Patents Assigned to Adobe Inc.
  • Publication number: 20210110151
    Abstract: Techniques are disclosed for identifying asides within a document, and detecting a display order of contents based of the identified asides. In a document, an “aside” represents a content region of the document that is distinct from the main content regions, and may be visually distinguishable from the main content region. In an example, a document is received, where the document lacks identification of asides. The document is analyzed to identify asides within the document. A display order of contents within the document is then determined, based on the identified asides. For example, in the display order, the asides are ordered between two segments of the main content and/or at a beginning or an end of the main content, but may not be ordered to be embedded in between a segment of the main content. The document is displayed in accordance with the display order.
    Type: Application
    Filed: October 10, 2019
    Publication date: April 15, 2021
    Applicant: Adobe Inc.
    Inventors: Sanjeev Tagra, Shawn Alan Gaither, Shagun Kush, Samarth Gupta, Sachin Soni, Nikolaos Barmpalios, Abhishek Jain, Naqushab Neyazee
  • Publication number: 20210110432
    Abstract: Automatic item placement recommendation is described. An item placement configuration system receives an item for which a recommended placement is to be generated and identifies an entity associated with the item. The item placement configuration system then identifies a multi-domain taxonomy that describes relationships between different entities based on items associated with the different entities published among different domains. A representation of the entity associated with the item to be placed is then identified within the multi-domain taxonomy, along with a representation of at least one similar entity. Upon identifying a similar entity, historic item placement metrics for the similar entity are leveraged to generate a placement recommendation for the received item. In some implementations, the placement recommendation is output with a visual indication of a similar entity and associated performance metrics that were considered in generating the recommended placement.
    Type: Application
    Filed: October 10, 2019
    Publication date: April 15, 2021
    Applicant: Adobe Inc.
    Inventors: Xiang Chen, Viswanathan Swaminathan, Somdeb Sarkhel
  • Publication number: 20210110153
    Abstract: Techniques described herein implement heading identification and classification for a digital document in a digital medium environment. A document analysis system is leveraged to extract structural features from a digital document, identify heading candidates from among the structural features, validate the headings candidates, and classify validated headings into different headings types. The classified headings are then utilized to generate a sectioned version of the digital document (“sectioned document”) that is divided into different sections based on the headings. Further, a document directory is generated that includes the headings and that enables navigation to different sections of the sectioned document.
    Type: Application
    Filed: October 9, 2019
    Publication date: April 15, 2021
    Applicant: Adobe Inc.
    Inventors: Mohit Gupta, Uttam Dwivedi, Shawn Alan Gaither, Jayant Vaibhav Srivastava, Ashutosh Mehra
  • Publication number: 20210110587
    Abstract: Automatic positioning of textual content within digital images is leveraged in a digital medium environment. Initially, user input is received to add textual content to a digital image. The digital image can then be processed to identify at least one object in the digital image using an image segmentation model. A placement region for the textual content that does not overlap the at least one object can be automatically determined. After the placement region is automatically determined, the digital image can be modified by positioning the textual content within the automatically determined placement region of the digital image. Positioning the textual content may include automatically adjusting the textual content to fit within the placement region, such as by automatically scaling or aligning the textual content.
    Type: Application
    Filed: October 14, 2019
    Publication date: April 15, 2021
    Applicant: Adobe Inc.
    Inventors: Vipul Aggarwal, Neel Kadia
  • Patent number: 10977549
    Abstract: In implementations of object animation using generative neural networks, one or more computing devices of a system implement an animation system for reproducing animation of an object in a digital video. A mesh of the object is obtained from a first frame of the digital video and a second frame of the digital video having the object is selected. Features of the object from the second frame are mapped to vertices of the mesh, and the mesh is warped based on the mapping. The warped mesh is rendered as an image by a neural renderer and compared to the object from the second frame to train a neural network. The rendered image is then refined by a generator of a generative adversarial network which includes a discriminator. The discriminator trains the generator to reproduce the object from the second frame as the refined image.
    Type: Grant
    Filed: February 14, 2019
    Date of Patent: April 13, 2021
    Assignee: Adobe Inc.
