Patents Assigned to Adobe Inc.
  • Publication number: 20220147708
    Abstract: A dataset captioning system is described that generates captions of text to describe insights identified from a dataset, automatically and without user intervention. To do so, given an input of a dataset the dataset captioning system determines which data insights are likely to support potential visualizations of the dataset, generates text based on these insights, orders the text, processes the ordered text for readability, and then outputs the text as a caption. These techniques also include adjustments made to the complexity of the text, globalization of the text, inclusion of links to outside sources of information, translation of the text, and so on as part of generating the caption.
    Type: Application
    Filed: November 10, 2020
    Publication date: May 12, 2022
    Applicant: Adobe Inc.
    Inventors: Eunyee Koh, Xin Qian, Tak Yeon Lee, Sana Malik Lee, Ryan Anthony Rossi, Fan Du, Duy-Trung Trong Dinh
  • Publication number: 20220148015
    Abstract: Techniques are provided for analyzing user actions that have occurred over a time period. The user actions can be, for example, with respect to the user's navigation of content or interaction with an application. Such user data is provided in an action string, which is converted into a highly searchable format. As such, the presence and frequency of particular user actions and patterns of user actions within an action string of a particular user, as well as among multiple action strings of multiple users, are determinable. Subsequences of one or more action strings are identified and both the number of action strings that include a particular subsequence and the frequency that a particular subsequence is present in a given action string are determinable. The conversion involves breaking that string into a sorted list of locations for the actions within that string. Queries can be readily applied against the sorted list.
    Type: Application
    Filed: November 12, 2020
    Publication date: May 12, 2022
    Applicant: Adobe Inc.
    Inventors: Tung Mai, Iftikhar Ahamath Burhanuddin, Georgios Theocharous, Anup Rao
  • Publication number: 20220147713
    Abstract: A system for generating text using a trained language model comprises an encoder that includes a debiased language model that penalizes generated text based on an equalization loss that quantifies first and second probabilities of respective first and second tokens occurring at a first point in the generated text. The first and second tokens define respective first and second groups of people. The system further comprises a decoder configured to generate text using the debiased language model. The decoder is further configured to penalize the generated text based on a bias penalization loss that quantifies respective probabilities of the first and second tokens co-occurring with a generated word. The encoder and decoder are trained to produce the generated text using a task-specific training corpus.
    Type: Application
    Filed: November 7, 2020
    Publication date: May 12, 2022
    Applicant: Adobe Inc.
    Inventors: Aparna Garimella, Kiran Kumar Rathlavath, Balaji Vasan Srinivasan, Anandhavelu Natarajan, Akhash Nakkonda Amarnath, Akash Pramod Yalla
  • Publication number: 20220150123
    Abstract: Deriving network embeddings that represent attributes of, and relationships between, different nodes in a network while preserving network data temporal and structural properties is described. A network representation system generates a plurality of graph time-series representations of network data that each includes a subset of nodes and edges included in a time segment of the network data, constrained either by time or a number of edges included in the representation. A temporal graph of the network data is generated by implementing a temporal model that incorporates temporal dependencies into the graph time-series representations. From the temporal graph, network embeddings for the network data are derived, where the network embeddings capture temporal dependencies between nodes, as indicated by connecting edges, as well as temporal structural properties of the network data.
    Type: Application
    Filed: November 11, 2020
    Publication date: May 12, 2022
    Applicant: Adobe Inc.
    Inventors: Sungchul Kim, Di Jin, Ryan A. Rossi, Eunyee Koh
  • Publication number: 20220148135
    Abstract: A plurality of pixel-based sampling points are identified within an image, wherein sampling points of a pixel are distributed within the pixel. For individual sampling points of individual pixels, a corresponding radiance vector is estimated. A radiance vector includes one or more radiance values characterizing light received at a sampling point. A first machine learning module generates, for each pixel, a corresponding intermediate radiance feature vector, based on the radiance vectors associated with the sampling points within that pixel. A second machine learning module generates, for each pixel, a corresponding final radiance feature vector, based on an intermediate radiance feature vector for that pixel, and one or more other intermediate radiance feature vectors for one or more other pixels neighboring that pixel. One or more kernels are generated, based on the final radiance feature vectors, and applied to corresponding pixels of the image, to generate a lower noise image.
