-
公开(公告)号：US20240073159A1
公开(公告)日：2024-02-29
申请号：US17897419
申请日：2022-08-29
Applicant: ADOBE INC.
Inventor： Sumit BHATIA , Jivat Neet KAUR , Rachit BANSAL , Milan AGGARWAL , Balaji KRISHNAMURTHY
IPC: H04L51/02 , G06F40/295 , G06N5/02
CPC classification number: H04L51/02 , G06F40/295 , G06N5/022
Abstract: The technology described herein receives a natural-language sequence of words comprising multiple entities. The technology then identifies a plurality of entities in the natural-language sequence. The technology generates a masked natural-language sequence by masking a first entity in the natural-language sequence. The technology retrieves, from a knowledge base, information related to a second entity in the plurality of entities. The technology then trains a natural-language model to respond to a query. The training uses a first representation of the masked natural-language sequence, a second representation of the information, and the first entity.
-
公开(公告)号：US20210042625A1
公开(公告)日：2021-02-11
申请号：US16534856
申请日：2019-08-07
Applicant: ADOBE INC.
Inventor： Ayush CHOPRA , Abhishek SINHA , Hiresh GUPTA , Mausoom SARKAR , Kumar AYUSH , Balaji KRISHNAMURTHY
Abstract: Methods and systems are provided for facilitating the creation and utilization of a transformation function system capable of providing network agnostic performance improvement. The transformation function system receives a representation from a task neural network. The representation can be input into a composite function neural network of the transformation function system. A learned composite function can be generated using the composite function neural network. The composite function can be specifically constructed for the task neural network based on the input representation. The learned composite function can be applied to a feature embedding of the task neural network to transform the feature embedding. Transforming the feature embedding can optimize the output of the task neural network.
-
公开(公告)号：US20250148192A1
公开(公告)日：2025-05-08
申请号：US18501745
申请日：2023-11-03
Applicant: Adobe Inc.
Inventor： Simra SHAHID , Nikitha SRIKANTH , Surgan JANDAIL , Balaji KRISHNAMURTHY
IPC: G06F40/166 , G06F16/9538 , G06F40/194
Abstract: Methods, computer systems, computer-storage media, and graphical user interfaces are provided for efficiently generating alternative examples for content. In embodiments, a source example prompt is obtained at a large language model. The source example prompt includes text associated with a source content and an instruction to generate a source example from the text associated with the source content. Using the large language model, the source example that represents an entity and corresponding context from the text is generated. Thereafter, the source example and a set of user segments are provided as input into the large language model to generate alternative examples associated with the source content. Each alternative example corresponds to a user segment of the set of user segments. Based on a particular user segment associated with a user interested in the source content, an alternative example corresponding to the particular user segment is provided for display.
-
公开(公告)号：US20250054164A1
公开(公告)日：2025-02-13
申请号：US18232131
申请日：2023-08-09
Applicant: Adobe Inc.
Inventor： Silky SINGH , Shirpad DESHMUKH , Rishabh JAIN , Mayur HEMANI , Mausoom SARKAR , Balaji KRISHNAMURTHY
Abstract: Various disclosed embodiments are directed to learning-free video object segmentation (VOS) of one or more video frames. In various instances, such VOS does not rely on human supervision or labeling and can be generalized or applied to any video “in the wild.” This is because training and fine-tuning are not required for VOS. Particular embodiments perform VOS based on feature similarity of different sections of a video frame and/or estimated motion similarity of different sections of the video frame, such as via a graph cut on a graph.
-
公开(公告)号：US20240386315A1
公开(公告)日：2024-11-21
申请号：US18318524
申请日：2023-05-16
Applicant: ADOBE INC.
Inventor： Thomas BOUCHER , Tanay ANAND , Stephane LECERCLE , Saurabh GARG , Pranjal PRASOON , Nikaash PURI , Mukul LAMBA , Milan AGGARWAL , Jayakumar SUBRAMANIAN , Francoise CORVAISIER , David MENDEZ ACUNA , Camel AISSANI , Balaji KRISHNAMURTHY
Abstract: Methods and systems are provided for a transformer model for journey simulation and prediction. In embodiments described herein, training data is obtained from stored journeys. The training data for each journey indicates customer interactions with each event in the sequence of events of the journey. A machine learning model is trained using the training data to simulate customer interaction with an input journey. The trained machine learning model then generates a simulation of customer interaction with an input journey and the results of the simulation are displayed.
-
Patent Agency Ranking
公开(公告)号：US20250005048A1
公开(公告)日：2025-01-02
申请号：US18345990
申请日：2023-06-30
Applicant: Adobe Inc.
