoded claim, classify the claim by decoding the encoded claim to obtain a stance label that indicates a stance of the claim towards the topic, and transmit information indicating a viewpoint of the document towards the topic based on the stance label.Type: ApplicationFiled: July 23, 2021Publication date: February 2, 2023Inventors: Joseph Barrow, Rajiv Bhawanji Jain, Nedim Lipka, Vlad Ion Morariu, Franck Dernoncourt, Varun Manjunatha
-
Patent number: 11544503Abstract: 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.Type: GrantFiled: May 27, 2020Date of Patent: January 3, 2023Assignee: Adobe Inc.Inventors: Christopher Tensmeyer, Vlad Ion Morariu, Varun Manjunatha, Tong Sun, Nikolaos Barmpalios, Kai Li, Handong Zhao, Curtis Wigington
-
Publication number: 20220391768Abstract: 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.Type: ApplicationFiled: August 9, 2022Publication date: December 8, 2022Applicant: Adobe Inc.Inventors: Kai Li, Christopher Alan Tensmeyer, Curtis Michael Wigington, Handong Zhao, Nikolaos Barmpalios, Tong Sun, Varun Manjunatha, Vlad Ion Morariu
-
Patent number: 11508173Abstract: Various disclosed embodiments can resolve output inaccuracies produced by many machine learning models. Embodiments use content order as input to machine learning model systems so that they can process documents according to the position or rank of instances in a document or image. In this way, the model is less likely to misclassify or incorrectly detect instances or the ordering between predicted instances. The content order in various embodiments can be used as an additional signal to classify or make predictions.Type: GrantFiled: October 30, 2019Date of Patent: November 22, 2022Assignee: ADOBE INC.Inventors: Ashutosh Mehra, Vlad Ion Morariu, Kajal Gupta, Jayant Vaibhav Srivastava, Curtis Michael Wigington, Tushar Tiwari
-
Patent number: 11443193Abstract: 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.Type: GrantFiled: May 4, 2020Date of Patent: September 13, 2022Assignee: Adobe Inc.Inventors: Kai Li, Christopher Alan Tensmeyer, Curtis Michael Wigington, Handong Zhao, Nikolaos Barmpalios, Tong Sun, Varun Manjunatha, Vlad Ion Morariu
-
Publication number: 20220147838Abstract: Methods and systems disclosed herein relate generally to systems and methods for generating visual relationship graphs that identify relationships between objects depicted in an image. A vision-language application uses transformer encoders to generate a graph structure, in which the graph structure represents a dependency between a first region and a second region of an image. The dependency indicates that a contextual representation of the first region was derived, at least in part, by processing the second region. The contextual representation identifies a predicted identity of an image object depicted in the first region. The predicted identity is determined at least in part by identifying a relationship between the first region and other data objects associated with various modalities.Type: ApplicationFiled: November 9, 2020Publication date: May 12, 2022Inventors: Jiuxiang Gu, Vlad Ion Morariu, Tong Sun, Jason wen yong Kuen, Handong Zhao
-
Patent number: 11227159Abstract: 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.Type: GrantFiled: May 18, 2020Date of Patent: January 18, 2022Assignee: Adobe Inc.Inventors: Rajiv Bhawanji Jain, Vlad Ion Morariu, Vitali Petsiuk, Varun Manjunatha, Ashutosh Mehra, Vicente Ignacio Ordonez Roman
-
Publication number: 20210357644Abstract: 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.Type: ApplicationFiled: May 18, 2020Publication date: November 18, 2021Inventors: Rajiv Bhawanji Jain, Vlad Ion Morariu, Vitali Petsiuk, Varun Manjunatha, Ashutosh Mehra, Vicente Ignacio Ordonez Roman