    Type: Application
    Filed: November 10, 2020
    Publication date: May 12, 2022
    Applicant: Adobe Inc.
    Inventors: Mustafa Isik, Michael Yanis Gharbi, Matthew David Fisher, Krishna Bhargava Mullia Lakshminarayana, Jonathan Eisenmann, Federico Perazzi
  • Publication number: 20220148243
    Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.
    Type: Application
    Filed: November 10, 2020
    Publication date: May 12, 2022
    Applicant: Adobe Inc.
    Inventors: Yang Yang, Zhixin Shu, Shabnam Ghadar, Jingwan Lu, Jakub Fiser, Elya Schechtman, Cameron Y. Smith, Baldo Antonio Faieta, Alex Charles Filipkowski
  • Publication number: 20220148267
    Abstract: In implementations of systems for augmented reality sketching, a computing device implements a sketch system to generate three-dimensional scene data describing a three-dimensional representation of a physical environment including a physical object. The sketch system displays a digital video in a user interface that depicts the physical environment and the physical object and the sketch system tracks movements of the physical object depicted in the digital video using two-dimensional coordinates of the user interface. These two-dimensional coordinates are projected into the three-dimensional representation of the physical environment. The sketch system receives a user input connecting a portion of a graphical element in the user interface to the physical object depicted in the digital video. The sketch system displays the portion of the graphical element as moving in the user interface corresponding to the movements of the physical object depicted in the digital video.
    Type: Application
    Filed: October 26, 2021
    Publication date: May 12, 2022
    Applicant: Adobe Inc.
    Inventors: Kazi Rubaiat Habib, Stephen Joseph DiVerdi, Ryo Suzuki, Li-Yi Wei, Wilmot Wei-Mau Li
  • Publication number: 20220148326
    Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.
    Type: Application
    Filed: January 24, 2022
    Publication date: May 12, 2022
    Applicant: Adobe Inc.
    Inventors: Christopher Alan Tensmeyer, Rajiv Jain, Curtis Michael Wigington, Brian Lynn Price, Brian Lafayette Davis
  • Patent number: 11328002
    Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods for utilizing hash partitions to determine local densities and distances among users (or among other represented data points) for clustering sparse data into segments. For instance, the disclosed systems can generate hash signatures for users in a sparse dataset and can map users to hash partitions based on the hash signatures. The disclosed systems can further determine local densities and separation distances for particular users (or other represented data points) within the hash partitions. Upon determining local densities and separation distances for datapoints from the dataset, the disclosed systems can select a segment (or cluster of data points) grouped according to a hierarchy of a clustering algorithm, such as a density-peaks-clustering algorithm.
    Type: Grant
    Filed: April 17, 2020
    Date of Patent: May 10, 2022
    Assignee: Adobe Inc.
    Inventors: Fan Du, Yeuk-Yin Chan, Eunyee Koh, Ryan Rossi, Margarita Savova, Charles Menguy, Anup Rao
  • Patent number: 11328458
    Abstract: In some embodiments, a computing system generates a color gradient for data visualizations by displaying a color selection design interface. The computing system receives a user input identifying a start point of a color map path and an end point of a color map path. The computing system computes a color map path between the start point and the end point constrained to traverse colors having uniform transitions between one or more of lightness, chroma, and hue. The computing system selects a color gradient having a first color corresponding to the start point of the color map path and a second color corresponding to the end point of the color map path, and additional colors corresponding to additional points along the color map path. The computing system generates a color map for visually representing a range of data values.
