公开(公告)号：US20230161952A1

公开(公告)日：2023-05-25

申请号：US17456143

申请日：2021-11-22

Applicant: ADOBE INC.

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

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

CPC classification number: G06F40/174 ,  G06F40/284 ,  G06F40/30 ,  G06N3/0454

Abstract: 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：US11443389B2

公开(公告)日：2022-09-13

申请号：US17001984

申请日：2020-08-25

Applicant: Adobe Inc.

Inventor： Gaurush Hiranandani ,  Tanya Goyal ,  Sumit Shekhar ,  Payal Bajaj

IPC: G06Q40/00 ,  G06Q20/02 ,  G06Q20/12 ,  G06Q20/40

Abstract: Techniques and systems for determining paywall metrics are described. In an implementation, a candidate paywall metric is created that corresponds to an increased propensity of users to engage in a paid transaction when exposed to a paywall. In this way, providers of digital content may increase the proportion of users that perform a transaction when exposed to the paywall.

公开(公告)号：US20220019735A1

公开(公告)日：2022-01-20

申请号：US16929903

申请日：2020-07-15

Applicant: Adobe Inc.

Inventor： Sumit Shekhar ,  Zoya Bylinskii ,  Tushar Gurjar ,  Ritwick Chaudhry ,  Ayush Goyal

IPC: G06F40/205 ,  G06N20/00 ,  G06F16/9032 ,  G06F16/9538

Abstract: This disclosure describes methods, systems, and non-transitory computer readable media for automatically parsing infographics into segments corresponding to structured groups or lists and displaying the identified segments or reflowing the segments into various computing tasks. For example, the disclosed systems may utilize a novel infographic grouping taxonomy and annotation system to group elements within infographics. The disclosed systems can train and apply a machine-learning-detection model to generate infographic segments according to the infographic grouping taxonomy. By generating infographic segments, the disclosed systems can facilitate computing tasks, such as converting infographics into digital presentation graphics (e.g., slide carousels), reflow the infographic into query-and-response models, perform search functions, or other computational tasks.

公开(公告)号：US11769006B2

公开(公告)日：2023-09-26

申请号：US16929903

申请日：2020-07-15

Applicant: Adobe Inc.

Inventor： Sumit Shekhar ,  Zoya Bylinskii ,  Tushar Gurjar ,  Ritwick Chaudhry ,  Ayush Goyal

IPC: G06F40/205 ,  G06F16/9538 ,  G06F16/9032 ,  G06N20/00

CPC classification number: G06F40/205 ,  G06F16/90332 ,  G06F16/9538 ,  G06N20/00

Abstract: This disclosure describes methods, systems, and non-transitory computer readable media for automatically parsing infographics into segments corresponding to structured groups or lists and displaying the identified segments or reflowing the segments into various computing tasks. For example, the disclosed systems may utilize a novel infographic grouping taxonomy and annotation system to group elements within infographics. The disclosed systems can train and apply a machine-learning-detection model to generate infographic segments according to the infographic grouping taxonomy. By generating infographic segments, the disclosed systems can facilitate computing tasks, such as converting infographics into digital presentation graphics (e.g., slide carousels), reflow the infographic into query-and-response models, perform search functions, or other computational tasks.

公开(公告)号：US20230230358A1

公开(公告)日：2023-07-20

申请号：US17648482

申请日：2022-01-20

Applicant: ADOBE INC.

Inventor： Divya Kothandaraman ,  Sumit Shekhar ,  Abhilasha Sancheti ,  Manoj Ghuhan Arivazhagan ,  Tripti Shukla

IPC: G06V10/774 ,  G06V10/776 ,  G06V10/778 ,  G06V10/82

CPC classification number: G06V10/774 ,  G06V10/776 ,  G06V10/778 ,  G06V10/82

Abstract: Systems and methods for machine learning are described. The systems and methods include receiving target training data including a training image and ground truth label data for the training image, generating source network features for the training image using a source network trained on source training data, generating target network features for the training image using a target network, generating at least one attention map for training the target network based on the source network features and the target network features using a guided attention transfer network, and updating parameters of the target network based on the attention map and the ground truth label data.

