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：US20240419921A1

公开(公告)日：2024-12-19

申请号：US18336380

申请日：2023-06-16

Applicant: Adobe Inc.

Inventor： Joseph Barrow ,  Jennifer Healey ,  Franck Dernoncourt ,  Ani Nenkova ,  Vlad Morariu ,  Rajiv Jain ,  Nedim Lipka

IPC: G06F40/40 ,  G06F40/205 ,  G06V30/19

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that extract viewpoints from content for syntopical reading using an efficient claim-relation graph construction approach. For example, the disclosed systems utilize sentence transformers with claims from content to embed the claims within a metric space (as claim nodes). Furthermore, in some embodiments, the disclosed systems generate a claim relation graph for the claims by utilizing approximate nearest neighbor searches to determine relational edges between a claim node and the claim node's approximate nearest neighbors. Moreover, in some implementations, the disclosed systems utilize the claim relation graph with an edge weighted graph neural network to determine stance labels during extraction of viewpoints (e.g., stance, aspect, and topic) for the claims. Additionally, in one or more instances, the disclosed systems utilize the extracted viewpoints in content retrieval applications (e.g., viewpoint ranked search results and/or socially contextualized claims).

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

IPC: G06K9/62 ,  G06F11/32 ,  G06N3/04

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：US20240104951A1

公开(公告)日：2024-03-28

申请号：US17947737

申请日：2022-09-19

Applicant: ADOBE INC.

Inventor： Jiuxiang Gu ,  Vlad Morariu ,  Tong Sun ,  Jason wen yong Kuen ,  Ani Nenkova

IPC: G06V30/412 ,  G06V30/262 ,  G06V30/414

CPC classification number: G06V30/412 ,  G06V30/262 ,  G06V30/414

Abstract: In various examples, a table recognition model receives an image of a table and generates, using a first encoder of the table recognition machine learning model, an image feature vector including features extracted from the image of the table; generates, using a first decoder of the table recognition machine learning model and the image feature vector, a set of coordinates within the image representing rows and columns associated with the table, and generates, using a second decoder of the table recognition machine learning model and the image feature vector, a set of bounding boxes and semantic features associated with cells the table, then determines, using a third decoder of the table recognition machine learning model, a table structure associated with the table using the image feature vector, the set of coordinates, the set of bounding boxes, and the semantic features.

公开(公告)号：US20220277431A1

公开(公告)日：2022-09-01

申请号：US17187080

申请日：2021-02-26

Applicant: Adobe Inc.

Inventor： Christopher Tensmeyer ,  Vlad Morariu ,  Michael Brodie

IPC: G06T5/50 ,  G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: This disclosure describes one or more embodiments of systems, non-transitory computer-readable media, and methods that can learn or identify a learned-initialization-latent vector for an initialization digital image and reconstruct a target digital image using an image-generating-neural network based on a modified version of the learned-initialization-latent vector. For example, the disclosed systems learn a learned-initialization-latent vector from an initialization image utilizing a high number (e.g., thousands) of learning iterations on an image-generating-neural network (e.g., a GAN). Then, the disclosed systems can modify the learned-initialization-latent vector (of the initialization image) to generate modified or reconstructed versions of target images using the image-generating-neural network. For instance, the disclosed systems utilize the learned-initialization-latent vector as a starting point to learn a learned-latent vector for a target image that an image-generating-neural network converts into a high-fidelity reconstruction of the target image (with a reduced number of learning iterations).

公开(公告)号：US20240161529A1

公开(公告)日：2024-05-16

申请号：US18055752

申请日：2022-11-15

Applicant: Adobe Inc.

