公开(公告)号：US20220121679A1

公开(公告)日：2022-04-21

申请号：US17076484

申请日：2020-10-21

Applicant: Adobe Inc.

Inventor： Hrituraj SINGH ,  Sumit SHEKHAR

IPC: G06F16/26 ,  G06F40/284 ,  G06K9/00 ,  G06F16/2455 ,  G06F16/242 ,  G06F16/248

Abstract: Embodiments are disclosed for determining an answer to a query associated with a graphical representation of data. In particular, in one or more embodiments, the disclosed systems and methods comprise obtaining a visual embedding for a graphical representation of data, the visual embedding representing a plurality of graphical elements. The one or more embodiment further include obtaining a query embedding for a query associated with the graphical representation of data, the query embedding representing a plurality of textual elements of the query with at least one textual element substituted with an identifier for at least one graphical element of the set of graphical elements. The one or more embodiment further include generating a chart sequence from the visual embedding and a query sequence from the query embedding, generating an output sequence based on the graph and the query sequences, and determining an answer to the query from the output sequence.

公开(公告)号：US20250165517A1

公开(公告)日：2025-05-22

申请号：US18511186

申请日：2023-11-16

Applicant: Adobe Inc.

Inventor： Inderjeet NAIR ,  Sumit SHEKHAR ,  Srikrishna KARANAM ,  Niyati Himanshu CHHAYA ,  Natwar MODANI ,  Balaji Vasan SRINIVASAN ,  Aparna GARIMELLA

IPC: G06F16/34 ,  G06F16/31

Abstract: Embodiments are disclosed for a digital design system trained to segment unstructured text into topically coherent segments. The method may include receiving unstructured text, the unstructured text including a sequence of sentences. The disclosed systems and methods further comprise generating, by a neural network, a hierarchically segmented tree structure representing the unstructured text. The tree structure comprises a plurality of tree structure nodes, where a node of the tree structure nodes represents a sentence from the sequence of sentences. The segments and sub-segments of the unstructured text can then be determined based on node data for nodes of the hierarchically segmented tree structure. Using the determined segments and sub-segments of the unstructured text, a modified representation of the unstructured text can be displayed.

公开(公告)号：US20250053734A1

公开(公告)日：2025-02-13

申请号：US18446765

申请日：2023-08-09

Applicant: Adobe Inc.

Inventor： Inderjeet NAIR ,  Niyati Himanshu CHHAYA ,  Sumit SHEKHAR ,  Mohar KUNDU ,  Lakshya JAGADISH ,  Aravind VELURI ,  Anirudh PHUKAN ,  Akhash AMARNATH

IPC: G06F40/186 ,  G06F40/106 ,  G06V30/14 ,  G06V30/148 ,  G06V30/19 ,  G06V30/414 ,  G06V30/416

Abstract: Embodiments are disclosed for reflowing an infographic image for display in a mobile device using machine learning models. In particular, in one or more embodiments, the method may include receiving a document for display in a user device, the document including an infographic image. The method may further include identifying, using a convolutional neural network, visual components of the infographic image. The method may further include determining, using an encoder-decoder network, an ordered sequence of the identified visual components. A generative adversarial network then generates a modified visual representation of the infographic image based on the identified visual components and the determined ordered sequence of the identified visual components. The modified visual of representation of the infographic image is then presented for display in a viewing pane of a user device in place of the infographic image.