公开(公告)号：US12223002B2

公开(公告)日：2025-02-11

申请号：US17454445

申请日：2021-11-10

Applicant: ADOBE INC.

Inventor： Pinkesh Badjatiya ,  Tanay Anand ,  Simra Shahid ,  Nikaash Puri ,  Milan Aggarwal ,  S Sejal Naidu ,  Sharat Chandra Racha

IPC: G06F16/9536 ,  G06F16/9538 ,  G06F40/20

Abstract: A method of finding online relevant conversing posts, comprises receiving, by a web server serving an online forum, a query post from an inquirer using the online forum, computing a contextual similarity score between each conversing post of a set of conversing posts with a query post, wherein the contextual similarity score is computed between the body of each of conversing posts and of the query post, wherein N1 conversing posts with a highest contextual similarity score are selected; computing a fine grained similarity score between the subject of the query post and of each of the N1 conversing posts, wherein N2 conversing posts with a highest fine grained similarity score are selected; and boosting the fine grained similarity score of the N2 conversing posts based on relevance metrics, wherein N3 highest ranked conversing posts are selected as a list of conversing posts most relevant to the query post.

公开(公告)号：US12111884B2

公开(公告)日：2024-10-08

申请号：US17659983

申请日：2022-04-20

Applicant: ADOBE INC.

Inventor： Tanay Anand ,  Pinkesh Badjatiya ,  Sriyash Poddar ,  Jayakumar Subramanian ,  Georgios Theocharous ,  Balaji Krishnamurthy

IPC: G06F18/2137 ,  G06N3/088

CPC classification number: G06F18/2137 ,  G06N3/088

Abstract: Systems and methods for machine learning are described. Embodiments of the present disclosure receive state information that describes a state of a decision making agent in an environment; compute an action vector from an action embedding space based on the state information using a policy neural network of the decision making agent, wherein the policy neural network is trained using reinforcement learning based on a topology loss that constrains changes in a mapping between an action set and the action embedding space; and perform an action that modifies the state of the decision making agent in the environment based on the action vector, wherein the action is selected based on the mapping.

公开(公告)号：US20240005146A1

公开(公告)日：2024-01-04

申请号：US17855085

申请日：2022-06-30

Applicant: Adobe Inc. ,  Delhi Technological University

Inventor： Tanay Anand ,  Piyush Gupta ,  Pinkesh Badjatiya ,  Nikaash Puri ,  Jayakumar Subramanian ,  Balaji Krishnamurthy ,  Chirag Singla ,  Rachit Bansal ,  Anil Singh Parihar

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0445

Abstract: In some embodiments, techniques for extracting high-value sequential patterns are provided. For example, a process may involve training a machine learning model to learn a state-action map that contains high-utility sequential patterns; extracting at least one high-utility sequential pattern from the trained machine learning model; and causing a user interface of a computing environment to be modified based on information from the at least one high-utility sequential pattern.

公开(公告)号：US20230342425A1

公开(公告)日：2023-10-26

申请号：US17659983

申请日：2022-04-20

Applicant: ADOBE INC.

Inventor： Tanay Anand ,  Pinkesh Badjatiya ,  Sriyash Poddar ,  Jayakumar Subramanian ,  Georgios Theocharous ,  Balaji Krishnamurthy

IPC: G06K9/62 ,  G06N3/08

CPC classification number: G06K9/6251 ,  G06N3/088

Abstract: Systems and methods for machine learning are described. Embodiments of the present disclosure receive state information that describes a state of a decision making agent in an environment; compute an action vector from an action embedding space based on the state information using a policy neural network of the decision making agent, wherein the policy neural network is trained using reinforcement learning based on a topology loss that constrains changes in a mapping between an action set and the action embedding space; and perform an action that modifies the state of the decision making agent in the environment based on the action vector, wherein the action is selected based on the mapping.

公开(公告)号：US20230169271A1

公开(公告)日：2023-06-01

申请号：US17644856

申请日：2021-12-17

Applicant: ADOBE INC.

