-
公开(公告)号：US11574477B2
公开(公告)日：2023-02-07
申请号：US17194755
申请日：2021-03-08
Applicant: Adobe Inc.
Inventor： Gang Wu , Viswanathan Swaminathan , Uttaran Bhattacharya , Stefano Petrangeli
Abstract: In implementations for highlight video generated with adaptable multimodal customization, a multimodal detection system tracks activities based on poses and faces of persons depicted in video clips of video content. The system determines a pose highlight score and a face highlight score for each of the video clips that depict at least one person, the highlight scores representing a relative level of the interest in an activity depicted in a video clip. The system also determines pose-based emotion features for each of the video clips. The system can detect actions based on the activities of the persons depicted in the video clips, and detect emotions exhibited by the persons depicted in the video clips. The system can receive input selections of actions and emotions, and filter the video clips based on the selected actions and emotions. The system can then generate a highlight video of ranked and filtered video clips.
-
公开(公告)号：US20220284220A1
公开(公告)日：2022-09-08
申请号：US17194755
申请日：2021-03-08
Applicant: Adobe Inc.
Inventor： Gang Wu , Viswanathan Swaminathan , Uttaran Bhattacharya , Stefano Petrangeli
Abstract: In implementations for highlight video generated with adaptable multimodal customization, a multimodal detection system tracks activities based on poses and faces of persons depicted in video clips of video content. The system determines a pose highlight score and a face highlight score for each of the video clips that depict at least one person, the highlight scores representing a relative level of the interest in an activity depicted in a video clip. The system also determines pose-based emotion features for each of the video clips. The system can detect actions based on the activities of the persons depicted in the video clips, and detect emotions exhibited by the persons depicted in the video clips. The system can receive input selections of actions and emotions, and filter the video clips based on the selected actions and emotions. The system can then generate a highlight video of ranked and filtered video clips.
-
公开(公告)号：US20230368265A1
公开(公告)日：2023-11-16
申请号：US17743360
申请日：2022-05-12
Applicant: Adobe Inc.
Inventor： Ryan A. Rossi , Aravind Reddy Talla , Zhao Song , Anup Rao , Tung Mai , Nedim Lipka , Gang Wu , Anup Rao
IPC: G06Q30/06
CPC classification number: G06Q30/0631 , G06Q30/0629 , G06Q30/0643
Abstract: Embodiments provide systems, methods, and computer storage media for a Nonsymmetric Determinantal Point Process (NDPPs) for compatible set recommendations in a setting where data representing entities (e.g., items) arrives in a stream. A stream representing compatible sets of entities is received and used to update a latent representation of the entities and a compatibility distribution indicating likelihood of compatibility of subsets of the entities. The probability distribution is accessed in a single sequential pass to predict a compatible complete set of entities that completes an incomplete set of entities. The predicted complete compatible set is provided a recommendation for entities that complete the incomplete set of entities.
-
公开(公告)号：US11783486B2
公开(公告)日：2023-10-10
申请号：US17553114
申请日：2021-12-16
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Gang Wu , Akshay Malhotra
IPC: G06T7/00 , G06T7/11 , G06T11/60 , G06T7/70 , G06N3/08 , G06V40/10 , G06F18/214 , G06F18/21 , G06V10/774 , G06V10/776 , G06V10/82
CPC classification number: G06T7/11 , G06F18/214 , G06F18/217 , G06N3/08 , G06T7/70 , G06T11/60 , G06V10/774 , G06V10/776 , G06V10/82 , G06V40/10 , G06V40/103 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30168 , G06T2207/30196
Abstract: Generating images and videos depicting a human subject wearing textually defined attire is described. An image generation system receives a two-dimensional reference image depicting a person and a textual description describing target clothing in which the person is to be depicted as wearing. To maintain a personal identity of the person, the image generation system implements a generative model, trained using both discriminator loss and perceptual quality loss, which is configured to generate images from text. In some implementations, the image generation system is configured to train the generative model to output visually realistic images depicting the human subject in the target clothing. The image generation system is further configured to apply the trained generative model to process individual frames of a reference video depicting a person and output frames depicting the person wearing textually described target clothing.
-
公开(公告)号：US20220108509A1
公开(公告)日：2022-04-07
申请号：US17553114
申请日：2021-12-16
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Gang Wu , Akshay Malhotra
Abstract: Generating images and videos depicting a human subject wearing textually defined attire is described. An image generation system receives a two-dimensional reference image depicting a person and a textual description describing target clothing in which the person is to be depicted as wearing. To maintain a personal identity of the person, the image generation system implements a generative model, trained using both discriminator loss and perceptual quality loss, which is configured to generate images from text. In some implementations, the image generation system is configured to train the generative model to output visually realistic images depicting the human subject in the target clothing. The image generation system is further configured to apply the trained generative model to process individual frames of a reference video depicting a person and output frames depicting the person wearing textually described target clothing.