    Type: Grant
    Filed: January 15, 2021
    Date of Patent: May 10, 2022
    Assignee: Adobe Inc.
    Inventors: Jose Ignacio Echevarria Vallespi, Stephen DiVerdi, Hema Susmita Padala, Bernard Kerr, Dmitry Baranovskiy
  • Patent number: 11327710
    Abstract: A computer-implemented method for audio signal processing includes analyzing a foreground audio signal to determine metrics corresponding to audio slices of the foreground audio signal. Each such metric indicates a value for an audio property of a respective audio slice. The method further includes computing a total metric for an audio slice as a function of a set of the metrics corresponding to a set of the audio slices including the audio slice. The method further includes adding a key frame to a track based on the total metric. The track includes the foreground audio signal and a background audio signal, and a location of the key frame corresponds to a location of the audio slice on the track. The key frame indicates a change to the audio property of the background audio signal at the location on the track, and the key frame is utilizable for audio ducking.
    Type: Grant
    Filed: March 27, 2020
    Date of Patent: May 10, 2022
    Assignee: Adobe Inc.
    Inventors: Nico Becherer, Sven Duwenhorst
  • Patent number: 11328523
    Abstract: The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.
    Type: Grant
    Filed: June 9, 2020
    Date of Patent: May 10, 2022
    Assignee: Adobe Inc.
    Inventors: Elya Shechtman, Oliver Wang, Mehmet Yumer, Chen-Hsuan Lin
  • Patent number: 11328385
    Abstract: Techniques and systems are provided for configuring neural networks to perform warping of an object represented in an image to create a caricature of the object. For instance, in response to obtaining an image of an object, a warped image generator generates a warping field using the image as input. The warping field is generated using a model trained with pairings of training images and known warped images using supervised learning techniques and one or more losses. The warped image generator determines, based on the warping field, a set of displacements associated with pixels of the input image. These displacements indicate pixel displacement directions for the pixels of the input image. These displacements are applied to the digital image to generate a warped image of the object.
    Type: Grant
    Filed: April 14, 2020
    Date of Patent: May 10, 2022
    Assignee: Adobe Inc.
    Inventors: Julia Gong, Yannick Hold-Geoffroy, Jingwan Lu
  • Publication number: 20220138557
    Abstract: In implementations of deep hybrid graph-based forecasting systems, a computing device implements a forecast system to receive time-series data describing historic computing metric values for a plurality of processing devices. The forecast system determines dependency relationships between processing devices of the plurality of processing devices based on time-series data of the processing devices. Time-series data of each processing device is represented as a node of a graph and the nodes are connected based on the dependency relationships. The forecast system generates an indication of a future computing metric value for a particular processing device by processing a first set of the time-series data using a relational global model and processing a second set of the time-series data using a relational local model. The first and second sets of the time-series data are determined based on a structure of the graph.
    Type: Application
    Filed: November 4, 2020
    Publication date: May 5, 2022
    Applicant: Adobe Inc.
    Inventors: Ryan A. Rossi, Hongjie Chen, Kanak Vivek Mahadik, Sungchul Kim
  • Publication number: 20220139009
    Abstract: Curve antialiasing based on curve-pixel intersection is leveraged in a digital medium environment. For instance, to apply antialiasing according to techniques described herein, curves of a visual object are mapped from an original pixel space to a virtual pixel space. Virtual pixels of the virtual pixel space that are intersected by the mapped curves are identified and aggregated as intersected virtual pixels. The intersected virtual pixels are then mapped back into the original pixel space to identify which intersected virtual pixels positionally coincide with respective original pixels of the original pixel space. Intersected virtual pixels are mapped to original pixels to generate pixel coverage for original pixels. The generated pixel coverage values for original pixels are applied to render antialiased curves as part of an antialiased version of the original visual object.
    Type: Application
    Filed: January 10, 2022
    Publication date: May 5, 2022
    Applicant: Adobe Inc.
