Huawei Technologies Co., Limited

Tencent Technology (shenzhen) Company Limited

Yang Ding

Kunpeng Liu

Jian Yu

Gang Yu

Chao Wang

Qiang Li

Jiafeng Shao

Pei Cheng

Yuxuan Yan

Youcheng Ben

Shengyu Li

Bin Fu

Kui Zhang

Xiao Zhou

Ruijie Li

Ruixue Shen

Xiaohang Ren

Hui Shi

Chengyuan Wang

Embodiments of this application provide a communication method and a related device. The method includes: A terminal device obtains a plurality of power offset values corresponding to one reference signal resource, determines a plurality of pieces of channel state information CSI based on the plurality of offset values, and sends some or all of the plurality of pieces of CSI to a network device. The network device may flexibly adjust data transmit power based on the plurality of power offset values and the plurality of pieces of corresponding CSI, and perform appropriate link adaptation adjustment.

Communication method and related device

Disclosed is a method for training an expression transfer model performed by a computer device, the method including: obtaining a source domain facial image of a first object, a target domain facial image of a second object and a facial feature image associated with the target domain facial image; applying the facial feature image and the source domain facial image to an expression transfer model to obtain a synthesized facial image of the first object; applying the synthesized facial image and the target domain facial image to a discriminative network model obtain two discrimination results; applying the synthesized facial image and the target domain facial image to an image classification model to obtain a category feature vector for identifying a difference between the synthesized facial image and the target domain facial image; and updating the expression transfer model according to the category feature vector and the discrimination results.

Training method for expression transfer model, expression transfer method and apparatus

An embodiment of this application discloses an artificial intelligence-based image generation method performed by a computer device. The method includes: acquiring a source image including a target object whose pose is to be transformed, and a target image including a reference object presenting a target pose; determining a pose transition matrix according to a model pose corresponding to the pose of the target object and a model pose corresponding to the target pose of the reference object; extracting a basic appearance feature of the target object from the source image; processing the basic appearance feature based on the pose transition matrix, to obtain a target appearance feature of the target object in the target pose; and generating a target synthetic image of the target object in the target pose based on the target appearance feature.

Artificial intelligence-based image generation method, device and apparatus, and storage medium

The technology of this application relates to a memory management method and apparatus. When garbage collection is performed by using the method, stored information about a first reference cycle is first obtained, where the first reference cycle is a cyclic reference formed by a plurality of objects, and the information about the first reference cycle includes the plurality of objects in the first reference cycle and a reference relationship between the plurality of objects. The method further includes determining that a second reference cycle exists, where information about the second reference cycle matches the information about the first reference cycle, and the information about the second reference cycle includes a plurality of objects in the second reference cycle and a reference relationship between the plurality of objects. The method further includes reclaiming memory occupied by the plurality of objects in the second reference cycle.

Memory management method and apparatus

Growing community of inventors

Shenzhen, China

Yang Ding