-
公开(公告)号：US20220351019A1
公开(公告)日：2022-11-03
申请号：US17864521
申请日：2022-07-14
Applicant: Huawei Technologies Co., Ltd.
Inventor： Minqi Chen , Chuanyun Deng , Xiangyu Hu , Shaohua Tang
Abstract: An adaptive search method includes: receiving a search condition set comprising target hardware platform information, network structure information of a source neural network, and one or more evaluation metrics; performing a training process on a to-be-trained super network based on a training dataset to obtain a trained super network, by extending a network structure of the source neural network; and performing a subnet search process on the trained super network based on the one or more evaluation metrics to obtain network structure information of a target neural network, which represents the target neural network and an evaluation result of the target neural network running on a target hardware platform is better than an evaluation result of the source neural network running on the target hardware platform.
-
公开(公告)号：US20220165091A1
公开(公告)日：2022-05-26
申请号：US17671253
申请日：2022-02-14
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Kai Chen , Wenhong Gong , Haoquan Shen , Mingxue Wang , Changcai Lai , Xiangyu Hu
IPC: G06V40/16 , G06V10/80 , G06V10/774 , G06V10/77 , G06V10/74
Abstract: A face search method and apparatus are provided. The method includes obtaining a to-be-searched face image, and inputting the face image into a first feature extraction model to obtain a first face feature. The method further includes inputting the face image and the first face feature into a first feature mapping model for feature mapping, to output a standard feature corresponding to the first face feature, and performing face search for the face image based on the standard feature. Features extracted by using a plurality of feature extraction models are concatenated, and a concatenated feature is used as a basis for constructing a standard feature.
-
公开(公告)号：US20250045871A1
公开(公告)日：2025-02-06
申请号：US18713237
申请日：2022-11-23
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xiangyu Hu , Weiwei Xu , Jinsong Wen , Yanbing Jia , Jiantong Zhou , Qiyan Zhai , Yihua Zeng , Quanhe Yu , Zizhong Wang , Yichuan Wang , Hu Chen , Jinqin Ai , Yutong Hu
IPC: G06T5/20 , G06F3/04845 , G06F3/04883
Abstract: This application provides a picture processing method. The method includes: The encoder side obtains a to-be-processed picture, obtains a plurality of groups of visual sensory experience parameters, and encodes the to-be-processed picture and the plurality of groups of visual sensory experience parameters. At a decoder side, the method includes: The decoder side obtains a to-be-processed picture, obtains a zoom-in operation instruction, obtains one or more groups of visual sensory experience parameters corresponding to one or more local pictures, and separately processes the corresponding local picture based on the one or more groups of visual sensory experience parameters to obtain a processed local picture.
-
公开(公告)号：US11881052B2
公开(公告)日：2024-01-23
申请号：US17671253
申请日：2022-02-14
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Kai Chen , Wenhong Gong , Haoquan Shen , Mingxue Wang , Changcai Lai , Xiangyu Hu
CPC classification number: G06V40/172 , G06V10/761 , G06V10/774 , G06V10/7715 , G06V10/806 , G06V40/168 , G06V10/82
Abstract: A face search method and apparatus are provided. The method includes obtaining a to-be-searched face image, and inputting the face image into a first feature extraction model to obtain a first face feature. The method further includes inputting the face image and the first face feature into a first feature mapping model for feature mapping, to output a standard feature corresponding to the first face feature, and performing face search for the face image based on the standard feature. Features extracted by using a plurality of feature extraction models are concatenated, and a concatenated feature is used as a basis for constructing a standard feature.
-
-
-
Search Results
4
records
(took 0.013 seconds)