    Inventors: Harish Kumar, Anmol Sud
  • Publication number: 20220138781
    Abstract: Quantitative rating systems and techniques are described that prioritize customers by propensity to buy and buy size to generate customer ratings. In one example, a propensity model is used to determine a likelihood of a potential customer to purchase a product, and a projected timeframe buy size for the potential customer is determined. An expected value for the potential customer is generated by combining the likelihood of the potential customer to purchase the product and the projected timeframe buy size. In another example, a ratio model of annualized recurring revenue (ARR) is used to determine a timeframe buy size for an existing customer in consecutive time frames. An upsell opportunity for the existing customer is determined based on the timeframe buy size less an ARR for a current time frame for the existing customer. A rating of the potential or existing customer is output in a user interface.
    Type: Application
    Filed: January 18, 2022
    Publication date: May 5, 2022
    Applicant: Adobe Inc.
    Inventors: Jin Xu, Zhenyu Yan, Wenqing Yang, Tianyu Wang, Abhishek Pani
  • Patent number: 11321373
    Abstract: This disclosure covers methods, non-transitory computer readable media, and systems that use an intelligent analytics interface to process natural-language and other inputs to configure an analytics task for the system. The disclosed methods, non-transitory computer readable media, and systems provide the intelligent analytics interface to facilitate an exchange between the systems and a user to determine values for the analytics task. The methods, non-transitory computer readable media, and systems then use these values to execute an analytics task.
    Type: Grant
    Filed: November 27, 2019
    Date of Patent: May 3, 2022
    Assignee: Adobe Inc.
    Inventors: Prakhar Gupta, Iftikhar Ahamath Burhanuddin, Harvineet Singh, Atanu Ranjan Sinha
  • Patent number: 11321895
    Abstract: Digital character animation automated generation techniques are described that are implemented by an animation generation system via a computing device. These techniques enable the animation generation system to generate an animation of a digital character automatically and without user intervention responsive to a user input of a target action such that the digital character is capable of performing a complex set of actions in a precise and realistic manner within an environment contained within digital content, e.g., an animation as part of a digital video.
    Type: Grant
    Filed: May 29, 2020
    Date of Patent: May 3, 2022
    Assignee: Adobe Inc.
    Inventors: Wolfram Sebastian Starke, Jun Saito
  • Patent number: 11321889
    Abstract: A multi-layer light source includes an emissive layer and a textured lighting gel layer, the lighting gel layer being situated between the emissive layer and a 2D canvas or a 3D object. User inputs controlling the multi-layer light source are received, these user inputs being provided with the user interacting with the 2D canvas without switching to editing in 3D space. The multi-layer light source is configured based on the user inputs and, based on the configuration, emission of light rays from the multi-layer light source is determined. Areas of shadows cast by 3D objects are also determined. An image generation system determines, a color of a location (e.g., a pixel) on the 2D canvas or the 3D object that a light ray intersects based on the color that is in the lighting gel layer that the light ray passes through.
    Type: Grant
    Filed: October 28, 2020
    Date of Patent: May 3, 2022
    Assignee: Adobe Inc.
    Inventors: Xin Sun, Vineet Batra, Sumit Dhingra, Nathan Aaron Carr, Ankit Phogat
  • Patent number: 11321012
    Abstract: The present disclosure relates to a digital asset conflict resolution system that provides conflict resolution of composite-part-based synchronized digital assets. In particular, the digital asset conflict resolution system detects conflicts within composite-part-based digital assets and resolves the conflicts at a composite-part level (i.e., composite-part level) within the digital asset based on format-specific rules. In various embodiments, the digital asset conflict resolution system utilizes format-specific rules and rule sets to automatically resolve conflicts at the composite-part level within a digital asset without duplicating the digital asset and without requiring immediate user involvement.
    Type: Grant
    Filed: March 4, 2019
    Date of Patent: May 3, 2022
    Assignee: Adobe Inc.
    Inventors: Roey Horns, Oliver I. Goldman