中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

107 records (took 0.029 seconds)

    Graph neural networks for datasets with heterophily
    81.
    发明授权
    Graph neural networks for datasets with heterophily 有权

    公开(公告)号：US12175366B2

    公开(公告)日：2024-12-24

    申请号：US17210157

    申请日：2021-03-23

    Applicant: Adobe Inc.

    Inventor： Ryan Rossi ,  Tung Mai ,  Nedim Lipka ,  Jiong Zhu ,  Anup Rao ,  Viswanathan Swaminathan

    IPC: G06N3/08 ,  G06F16/901 ,  G06F18/2132 ,  G06F18/2413 ,  G06N5/02

    Abstract: Techniques are provided for training graph neural networks with heterophily datasets and generating predictions for such datasets with heterophily. A computing device receives a dataset including a graph data structure and processes the dataset using a graph neural network. The graph neural network defines prior belief vectors respectively corresponding to nodes of the graph data structure, executes a compatibility-guided propagation from the set of prior belief vectors and using a compatibility matrix. The graph neural network predicts predicting a class label for a node of the graph data structure based on the compatibility-guided propagations and a characteristic of at least one node within a neighborhood of the node. The computing device outputs the graph data structure where it is usable by a software tool for modifying an operation of a computing environment.

    IMAGE COMPRESSION PERFORMANCE OPTIMIZATION FOR IMAGE COMPRESSION
    86.
    发明公开
    IMAGE COMPRESSION PERFORMANCE OPTIMIZATION FOR IMAGE COMPRESSION 审中-公开

    公开(公告)号：US20240070927A1

    公开(公告)日：2024-02-29

    申请号：US17895758

    申请日：2022-08-25

    Applicant: Adobe Inc.

    Inventor： Haoliang Wang ,  Stefano Petrangeli ,  Viswanathan Swaminathan

    IPC: G06T9/40 ,  G06T3/40

    CPC classification number: G06T9/40 ,  G06T3/40

    Abstract: The context-aware optimization method includes training a context model by determining whether to split each node in the context by identifying a first subset of virtual context to evaluate by identifying a second subset of virtual contexts to evaluate and obtaining an encoding cost of splitting of the context model for each virtual context in the second subset and identifying the first subset of virtual contexts to evaluate by selecting a predetermined number of virtual contexts from the second subset based on the encoding cost such that the predetermined number of virtual contexts with lowest encoding cost are selected. The modified tree-traversal method includes encoding a mask or performing a speculative-based method. The modified entropy coding method includes representing data into an array of bits, using multiple coders to process each bit in the array and combining the output from the multiple coders into a data range.

    Automatic Item Placement Recommendations Based on Entity Similarity
    87.
    发明公开
    Automatic Item Placement Recommendations Based on Entity Similarity 审中-公开

    公开(公告)号：US20240029107A1

    公开(公告)日：2024-01-25

    申请号：US18478856

    申请日：2023-09-29

    Applicant: Adobe Inc.

    Inventor： Xiang Chen ,  Viswanathan Swaminathan ,  Somdeb Sarkhel

    IPC: G06Q30/0251 ,  G06F16/28 ,  G06F16/22 ,  G06Q30/0241

    CPC classification number: G06Q30/0254 ,  G06F16/285 ,  G06F16/2237 ,  G06Q30/0255 ,  G06Q30/0277 ,  G06Q30/0261 ,  G06Q30/0264 ,  G06F16/2264

    Abstract: Automatic item placement recommendation is described. An item placement configuration system receives an item for which a recommended placement is to be generated and identifies an entity associated with the item. The item placement configuration system then identifies a multi-domain taxonomy that describes relationships between different entities based on items associated with the different entities published among different domains. A representation of the entity associated with the item to be placed is then identified within the multi-domain taxonomy, along with a representation of at least one similar entity. Upon identifying a similar entity, historic item placement metrics for the similar entity are leveraged to generate a placement recommendation for the received item. In some implementations, the placement recommendation is output with a visual indication of a similar entity and associated performance metrics that were considered in generating the recommended placement.

    Automatic item placement recommendations based on entity similarity
    89.
    发明授权
    Automatic item placement recommendations based on entity similarity 有权

    公开(公告)号：US11810152B2

    公开(公告)日：2023-11-07

    申请号：US16598933

    申请日：2019-10-10

    Applicant: Adobe Inc.

    Inventor： Xiang Chen ,  Viswanathan Swaminathan ,  Somdeb Sarkhel

    IPC: G06Q30/0251 ,  G06F16/28 ,  G06F16/22 ,  G06Q30/0241

    CPC classification number: G06Q30/0254 ,  G06F16/2237 ,  G06F16/2264 ,  G06F16/285 ,  G06Q30/0255 ,  G06Q30/0261 ,  G06Q30/0264 ,  G06Q30/0277

    Abstract: Automatic item placement recommendation is described. An item placement configuration system receives an item for which a recommended placement is to be generated and identifies an entity associated with the item. The item placement configuration system then identifies a multi-domain taxonomy that describes relationships between different entities based on items associated with the different entities published among different domains. A representation of the entity associated with the item to be placed is then identified within the multi-domain taxonomy, along with a representation of at least one similar entity. Upon identifying a similar entity, historic item placement metrics for the similar entity are leveraged to generate a placement recommendation for the received item. In some implementations, the placement recommendation is output with a visual indication of a similar entity and associated performance metrics that were considered in generating the recommended placement.

    TECHNIQUES FOR IMAGE ATTRIBUTE EDITING USING NEURAL NETWORKS
    90.
    发明公开
    TECHNIQUES FOR IMAGE ATTRIBUTE EDITING USING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230162330A1

    公开(公告)日：2023-05-25

    申请号：US17531640

    申请日：2021-11-19

    Applicant: Adobe Inc.

    Inventor： Stefano Petrangeli ,  Viswanathan Swaminathan ,  Haoliang Wang ,  YoungJoong Kwon

    IPC: G06T5/00 ,  G06N3/04 ,  G06K9/62

    CPC classification number: G06T5/005 ,  G06N3/0454 ,  G06K9/6209

    Abstract: The present disclosure describes multi-stage image editing techniques to improve detail and accuracy in edited images. An input image including a target region to be edited and an edit parameter specifying a modification to the target region are received. A parsing map of the input image is generated. A latent representation of the parsing map is generated. An edit is applied to the latent representation of the parsing map based on the edit parameter. The edited latent representation is input to a neural network to generate a modified parsing map including the target region with a shape change according to the edit parameter. Based on the input image and the modified parsing map, a masked image corresponding to the shape change is generated. Based on the masked image, a neural network is used to generate an edited image with the modification to the target region.

Patent Agency Ranking