公开(公告)号：US11783584B2

公开(公告)日：2023-10-10

申请号：US17691526

申请日：2022-03-10

申请人： Adobe Inc.

发明人： Niyati Himanshu Chhaya ,  Tripti Shukla ,  Jeevana Kruthi Karnuthala ,  Bhanu Prakash Reddy Guda ,  Ayudh Saxena ,  Abhinav Bohra ,  Abhilasha Sancheti ,  Aanisha Bhattacharyya

IPC分类号： G06V20/40 ,  G06N20/00 ,  G06F16/73 ,  G06V10/86 ,  G06F40/166

CPC分类号： G06V20/47 ,  G06F16/73 ,  G06F40/166 ,  G06N20/00 ,  G06V10/86 ,  G06V20/41

摘要： Techniques are described that support automated generation of a digital document from digital videos using machine learning. The digital document includes textual components that describe a sequence of entity and action descriptions from the digital video. These techniques are usable to generate a single digital document based on a plurality of digital videos as well as incorporate user-specified constraints in the generation of the digital document.

公开(公告)号：US20230419666A1

公开(公告)日：2023-12-28

申请号：US18464493

申请日：2023-09-11

申请人： Adobe Inc.

发明人： Niyati Himanshu Chhaya ,  Tripti Shukla ,  Jeevana Kruthi Karnuthala ,  Bhanu Prakash Reddy Guda ,  Ayudh Saxena ,  Abhinav Bohra ,  Abhilasha Sancheti ,  Aanisha Bhattacharyya

IPC分类号： G06V20/40 ,  G06F16/73 ,  G06V10/86 ,  G06F40/166 ,  G06N20/00

CPC分类号： G06V20/47 ,  G06F16/73 ,  G06V10/86 ,  G06V20/41 ,  G06F40/166 ,  G06N20/00

摘要： Techniques are described that support automated generation of a digital document from digital videos using machine learning. The digital document includes textual components that describe a sequence of entity and action descriptions from the digital video. These techniques are usable to generate a single digital document based on a plurality of digital videos as well as incorporate user-specified constraints in the generation of the digital document.

公开(公告)号：US20230196008A1

公开(公告)日：2023-06-22

申请号：US18170125

申请日：2023-02-16

申请人： Adobe Inc.

发明人： Vinay Aggarwal ,  Vishwa Vinay ,  Rizurekh Saha ,  Prabhat Mahapatra ,  Niyati Himanshu Chhaya ,  Harshit Agrawal ,  Chloe McConnell ,  Bhanu Prakash Reddy Guda ,  Balaji Vasan Srinivasan

IPC分类号： G06F40/186 ,  G06F40/30 ,  G06F40/109 ,  G06F18/2411 ,  G06N20/00

CPC分类号： G06F40/186 ,  G06F40/30 ,  G06F40/109 ,  G06F18/2411 ,  G06N20/00

摘要： Techniques for template generation from image content includes extracting information associated with an input image. The information comprises: 1) layout information indicating positions of content corresponding to a content type of a plurality of content types within the input image; and 2) text attributes indicating at least a font of text included in the input image. A user-editable template having the characteristics of the input image is generated based on the layout information and the text attributes

公开(公告)号：US11880648B2

公开(公告)日：2024-01-23

申请号：US17456143

申请日：2021-11-22

申请人： ADOBE INC.

发明人： Aparna Garimella ,  Sumit Shekhar ,  Bhanu Prakash Reddy Guda ,  Vinay Aggarwal ,  Vlad Ion Morariu ,  Ashutosh Mehra

IPC分类号： G06F40/174 ,  G06F40/30 ,  G06F40/284 ,  G06N3/045

CPC分类号： G06F40/174 ,  G06F40/284 ,  G06F40/30 ,  G06N3/045

摘要： 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.

公开(公告)号：US20230114742A1

公开(公告)日：2023-04-13

申请号：US17450250

申请日：2021-10-07

申请人： Adobe Inc.

发明人： Vinay Aggarwal ,  Vishwa Vinay ,  Rizurekh Saha ,  Prabhat Mahapatra ,  Niyati Himanshu Chhaya ,  Harshit Agrawal ,  Chloe McConnell ,  Bhanu Prakash Reddy Guda ,  Balaji Vasan Srinivasan

IPC分类号： G06F40/186 ,  G06F40/109 ,  G06N20/00 ,  G06F40/30 ,  G06K9/62

摘要： Techniques for template generation from image content includes extracting information associated with an input image. The information comprises: 1) layout information indicating positions of content corresponding to a content type of a plurality of content types within the input image; and 2) text attributes indicating at least a font of text included in the input image. A user-editable template having the characteristics of the input image is generated based on the layout information and the text attributes

公开(公告)号：US20230161952A1

公开(公告)日：2023-05-25

申请号：US17456143

申请日：2021-11-22

申请人： ADOBE INC.