Inventor： Shashank Shailabh ,  Madhur Panwar ,  Milan Aggarwal ,  Pinkesh Badjatiya ,  Simra Shahid ,  Nikaash Puri ,  S Sejal Naidu ,  Sharat Chandra Racha ,  Balaji Krishnamurthy ,  Ganesh Karbhari Palwe

IPC: G06F40/289 ,  G06F40/40 ,  G06F40/30

CPC classification number: G06F40/289 ,  G06F40/40 ,  G06F40/30

Abstract: Systems and methods for topic modeling are described. The systems and methods include encoding words of a document using an embedding matrix to obtain word embeddings for the document. The words of the document comprise a subset of words in a vocabulary, and the embedding matrix is trained as part of a topic attention network based on a plurality of topics. The systems and methods further include encoding a topic-word distribution matrix using the embedding matrix to obtain a topic embedding matrix. The topic-word distribution matrix represents relationships between the plurality of topics and the words of the vocabulary. The systems and methods further include computing a topic context matrix based on the topic embedding matrix and the word embeddings and identifying a topic for the document based on the topic context matrix.

公开(公告)号：US20230154232A1

公开(公告)日：2023-05-18

申请号：US17454645

申请日：2021-11-12

Applicant: ADOBE INC.

Inventor： Pinkesh Badjatiya ,  Parth Patel

IPC: G06K9/00 ,  G06T11/60 ,  G06F3/0484

CPC classification number: G06K9/00228 ,  G06F3/04847 ,  G06K9/00268 ,  G06T11/60 ,  G06N3/02 ,  G06T2200/24

Abstract: Systems and methods for image processing are described. One or more embodiments of the method, apparatus, non-transitory computer readable medium, and system include identifying an encoding of an image, an attribute to be modified in the image, and a plurality of attributes to be preserved in the image; generating a non-linear interpolation for the encoding by iteratively identifying a sequence of boundary vectors, wherein each boundary vector of the sequence of boundary vectors is based on selecting a plurality of conditional boundary vectors representing a subset of the plurality of attributes to be preserved at each corresponding iteration; and generating a modified image based on the image encoding and the non-linear interpolation, wherein the modified image corresponds to the image with the attribute to be modified.

公开(公告)号：US20230154186A1

公开(公告)日：2023-05-18

申请号：US17455126

申请日：2021-11-16

Applicant: ADOBE INC.

Inventor： Sumegh Roychowdhury ,  Sumedh A. Sontakke ,  Mausoom Sarkar ,  Nikaash Puri ,  Pinkesh Badjatiya ,  Milan Aggarwal

IPC: G06K9/00 ,  G06N3/08

CPC classification number: G06K9/00718 ,  G06K9/00751 ,  G06N3/088 ,  G06K2009/00738

Abstract: Systems and methods for video processing are described. Embodiments of the present disclosure generate a plurality of image feature vectors corresponding to a plurality of frames of a video; generate a plurality of low-level event representation vectors based on the plurality of image feature vectors, wherein a number of the low-level event representation vectors is less than a number of the image feature vectors; generate a plurality of high-level event representation vectors based on the plurality of low-level event representation vectors, wherein a number of the high-level event representation vectors is less than the number of the low-level event representation vectors; and identify a plurality of high-level events occurring in the video based on the plurality of high-level event representation vectors.

公开(公告)号：US20220237406A1

公开(公告)日：2022-07-28

申请号：US17160862

申请日：2021-01-28

Applicant: Adobe Inc.

Inventor： Pinkesh Badjatiya ,  Surgan Jandial ,  Pranit Chawla ,  Mausoom Sarkar ,  Ayush Chopra

IPC: G06K9/62 ,  G06N3/04 ,  G06F16/532 ,  G06F16/535 ,  G06F16/538

Abstract: Techniques are disclosed for text conditioned image searching. A methodology implementing the techniques according to an embodiment includes receiving a source image and a text query defining a target image attribute. The method also includes decomposing the source image into image content and style feature vectors and decomposing the text query into text content and style feature vectors, wherein image style is descriptive of image content and text style is descriptive of text content. The method further includes composing a global content feature vector based on the text content feature vector and the image content feature vector and composing a global style feature vector based on the text style feature vector and the image style feature vector. The method further includes identifying a target image that relates to the global content feature vector and the global style feature vector so that the target image relates to the target image attribute.