-
公开(公告)号：US20230119509A1
公开(公告)日：2023-04-20
申请号：US17865762
申请日：2022-07-15
发明人： Bohyung Han , Jonghyeon Seon , Jaedong Hwang
IPC分类号： G06V10/82 , G06V20/40 , G06V10/774 , G06V10/776
摘要： A method includes generating, by a neural network having a plurality of layers, final feature vectors of one or more frames of a plurality of frames of an input video, while sequentially processing each of the plurality of, and generating image information corresponding to the input video based on the generated final feature vectors. For each of the plurality of frames, the generating of the final feature vectors comprises determining whether to proceed with or stop a corresponding sequenced operation through layers of the neural network for generating a final feature vector of a corresponding frame, and generating the final feature vector of the corresponding frame in response to the corresponding sequenced operation completing a final stage of the corresponding sequenced operation.
-
公开(公告)号：US11688403B2
公开(公告)日：2023-06-27
申请号：US16811452
申请日：2020-03-06
发明人： Seungju Han , Jaejoon Han , Minsu Ko , Chang Kyu Choi , Bohyung Han
IPC分类号： G10L17/02 , G06N3/08 , G10L17/06 , G10L17/18 , G10L17/04 , G06V40/50 , G06V40/70 , G06F21/36 , G06F21/45 , G06V10/82 , G06F18/00 , G06F18/24 , G06N3/045 , G06V10/764
CPC分类号： G10L17/02 , G06F18/00 , G06F18/24 , G06F21/36 , G06F21/45 , G06N3/045 , G06N3/08 , G06V10/764 , G06V10/82 , G06V40/50 , G06V40/70 , G10L17/04 , G10L17/06 , G10L17/18
摘要： An authentication method and apparatus using a transformation model are disclosed. The authentication method includes generating, at a first apparatus, a first enrolled feature based on a first feature extractor, obtaining a second enrolled feature to which the first enrolled feature is transformed, determining an input feature by extracting a feature from input data with a second feature extractor different from the first feature extractor, and performing an authentication based on the second enrolled feature and the input feature.
-
公开(公告)号：US09940539B2
公开(公告)日：2018-04-10
申请号：US15147665
申请日：2016-05-05
发明人： Bohyung Han , Seunghoon Hong , Hyeonwoo Noh
CPC分类号： G06K9/4628 , G06K9/6272
摘要： An object recognition apparatus and method thereof are disclosed. An exemplary apparatus may determine an image feature vector of a first image by applying a convolution network to the first image. The convolution network may extract features from image learning sets that include the first image and a sample segmentation map of the first image. The exemplary apparatus may determine a segmentation map of the first image by applying a deconvolution network to the determined image feature vector. The exemplary apparatus may determine a weight of the convolution network and a weight of the deconvolution network based on the sample segmentation map and the first segmentation map. The exemplary apparatus may determine a second segmentation map of a second image through the convolution network using the determined weight of the convolution network and through the deconvolution network using the determined weight of the deconvolution network.
-
公开(公告)号：US09922262B2
公开(公告)日：2018-03-20
申请号：US14963856
申请日：2015-12-09
发明人： Taegyu Lim , Bohyung Han , Seunghoon Hong
CPC分类号： G06K9/3241 , G06K9/00785 , G06K9/6296 , G06K2009/3291 , G06T7/246 , G06T2207/10016 , G06T2207/20072 , G06T2207/30236
摘要： A method by which a tracking apparatus tracks a target object includes: acquiring a first tree structure indicating a tracking processing order of frames, each frame including a tracking area in which the target object is located; acquiring a plurality of frame groups, each frame group consisting of two frames, and acquiring distance evaluation values of the respective frame groups; acquiring a second tree structure based on the first tree structure and the distance evaluation values; and tracking the target object based on the acquired second tree structure, wherein the distance evaluation value is determined based on at least one of locations of tracking areas included in two frames belonging to the frame group and pixel values included in the tracking areas.
-
-
-
搜索结果
4 条记录 (耗时 0.018 秒)
