公开(公告)号：US20200327681A1

公开(公告)日：2020-10-15

申请号：US16913795

申请日：2020-06-26

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhigang LI ,  Jianzhuang LIU ,  Li QIAN

IPC: G06T7/246 ,  G06K9/62 ,  G06T7/73

Abstract: In one embodiment, a target tracking method includes: receiving a current frame of picture including a target object; determining, based on a drift determining model, whether a tracker drifts for tracking of the target object in the current frame of picture, where the drift determining model is obtained through modeling based on largest values of responses values of a training sample used to train the drift determining model, where the training sample is collected from a training picture that includes the target object, where the response value of the sample is a value indicating a probability that the training sample is the target object in the training picture; and outputting a tracking drift result, where the tracking drift result includes: drift is generated for the tracking of the target object, or no drift is generated for the tracking of the target object.

公开(公告)号：US20230008363A1

公开(公告)日：2023-01-12

申请号：US17780384

申请日：2020-11-17

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Heng LIU ,  Zhigang LI ,  Mingyu YU ,  Huimin CHE ,  Honglei ZHANG

IPC: G10L15/25 ,  G10L15/02 ,  G10L15/06 ,  G06V40/16

Abstract: Embodiments of the present application disclose an audio matching method and a related device. The audio matching method includes: obtaining audio data and video data; extracting to-be-recognized audio information from the audio data; extracting lip movement information of N users from the video data, where N is an integer greater than 1; inputting the to-be-recognized audio information and the lip movement information of the N users into a target feature matching model, to obtain a matching degree between each of the lip movement information of the N users and the to-be-recognized audio information; and determining a user corresponding to the lip movement information of the user with the highest matching degree as the target user to which the to-be-recognized audio information belongs.

公开(公告)号：US20180129672A1

公开(公告)日：2018-05-10

申请号：US15576637

申请日：2015-05-27

Applicant: Huawei Technologies Co., Ltd.

Inventor： Guojun SHI ,  Zhigang LI ,  Fuzhou XIAO

IPC: G06F17/30 ,  G06F3/06 ,  G06F12/02

CPC classification number: G06F16/13 ,  G06F3/06 ,  G06F3/0613 ,  G06F3/064 ,  G06F12/02 ,  G06F16/16 ,  G06F16/1724 ,  G06F16/182

Abstract: A method and an apparatus for accessing a file, and a storage system. The method includes: determining L first-file invoking request messages; separately adding, according to physical sector information in the L first-file invoking request messages, the L first-file invoking request messages to M first-file dispatch queues; and processing a first-file invoking request message included in each first-file dispatch queue, to obtain an invoking request message of each first-file dispatch queue, where the invoking request message is used to access a first file. By means of the method and apparatus for accessing a file and the storage system in the embodiments of the present disclosure, a corresponding dispatch queue is allocated to an invoking request message of a micro file, so that combination processing can be performed on invoking request messages of multiple micro files, and a quantity of times of invoking a micro file is reduced.