公开(公告)号：US11322133B2

公开(公告)日：2022-05-03

申请号：US16934836

申请日：2020-07-21

Applicant: Adobe Inc.

Inventor： Sumit Shekhar ,  Gautam Choudhary ,  Abhilasha Sancheti ,  Shubhanshu Agarwal ,  E Santhosh Kumar ,  Rahul Saxena

IPC: G10L25/30 ,  G10L13/047

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate expressive audio for input texts based on a word-level analysis of the input text. For example, the disclosed systems can utilize a multi-channel neural network to generate a character-level feature vector and a word-level feature vector based on a plurality of characters of an input text and a plurality of words of the input text, respectively. In some embodiments, the disclosed systems utilize the neural network to generate the word-level feature vector based on contextual word-level style tokens that correspond to style features associated with the input text. Based on the character-level and word-level feature vectors, the disclosed systems can generate a context-based speech map. The disclosed systems can utilize the context-based speech map to generate expressive audio for the input text.

公开(公告)号：US20220028367A1

公开(公告)日：2022-01-27

申请号：US16934836

申请日：2020-07-21

Applicant: Adobe Inc.

Inventor： Sumit Shekhar ,  Gautam Choudhary ,  Abhilasha Sancheti ,  Shubhanshu Agarwal ,  E Santhosh Kumar ,  Rahul Saxena

IPC: G10L13/047 ,  G10L25/30

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate expressive audio for input texts based on a word-level analysis of the input text. For example, the disclosed systems can utilize a multi-channel neural network to generate a character-level feature vector and a word-level feature vector based on a plurality of characters of an input text and a plurality of words of the input text, respectively. In some embodiments, the disclosed systems utilize the neural network to generate the word-level feature vector based on contextual word-level style tokens that correspond to style features associated with the input text. Based on the character-level and word-level feature vectors, the disclosed systems can generate a context-based speech map. The disclosed systems can utilize the context-based speech map to generate expressive audio for the input text.

公开(公告)号：US10665030B1

公开(公告)日：2020-05-26

申请号：US16247235

申请日：2019-01-14

Applicant: Adobe Inc.

Inventor： Sumit Shekhar ,  Paridhi Maheshwari ,  Monisha J ,  Kundan Krishna ,  Amrit Singhal ,  Kush Kumar Singh

IPC: G06T19/00 ,  G06F40/40

Abstract: A natural language scene description is converted into a scene that is rendered in three dimensions by an augmented reality (AR) display device. Text-to-AR scene conversion allows a user to create an AR scene visualization through natural language text inputs that are easily created and well-understood by the user. The user can, for instance, select a pre-defined natural language description of a scene or manually enter a custom natural language description. The user can also select a physical real-world surface on which the AR scene is to be rendered. The AR scene is then rendered using the augmented reality display device according to its natural language description using 3D models of objects and humanoid characters with associated animations of those characters, as well as from extensive language-to-visual datasets. Using the display device, the user can move around the real-world environment and experience the AR scene from different angles.

公开(公告)号：US10311913B1

公开(公告)日：2019-06-04

申请号：US15902046

申请日：2018-02-22

Applicant: Adobe Inc.

Inventor： Sumit Shekhar ,  Harvineet Singh ,  Dhruv Singal ,  Atanu R. Sinha

IPC: G11B27/031 ,  G06K9/00 ,  G06K9/62

Abstract: Certain embodiments involve generating summarized versions of video content based on memorability of the video content. For example, a video summarization system accesses segments of an input video. The video summarization system identifies memorability scores for the respective segments. The video summarization system selects a subset of segments from the segments based on each computed memorability score in the subset having a threshold memorability score. The video summarization system generates visual summary content from the subset of the segments.

公开(公告)号：US11948387B2

公开(公告)日：2024-04-02

申请号：US17170307

申请日：2021-02-08

Applicant: ADOBE INC.

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

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

CPC classification number: G06V40/10 ,  G06F18/211 ,  G06F18/2155 ,  G06F18/2178 ,  G06N20/00 ,  G06V20/20

Abstract: 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.