    Inventors: Vladimir Kim, Omid Poursaeed, Jun Saito, Elya Shechtman
  • Patent number: 10977767
    Abstract: Systems and techniques for propagating spot healing edits from a source image to a target image include receiving a source image depicting a face with a healing region and a target image depicting the face. The face is detected in the source image including detecting facial feature points in the source image. The face is identified in the target image including detecting facial feature points in the target image. Facial feature point correspondence is determined between the facial feature points of the source image in the facial feature points of the target image. Region correspondence is determined between regions of the source image and regions of the target image using the facial feature point correspondence. The healing region of the face in the source image is transformed to a corresponding region of the face in the target image using the region correspondence.
    Type: Grant
    Filed: November 28, 2018
    Date of Patent: April 13, 2021
    Assignee: ADOBE INC.
    Inventors: Subham Gupta, Nitish Singla
  • Patent number: 10977691
    Abstract: Systems and methods are disclosed for recommending shared electronic content via an online service. In some embodiments, a server can identify a first subscriber and a second subscriber to an online service that have access via the online service to an application for using or editing electronic content. The server can also determine a correspondence between usages of the application by the first and second subscribers via the online service with respect to at least one attribute of the application. The server can also identify an electronic content item generated with the application by the first subscriber. The server can also provide, via the online service, a recommendation for the electronic content item to the second subscriber based on the correspondence between the first usage and the second usage with respect to one or more attributes of the application.
    Type: Grant
    Filed: June 30, 2014
    Date of Patent: April 13, 2021
    Assignee: Adobe Inc.
    Inventors: Ajay Jain, Mansukh Patidar
  • Patent number: 10979640
    Abstract: The present disclosure is directed toward systems and methods for predicting lighting conditions. In particular, the systems and methods described herein analyze a single low-dynamic range digital image to estimate a set of high-dynamic range lighting conditions associated with the single low-dynamic range lighting digital image. Additionally, the systems and methods described herein train a convolutional neural network to extrapolate lighting conditions from a digital image. The systems and methods also augment low-dynamic range information from the single low-dynamic range digital image by using a sky model algorithm to predict high-dynamic range lighting conditions.
    Type: Grant
    Filed: February 12, 2020
    Date of Patent: April 13, 2021
    Assignee: ADOBE INC.
    Inventors: Yannick Hold-Geoffroy, Sunil S. Hadap, Kalyan Krishna Sunkavalli, Emiliano Gambaretto
  • Patent number: 10977844
    Abstract: Methods and systems are provided for presenting and using multiple masks based on a segmented image in editing the image. In particular, multiple masks can be presented to a user using a graphical user interface for easy selection and utilization in the editing of an image. The graphical user interface can include a display configured to display an image, a mask zone configured to display segmentations of the image using masks, and an edit zone configured to display edits to the image. Upon receiving segmentation for the image, the masks can be displayed in the mask zone where the masks are based on a selected segmentation detail level.
    Type: Grant
    Filed: November 29, 2017
    Date of Patent: April 13, 2021
    Assignee: Adobe Inc.
    Inventors: Sarah Aye Kong, I-Ming Pao, Hyunghwan Byun
  • Publication number: 20210104085
    Abstract: In implementations of jointly editing related objects in a digital image, an image editing application segments a first object in a digital image, and an additional object corresponding to the first object, such a shadow cast by the first object, a reflection of the first object, or an object of a same object class as the first object. Respective stick diagrams for the first object and the additional object are generated, and a mapping of the first object to the additional object is generated based on the stick diagrams. Based on a user request to edit the first object, such as to warp the first object, the first object and the additional object are jointly edited based on the mapping. Accordingly, realistic digital images are efficiently generated that maintain correspondence between related objects, without requiring a user to edit each object individually, thus saving time and resources.
    Type: Application
    Filed: December 17, 2020
    Publication date: April 8, 2021
    Applicant: Adobe Inc.
