-
公开(公告)号：US20210156695A1
公开(公告)日：2021-05-27
申请号：US17169064
申请日：2021-02-05
发明人： Jun Zhang , Bin Xu , Ronghao Li , Xiaoqiang Teng , Chao Liu , Chong Deng , Gengxin Gu , Huanqing Zhou , Qi Zhou , Yue Liu , Pengfei Xu , Runbo Hu , Hongxia Zhang , Yingfeng Zhang , Guanghui Zhao , Bin Du , Hua Chai , Xian Zhang
摘要： Systems and methods for navigating a user to a destination are provided. An exemplary indoor navigation method uses a terminal device. The method includes capturing, by the terminal device, image data of an indoor scene, and determining a current position of the user based on the captured image data. The method also includes determining a navigation path and a navigation sign for navigating the user from the current position to the destination, and rendering, by the terminal device, a three-dimensional representation of the indoor scene with the navigation sign placed therein based on the image data and the navigation path. The navigation sign signals the navigation path in the three-dimensional representation. The method further includes displaying, on the terminal device, the three-dimensional representation to the user.
-
公开(公告)号：US20210295208A1
公开(公告)日：2021-09-23
申请号：US16826084
申请日：2020-03-20
发明人： Pengfei Xu , Sicheng Zhao , Guangzhi Wang , Shanghang Zhang , Yang Gu , Yaxian Li , Zhichao Song , Runbo Hu , Hua Chai
摘要： Embodiments of the disclosure provide systems and methods for domain adaptation between a plurality of source domains and a target domain. The artificial intelligence method includes receiving labeled data from the plurality of source domains and unlabeled data from the target domain. The method further includes separately training, by a processor, a plurality of source classifiers each corresponding to a source domain using the labeled data received from the respective source domains. The method also includes selecting a subset of the labeled data received from each source domain based on a similarity between the selected labeled data and the unlabeled data of the target domain. The method additionally includes refining, by the processor, each source classifier using the selected subset of the labeled data, and predicting labels of the unlabeled data using the refined source classifiers.
-
公开(公告)号：US11526807B2
公开(公告)日：2022-12-13
申请号：US16826084
申请日：2020-03-20
发明人： Pengfei Xu , Sicheng Zhao , Guangzhi Wang , Shanghang Zhang , Yang Gu , Yaxian Li , Zhichao Song , Runbo Hu , Hua Chai
摘要： Embodiments of the disclosure provide systems and methods for domain adaptation between a plurality of source domains and a target domain. The artificial intelligence method includes receiving labeled data from the plurality of source domains and unlabeled data from the target domain. The method further includes separately training, by a processor, a plurality of source classifiers each corresponding to a source domain using the labeled data received from the respective source domains. The method also includes selecting a subset of the labeled data received from each source domain based on a similarity between the selected labeled data and the unlabeled data of the target domain. The method additionally includes refining, by the processor, each source classifier using the selected subset of the labeled data, and predicting labels of the unlabeled data using the refined source classifiers.
-
-
搜索结果
3 条记录 (耗时 0.019 秒)
