-
公开(公告)号:US20230281926A1
公开(公告)日:2023-09-07
申请号:US18179415
申请日:2023-03-07
发明人: Xiangyu XU , Lijuan LIU , Shuicheng YAN
CPC分类号: G06T17/20 , G06T7/80 , G06T7/70 , G06T7/50 , G06T2207/20081 , G06T2207/20084 , G06T2207/30196
摘要: A method for estimating the shape and pose of a body includes obtaining an image of the body, extracting image features, and transforming the image features to a set of parameter values describing the body's shape and pose using a transformer comprising a cascade of transformer units, wherein each transformer unit operates on a representation of a respective version of the set of parameter values and modifies the representation of the respective version of the set of parameter values by the image features weighted by an attention of the respective version of the set of parameter values to the image features in sequence with a self-attention layer modifying the representation of the respective version of the set of parameter values by components of the representation of parameter values weighted by an attention between the components of the representation of the respective version of the set of parameter values to themselves.
-
公开(公告)号:US20240259332A1
公开(公告)日:2024-08-01
申请号:US18417342
申请日:2024-01-19
发明人: Rundong WANG , Zhongwen XU , Shuicheng YAN
IPC分类号: H04L51/02 , H04L51/07 , H04L51/216
CPC分类号: H04L51/02 , H04L51/07 , H04L51/216
摘要: Systems, methods, and non-transitory computer-readable mediums are provided for an improved system for determining a response strategy to a set of messages received by at least one agent of a plurality of agents. For example, a system may be configured to obtain a set of messages received by at least one agent of a plurality of agents. Additionally, the system may be configured to categorize each message of the set of messages into an asynchronous category or a synchronous category. Moreover, the system may be configured to determine a significance parameter indicative of an importance of the received content parameter of each of at least two asynchronous messages. Further, the system may be configured to determine, for the at least one agent, a response signal related to the response strategy. In some examples, response signal may be determined based on the significance parameter.
-
公开(公告)号:US20230376729A1
公开(公告)日:2023-11-23
申请号:US18319167
申请日:2023-05-17
发明人: YiChen ZHOU , Pan ZHOU , Shuicheng YAN
IPC分类号: G06N3/0455 , G06N3/0985
CPC分类号: G06N3/0455 , G06N3/0985
摘要: Aspects concern a method for training a neural network, comprising forming an autoencoder comprising the neural network as encoder and comprising a decoder, for each training image of multiple training images, generating a latent representation of the training image by the encoder, transforming the training image and supplying information about the transformation and at least a part of the latent representation to the decoder to generate a decoder output for the training image and adjusting the encoder and the decoder to reduce a loss between the transformed training images and the decoder outputs.
-
公开(公告)号:US20240144029A1
公开(公告)日:2024-05-02
申请号:US18464126
申请日:2023-09-08
发明人: Haozhe FENG , Tianyu PANG , Chao DU , Shuicheng YAN , Min LIN
IPC分类号: G06N3/098
CPC分类号: G06N3/098
摘要: A method for training a machine learning model is described, comprising receiving, for each perturbation of a plurality of perturbations of model parameters of a starting version of the machine learning model, a change of loss of the machine learning model caused by the perturbation for a set of training data determined by feeding the set of training data to one or more perturbed versions of the machine learning model, estimating a gradient of the loss of the machine learning model with respect to the model parameters from the determined changes of loss and updating the starting version of the machine learning model to an updated version of the machine learning model by changing the model parameters in a direction for which the estimated gradient indicates a reduction of loss.
-
-
-