发明人： Aparna Garimella ,  Sumit Shekhar ,  Bhanu Prakash Reddy Guda ,  Vinay Aggarwal ,  Vlad Ion Morariu ,  Ashutosh Mehra

IPC分类号： G06F40/174 ,  G06F40/284 ,  G06F40/30 ,  G06N3/04

CPC分类号： G06F40/174 ,  G06F40/284 ,  G06F40/30 ,  G06N3/0454

摘要： 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.

公开(公告)号：US11610054B1

公开(公告)日：2023-03-21

申请号：US17450250

申请日：2021-10-07

申请人： Adobe Inc.

发明人： Vinay Aggarwal ,  Vishwa Vinay ,  Rizurekh Saha ,  Prabhat Mahapatra ,  Niyati Himanshu Chhaya ,  Harshit Agrawal ,  Chloe McConnell ,  Bhanu Prakash Reddy Guda ,  Balaji Vasan Srinivasan

IPC分类号： G06F40/186 ,  G06F40/109 ,  G06K9/62 ,  G06F40/30 ,  G06N20/00

摘要： Techniques for template generation from image content includes extracting information associated with an input image. The information comprises: 1) layout information indicating positions of content corresponding to a content type of a plurality of content types within the input image; and 2) text attributes indicating at least a font of text included in the input image. A user-editable template having the characteristics of the input image is generated based on the layout information and the text attributes.

公开(公告)号：US20220129621A1

公开(公告)日：2022-04-28

申请号：US17079681

申请日：2020-10-26

申请人： Adobe Inc.

发明人： Bhanu Prakash Reddy Guda ,  Niyati Chhaya ,  Aparna Garimella

IPC分类号： G06F40/166 ,  G10L25/63 ,  G06N20/00 ,  G06K9/62

摘要： Certain embodiments involve using machine-learning tools that include Bidirectional Encoder Representations from Transformers (“BERT”) language models for predicting emotional responses to text by, for example, target readers having certain demographics. For instance, a machine-learning model includes, at least, a BERT encoder and a classification module that is trained to predict demographically specific emotional responses. The BERT encoder encodes the input text into an input text vector. The classification module generates, from the input text vector and an input demographics vector representing a demographic profile of the reader, an emotional response score.

公开(公告)号：US11948387B2

公开(公告)日：2024-04-02

申请号：US17170307

申请日：2021-02-08

申请人： ADOBE INC.

发明人： Sumit Shekhar ,  Bhanu Prakash Reddy Guda ,  Ashutosh Chaubey ,  Ishan Jindal ,  Avneet Jain

IPC分类号： G06V40/10 ,  G06F18/21 ,  G06F18/211 ,  G06F18/214 ,  G06N20/00 ,  G06V20/20

CPC分类号： G06V40/10 ,  G06F18/211 ,  G06F18/2155 ,  G06F18/2178 ,  G06N20/00 ,  G06V20/20

摘要： Systems and methods for training an object detection network are described. Embodiments train an object detection network using a labeled training set, wherein each element of the labeled training set includes an image and ground truth labels for object instances in the image, predict annotation data for a candidate set of unlabeled data using the object detection network, select a sample image from the candidate set using a policy network, generate a labeled sample based on the selected sample image and the annotation data, wherein the labeled sample includes labels for a plurality of object instances in the sample image, and perform additional training on the object detection network based at least in part on the labeled sample.

公开(公告)号：US11914951B2

公开(公告)日：2024-02-27

申请号：US18170125

申请日：2023-02-16

申请人： Adobe Inc.

发明人： Vinay Aggarwal ,  Vishwa Vinay ,  Rizurekh Saha ,  Prabhat Mahapatra ,  Niyati Himanshu Chhaya ,  Harshit Agrawal ,  Chloe McConnell ,  Bhanu Prakash Reddy Guda ,  Balaji Vasan Srinivasan

IPC分类号： G06F40/186 ,  G06F40/109 ,  G06F40/30 ,  G06N20/00 ,  G06F18/2411

CPC分类号： G06F40/186 ,  G06F18/2411 ,  G06F40/109 ,  G06F40/30 ,  G06N20/00

摘要： Techniques for template generation from image content include extracting information associated with an input image. The information comprises: 1) layout information indicating positions of content corresponding to a content type of a plurality of content types within the input image; and 2) text attributes indicating at least a font of text included in the input image. A user-editable template having the characteristics of the input image is generated based on the layout information and the text attributes.