-
Patent Agency Ranking
公开(公告)号：US11210831B2
公开(公告)日：2021-12-28
申请号：US16804822
申请日：2020-02-28
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Gang Wu , Akshay Malhotra
Abstract: Generating images and videos depicting a human subject wearing textually defined attire is described. An image generation system receives a two-dimensional reference image depicting a person and a textual description describing target clothing in which the person is to be depicted as wearing. To maintain a personal identity of the person, the image generation system implements a generative model, trained using both discriminator loss and perceptual quality loss, which is configured to generate images from text. In some implementations, the image generation system is configured to train the generative model to output visually realistic images depicting the human subject in the target clothing. The image generation system is further configured to apply the trained generative model to process individual frames of a reference video depicting a person and output frames depicting the person wearing textually described target clothing.
-
公开(公告)号：US10567838B2
公开(公告)日：2020-02-18
申请号：US14503802
申请日：2014-10-01
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Gang Wu
IPC: H04N21/442 , H04N21/482 , H04N21/81 , H04N21/845 , H04L29/08
Abstract: Content consumption session progress is predicted based on historical observations of how users have interacted with a repository of digital content. This is approached as a matrix completion problem. Information extracted from tracking logs maintained by one or more content providers is used to estimate the extent to which various content items are consumed. The extracted session progress data is used to populate a session progress matrix in which each matrix element represents a session progress for a particular user consuming a particular content item. This matrix, which in principle will be highly (≳95%) sparse, can be completed using a collaborative filtering matrix completion technique. The values obtained as a result of completing the session progress matrix represent predictions with respect to how much of a given content item will be consumed by a given user.
-
公开(公告)号：US20250061609A1
公开(公告)日：2025-02-20
申请号：US18451201
申请日：2023-08-17
Applicant: ADOBE INC.
Inventor： Junda Wu , Haoliang Wang , Tong Yu , Stefano Petrangeli , Gang Wu , Viswanathan Swaminathan , Sungchul Kim , Handong Zhao
Abstract: One or more aspects of the method, apparatus, and non-transitory computer readable medium include obtaining image data and computing a prediction residue value for a pixel of the image data using a prediction function. An entropy value for the pixel can then be determined based on the prediction residue value using context modeling, and progressive compressed image data for the image data can be generated based on the entropy value. The compressed image data can be used to enable collaborative image editing and other image processing tasks.
-
公开(公告)号：US12219180B2
公开(公告)日：2025-02-04
申请号：US17749846
申请日：2022-05-20
Applicant: Adobe Inc.
Inventor： Gang Wu , Yang Li , Stefano Petrangeli , Viswanathan Swaminathan , Haoliang Wang , Ryan A. Rossi , Zhao Song
IPC: G06K9/00 , G06N20/00 , H04N19/182 , H04N19/184 , H04N19/50 , H04N19/91 , H04N19/96
Abstract: Embodiments described herein provide methods and systems for facilitating actively-learned context modeling. In one embodiment, a subset of data is selected from a training dataset corresponding with an image to be compressed, the subset of data corresponding with a subset of data of pixels of the image. A context model is generated using the selected subset of data. The context model is generally in the form of a decision tree having a set of leaf nodes. Entropy values corresponding with each leaf node of the set of leaf nodes are determined. Each entropy value indicates an extent of diversity of context associated with the corresponding leaf node. Additional data from the training dataset is selected based on the entropy values corresponding with the leaf nodes. The updated subset of data is used to generate an updated context model for use in performing compression of the image.
-
公开(公告)号：US20230379507A1
公开(公告)日：2023-11-23
申请号：US17749846
申请日：2022-05-20
Applicant: Adobe Inc.
Inventor： Gang Wu , Yang Li , Stefano Petrangeli , Viswanathan Swaminathan , Haoliang Wang , Ryan A. Rossi , Zhao Song
IPC: H04N19/96 , H04N19/91 , H04N19/50 , H04N19/184 , H04N19/182 , G06N20/00
CPC classification number: H04N19/96 , H04N19/91 , H04N19/50 , H04N19/184 , H04N19/182 , G06N20/00
Abstract: Embodiments described herein provide methods and systems for facilitating actively-learned context modeling. In one embodiment, a subset of data is selected from a training dataset corresponding with an image to be compressed, the subset of data corresponding with a subset of data of pixels of the image. A context model is generated using the selected subset of data. The context model is generally in the form of a decision tree having a set of leaf nodes. Entropy values corresponding with each leaf node of the set of leaf nodes are determined. Each entropy value indicates an extent of diversity of context associated with the corresponding leaf node. Additional data from the training dataset is selected based on the entropy values corresponding with the leaf nodes. The updated subset of data is used to generate an updated context model for use in performing compression of the image.
-
-
-
-
-
-
-
-
-
Search Results
18
records
(took 0.018 seconds)