    Inventors: Sanjeev Tagra, Sachin Soni, Prasenjit Mondal, Ajay Jain
  • Publication number: 20210103940
    Abstract: Data-driven operating model (DDOM) systems and techniques are described to manage implementation, access, and promotion of digital services by a service provider system. In one example, the DDOM system includes a data aggregation module, a journey manager module and a segment manager module. The data aggregation module supports a unified data architecture that is then leverage by the journey and segment manager modules to support matrixed journey stage and segmentation of a data lake to provide insights that are not possible by a human being alone, that are usable to manage implementation, access, and promotion of digital services by a service provider system.
    Type: Application
    Filed: November 18, 2019
    Publication date: April 8, 2021
    Applicant: Adobe Inc.
    Inventors: Robert Keith Giglio, Mark Andrew Picone, Maninder Singh Sawhney, Eric L. Cox, Ashley Elizabeth Wells, Nicholas James Woo, Vineet Bhalla, Brandon John Tatton, Amit Sethi, Simmi Kochhar Bhargava, Ryan John Stansfield, Sharad Narang, Samarpan Das, Krishna Kishore Veturi, Jagadeswarareddi Vaka, Brian Daniel Block, Purnaram Kodavatiganti, Thomason Nguyen, Dhrumil Bharat Joshi, Amarendra Reddy Duvvuru, Ashfaq Mohiuddin, Sumesh Kumar
  • Patent number: 10970889
    Abstract: Embodiments provide systems, methods, and computer storage media for generating stroke predictions based on prior strokes and a reference image. An interactive drawing interface can allow a user to sketch over, or with respect to, a reference image. A UI tool such as an autocomplete or workflow clone tool can access or identify a set of prior strokes and a target region, and stroke predictions can be generated using an iterative algorithm that minimizes an energy function considering stroke-to-stroke and image-patch-to-image-patch comparisons. For any particular future stroke, one or more stroke predictions may be initialized based on the set of prior strokes. Each initialized prediction can be improved by iteratively executing search and assignment steps to incrementally improve the prediction, and the best prediction can be selected and presented as a stroke prediction for the future stroke. The process can be repeated to predict any number of future strokes.
    Type: Grant
    Filed: March 28, 2019
    Date of Patent: April 6, 2021
    Assignee: Adobe Inc.
    Inventors: Yilan Chen, Li-Yi Wei
  • Patent number: 10970765
    Abstract: The present disclosure relates to a personalized fashion generation system that synthesizes user-customized images using deep learning techniques based on visually-aware user preferences. In particular, the personalized fashion generation system employs an image generative adversarial neural network and a personalized preference network to synthesize new fashion items that are individually customized for a user. Additionally, the personalized fashion generation system can modify existing fashion items to tailor the fashion items to a user's tastes and preferences.
    Type: Grant
    Filed: February 15, 2018
    Date of Patent: April 6, 2021
    Assignees: ADOBE INC., THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
    Inventors: Chen Fang, Zhaowen Wang, Wangcheng Kang, Julian McAuley
  • Patent number: 10972332
    Abstract: The present disclosure is directed toward systems and methods for identifying contributing factors associated with a metric anomaly. One or more embodiments described herein identify contributing factors based on statistical analysis and machine learning. Additionally, one or more embodiments identify sub-factors associated with each contributing factor. In one or more embodiments, the systems and methods provide an interactive display that enables a user to select a particular anomaly for further analysis. The interactive display also provides additional interfaces through which the user can view informational displays that illustrate the factors that caused the particular anomaly and how those factors correlate with each other.
    Type: Grant
    Filed: August 31, 2015
    Date of Patent: April 6, 2021
    Assignee: ADOBE INC.
    Inventors: John Bates, James Meyer, William Brandon George
  • Patent number: 10972511
    Abstract: Digital signage techniques are disclosed that utilize streaming technology to deliver digital signage content to digital signage display devices. In some examples, a method may include rendering a digital signage content frame by frame, capturing an image of each rendered frame, transforming the captured image of each rendered frame into a video frame of a video stream, and delivering the video stream to at least one remote display device. The captured image may be an image of a portion of the rendered frame. The display devices that receive the video stream may render the video stream using a streaming media player.
    Type: Grant
    Filed: November 7, 2017
    Date of Patent: April 6, 2021
    Assignee: Adobe Inc.