Inventor： Vlad Morariu ,  Puneet Mathur ,  Rajiv Jain ,  Ashutosh Mehra ,  Jiuxiang Gu ,  Franck Dernoncourt ,  Anandhavelu N ,  Quan Tran ,  Verena Kaynig-Fittkau ,  Nedim Lipka ,  Ani Nenkova

IPC: G06V30/413 ,  G06V10/82

CPC classification number: G06V30/413 ,  G06V10/82

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a digital document hierarchy comprising layers of parent-child element relationships from the visual elements. For example, for a layer of the layers, the disclosed systems determine, from the visual elements, candidate parent visual elements and child visual elements. In addition, for the layer of the layers, the disclosed systems generate, from the feature embeddings utilizing a neural network, element classifications for the candidate parent visual elements and parent-child element link probabilities for the candidate parent visual elements and the child visual elements. Moreover, for the layer, the disclosed systems select parent visual elements from the candidate parent visual elements based on the parent-child element link probabilities. Further, the disclosed systems utilize the digital document hierarchy to generate an interactive digital document from the digital document image.

公开(公告)号：US11893717B2

公开(公告)日：2024-02-06

申请号：US17187080

申请日：2021-02-26

Applicant: Adobe Inc.

Inventor： Christopher Tensmeyer ,  Vlad Morariu ,  Michael Brodie

IPC: G06T5/50 ,  G06N3/08 ,  G06N3/04 ,  G06F18/214

CPC classification number: G06T5/50 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: This disclosure describes one or more embodiments of systems, non-transitory computer-readable media, and methods that can learn or identify a learned-initialization-latent vector for an initialization digital image and reconstruct a target digital image using an image-generating-neural network based on a modified version of the learned-initialization-latent vector. For example, the disclosed systems learn a learned-initialization-latent vector from an initialization image utilizing a high number (e.g., thousands) of learning iterations on an image-generating-neural network (e.g., a GAN). Then, the disclosed systems can modify the learned-initialization-latent vector (of the initialization image) to generate modified or reconstructed versions of target images using the image-generating-neural network. For instance, the disclosed systems utilize the learned-initialization-latent vector as a starting point to learn a learned-latent vector for a target image that an image-generating-neural network converts into a high-fidelity reconstruction of the target image (with a reduced number of learning iterations).

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：US20200175095A1

公开(公告)日：2020-06-04

申请号：US16204918

申请日：2018-11-29

Applicant: Adobe Inc.

Inventor： Vlad Morariu ,  Rajiv Jain ,  Nishant Sankaran

IPC: G06F17/21 ,  G06K9/00 ,  G06K9/62 ,  G06N5/04

Abstract: In some embodiments, a computing system computes tags for an electronic document. The computing system identifies sets of objects for the electronic document by applying a set of object-recognition rules to the electronic document, with each object-recognition rule generating a set of identified objects. The computing system generates feature maps that represent a set of identified objects. The computing system generates a heat map that identifies attributes of the electronic document including object candidates of the electronic document by applying a page-segmentation machine-learning model to the electronic document. The computing system computes a tag by applying a fusion deep learning module to the feature map and the heat map to correlate a document object identified by the feature map with an attribute of the electronic document identified by the heat map. The computing system generates the tagged electronic document by applying the tag to the electronic document.

公开(公告)号：US20250013831A1

公开(公告)日：2025-01-09

申请号：US18493465

申请日：2023-10-24

Applicant: Adobe Inc. ,  University of Maryland

Inventor： Puneet Mathur ,  Vlad Morariu ,  Verena Kaynig-Fittkau ,  Jiuxiang Gu ,  Franck Dernoncourt ,  Quan Tran ,  Ani Nenkova ,  Dinesh Manocha ,  Rajiv Jain

IPC: G06F40/30

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a temporal dependency graph. For example, the disclosed systems generate from a text document, a structural vector, a syntactic vector, and a semantic vector. In some embodiments, the disclosed systems generate a multi-dimensional vector by combining the various vectors. In these or other embodiments, the disclosed systems generate an initial dependency graph structure and an adjacency matrix utilizing an iterative deep graph learning model. Further, in some embodiments, the disclosed systems generate an entity-level relation matrix utilizing a convolutional graph neural network. Moreover, in some embodiments, the disclosed systems generate a temporal dependency graph from the entity-level relation matrix and the adjacency matrix.