公开(公告)号：US20230085687A1

公开(公告)日：2023-03-23

申请号：US17991249

申请日：2022-11-21

Applicant: ADOBE INC.

Inventor： Ashutosh MEHRA ,  Vlad Ion MORARIU ,  Kajal GUPTA ,  Jayant Vaibhav SRIVASTAVA ,  Curtis Michael WIGINGTON ,  Tushar TIWARI

IPC: G06V30/414 ,  G06N3/02 ,  G06K9/62 ,  G06N20/00

Abstract: Various disclosed embodiments can resolve output inaccuracies produced by many machine learning models. Embodiments use content order as input to machine learning model systems so that they can process documents according to the position or rank of instances in a document or image. In this way, the model is less likely to misclassify or incorrectly detect instances or the ordering between predicted instances. The content order in various embodiments can be used as an additional signal to classify or make predictions.

公开(公告)号：US20250165703A1

公开(公告)日：2025-05-22

申请号：US18511111

申请日：2023-11-16

Applicant: Adobe Inc.

Inventor： Shwetha S ,  Jayant Vaibhav SRIVASTAVA ,  Dinesh AGARWAL ,  Aparna GARIMELLA ,  Anandhavelu N

IPC: G06F40/174 ,  G06F40/109 ,  G06F40/40

Abstract: Embodiments are disclosed for merging misidentified text structures. The method may include receiving a document including a plurality of text elements. The method may further include determining, by a machine learning model, a likelihood of merging a first text element of the plurality of text elements with a second text element of the plurality of text elements based on structure data and context data associated with the first and second text elements. The method may further include determining whether the likelihood of merging the first text element with the second text element satisfies a threshold. The method further includes responsive to determining that the likelihood of merging the first text element with the second text element satisfies the threshold, merging the first text element with the second text element.

公开(公告)号：US20240403543A1

公开(公告)日：2024-12-05

申请号：US18328593

申请日：2023-06-02

Applicant: Adobe Inc.

Inventor： Punit SINGH ,  Jayant Vaibhav SRIVASTAVA ,  Ankit BAL

IPC: G06F40/169 ,  G06F40/197

Abstract: Techniques for document decomposition based on determined logical visual layering of document content. The techniques include iteratively identifying a plurality of logical visual layers of a document resulting in each logical visual layer being associated with one or more document content objects of the document. The one or more document content objects associated with each logical visual layer are annotated to be indicative of the associated logical visual layer. The document is then displayed with an indication of one or more of the annotated document objects.