    Inventors: Vitaly Tsaplin, Alexandre Capt
  • Patent number: 10970599
    Abstract: Techniques are disclosed for characterizing and defining the location of a copy space in an image. A methodology implementing the techniques according to an embodiment includes applying a regression convolutional neural network (CNN) to an image. The regression CNN is configured to predict properties of the copy space such as size and type (natural or manufactured). The prediction is conditioned on a determination of the presence of the copy space in the image. The method further includes applying a segmentation CNN to the image. The segmentation CNN is configured to generate one or more pixel-level masks to define the location of copy spaces in the image, whether natural or manufactured, or to define the location of a background region of the image. The segmentation CNN may include a first stage comprising convolutional layers and a second stage comprising pairs of boundary refinement layers and bilinear up-sampling layers.
    Type: Grant
    Filed: November 15, 2018
    Date of Patent: April 6, 2021
    Assignee: ADOBE INC.
    Inventors: Mingyang Ling, Alex Filipkowski, Zhe Lin, Jianming Zhang, Samarth Gulati
  • Patent number: 10970302
    Abstract: The present disclosure relates to a digital asset synchronization system that provides improved local and remote synchronization of digital assets. In particular, the digital asset synchronization system manages digital assets by separating each digital asset into multiple components stored as a set of distributed individual files. Employing individual components for a digital asset rather than single monolithic file enables the digital asset synchronization system to provide safe concurrent access to the digital asset from multiple applications on the same device and across different devices. In addition, using components for a digital asset provides the digital asset synchronization system with the ability to efficiently store and synchronize multiple versions of the digital asset, both locally and remotely.
    Type: Grant
    Filed: June 22, 2017
    Date of Patent: April 6, 2021
    Assignee: ADOBE INC.
    Inventors: Stanley J. Switzer, Roey Horns, Oliver I. Goldman, Julian R. Wixson
  • Patent number: 10970847
    Abstract: Techniques are disclosed for document boundary detection (BD) from an input image using a combination of deep learning model and image processing algorithms. Quadrilaterals approximating the document boundaries in the input image are determined and rated separately using both these approaches: deep leaning using convolutional neural network (CNN) and heuristics using image processing algorithms. Thereafter, the best rated quadrilateral is selected from the quadrilaterals obtained from both the approaches.
    Type: Grant
    Filed: May 16, 2019
    Date of Patent: April 6, 2021
    Assignee: Adobe Inc.
    Inventors: Prasenjit Mondal, Anuj Shara, Ankit Bal, Deepanshu Arora, Siddharth Kumar
  • Patent number: 10970338
    Abstract: The present disclosure relates to performing attribution channel modeling in real time using touchpoint data that corresponds to a user-specified set of channels and is retrieved from a database using a user-specified attribution model. For example, in one or more embodiments, a system stores raw data in an attribution database that comprises an aggregator and a plurality of nodes. In particular, each node stores touchpoint data associated with a different user. Upon receiving a query, the system can, in real time, retrieve subsets of the touchpoint data that corresponds to a user-defined set of distribution channels in accordance with a user-specified attribution model. The system then combines the subsets of touchpoint data using the aggregator and generates the digital attribution report using the combined data.
    Type: Grant
    Filed: November 13, 2018
    Date of Patent: April 6, 2021
    Assignee: ADOBE INC.
    Inventors: Trevor Paulsen, Ivan Andrus, Vladislav Turchenko, Dirk DeHart, David Wilcox, Brian Jarvis
  • Patent number: 10970289
    Abstract: Certain embodiments involve ranking search results from an information retrieval system using user query data to provide relevant search results to users of the information retrieval system. For example, a system determines a weight factor associated with a first user that provides a query to the information retrieval system based on a type or role of the first user. The system further determines a boost factor associated with the first user based on the weight factor and a number of consecutive search queries provided by the user. The system uses the boost factor to automatically tune a ranking algorithm to adjust a rank of a search result item resulting from a search query provided by a second user.
    Type: Grant
    Filed: May 20, 2016
    Date of Patent: April 6, 2021
    Assignee: ADOBE INC.
    Inventors: Tommaso Teofili, Michael Marth