Inventor： Abhinav JAVA , Surgan JANDIAL , Shripad DESHMUKH , Milan AGGARWAL , Mausoom SARKAR , Balaji KRISHNAMURTHY , Arneh JAIN
IPC: G06F16/332
Abstract: Embodiments are disclosed for one-shot document snippet search. A method of one-shot document snippet search may include obtaining a query snippet and a target document. A multi-modal snippet detection model combines first multi-modal features from the query snippet and second multi-modal features from the target document to create a feature volume. The multi-modal snippet detection model identifies one or more matching snippets from the target document based on the feature volume.
-
公开(公告)号：US20240153258A1
公开(公告)日：2024-05-09
申请号：US17976541
申请日：2022-10-28
Applicant: ADOBE INC.
Inventor： Puneet MANGLA , Milan AGGARWAL , Balaji KRISHNAMURTHY
IPC: G06V10/80 , G06F40/40 , G06V10/764 , G06V10/77 , G06V10/774 , G06V10/82 , G06V10/86
CPC classification number: G06V10/811 , G06F40/40 , G06V10/764 , G06V10/7715 , G06V10/774 , G06V10/82 , G06V10/86
Abstract: Various embodiments classify one or more portions of an image based on deriving an “intrinsic” modality. Such intrinsic modality acts as a substitute to a “text” modality in a multi-modal network. A text modality in image processing is typically a natural language text that describes one or more portions of an image. However, explicit natural language text may not be available across one or more domains for training a multi-modal network. Accordingly, various embodiments described herein generate an intrinsic modality, which is also a description of one or more portions of an image, except that such description is not an explicit natural language description, but rather a machine learning model representation. Some embodiments additionally leverage a visual modality obtained from a vision-only model or branch, which may learn domain characteristics that are not present in the multi-modal network. Some embodiments additionally fuse or integrate the intrinsic modality with the visual modality for better generalization.
-
公开(公告)号：US20210406935A1
公开(公告)日：2021-12-30
申请号：US16910357
申请日：2020-06-24
Applicant: ADOBE INC.
Inventor： Pankhri SINGHAI , Piyush GUPTA , Balaji KRISHNAMURTHY , Jayakumar SUBRAMANIAN , Nikaash PURI
Abstract: Methods and systems are provided for generating and providing insights associated with a journey. In embodiments described herein, journey data associated with a journey is obtained. A journey can include journey paths indicating workflows through which audience members can traverse. The journey data can include audience member attributes (e.g., demographics) and labels indicating journey paths traversed by audience members. A set of audience segments are determined that describe a set of audience members traversing a particular journey path. The set of audience segments can be determined using the journey data to train a segmentation model and, thereafter, analyzing the segmentation model to identify patterns that indicate audience segments associated with the particular journey path. An indication of the set of audience segments that describe the set of audience members traversing the particular journey path can be provided for display.
-
公开(公告)号：US20250124620A1
公开(公告)日：2025-04-17
申请号：US18380059
申请日：2023-10-13
Applicant: Adobe Inc.
Inventor： Tarun ARORA , Tanay ANAND , Siddarth RAMESH , Shripad DESHMUKH , Pranjal PRASOON , Piyush DEWNANI , Md anis ALAM , Jayakumar SUBRAMANIAN , Gaurav SATIJA , Diwakar Reddy YERRAGUNTA , Deepthi AMIRTHAGADESWARAN , Balaji KRISHNAMURTHY , Avinash KATIYAR
Abstract: Various disclosed embodiments are directed to deriving, via a language model, a summary of data by converting or encoding table data into one or more natural language sentences, which are then used as input to the language model for generating the summary. One or more embodiments are additionally or alternatively directed to deriving, via a language model, a response to a user question or command via a chat interface by providing the language model with the generated summary as input. In this way, for example, the language model can use the summary as a prompt or other target context for providing a response.
-
公开(公告)号：US20240086457A1
公开(公告)日：2024-03-14
申请号：US17944502
申请日：2022-09-14
Applicant: ADOBE INC.
Inventor： Yaman KUMAR , Vaibhav AHLAWAT , Ruiyi ZHANG , Milan AGGARWAL , Ganesh Karbhari PALWE , Balaji KRISHNAMURTHY , Varun KHURANA
Abstract: A content analysis system provides content understanding for a content item using an attention aware multi-modal model. Given a content item, feature extractors extract features from content components of the content item in which the content components comprise multiple modalities. A cross-modal attention encoder of the attention aware multi-modal model generates an embedding of the content item using features extracted from the content components. A decoder of the attention aware multi-modal model generates an action-reason statement using the embedding of the content item from the cross-modal attention encoder.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.013 seconds)
