专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

EP3625724B1 A METHOD TO AUTHENTICATE A SUBSTRATE USING SPECKLE PATTERNS AND A DEVICE TO PERFORM THE METHOD 有权
公开(公告)号：EP3625724B1
公开(公告)日：2023-07-26
申请号：EP17723700.5
申请日：2017-05-16
发明人： BERGQVIST, Johan
IPC分类号： G06F18/25 , G06V10/143 , G06V10/80 , G06V20/80

12. 发明公开

EP4152180A3 METHOD OF DETECTING ACTION, ELECTRONIC DEVICE, AND STORAGE MEDIUM 审中-实审
公开(公告)号：EP4152180A3
公开(公告)日：2023-07-12
申请号：EP22216478.2
申请日：2022-12-23
申请人： Beijing Baidu Netcom Science Technology Co., Ltd.
发明人： Ma, Caihong , Wang, Guanhao
IPC分类号： G06F18/25
摘要： The present disclosure provides a method of detecting an action, an apparatus of detecting an action, an electronic device, and a storage medium, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision and deep learning technologies. A specific implementation solution includes: performing a feature extraction on a plurality of target frame data of a target resource, so as to obtain at least one target feature data; performing a temporal action proposal on the at least one target feature data, so as to obtain at least one first candidate action proposal information, wherein the first candidate action proposal information includes a first candidate action proposal interval; classifying target feature data corresponding to the at least one first candidate action proposal interval, so as to obtain at least one classification confidence level corresponding to the at least one first candidate action proposal interval; and determining an action detection result for at least one action segment contained in the target resource according to the at least one classification confidence level corresponding to the at least one first candidate action proposal interval, wherein the action detection result includes an action category and an action period.

13. 发明公开

EP4177793A1 METHOD AND SYSTEM OF VERIFYING AUTHENTICITY OF DECLARATION INFORMATION, DEVICE AND MEDIUM 审中-实审
公开(公告)号：EP4177793A1
公开(公告)日：2023-05-10
申请号：EP22205567.5
申请日：2022-11-04
申请人： Nuctech Company Limited , Tsinghua University
发明人： Zhang, Li , Xing, Yuxiang , Tang, Hu , Sun, Yunda , Fu, Gang , Li, Qiang , Zhang, Yan , Wu, Wubin
IPC分类号： G06N3/04 , G06F18/25 , G01N23/04 , G06V10/82 , G06V10/80 , G06V20/60 , G06V30/413
摘要： Provided is a method of verifying an authenticity of declaration information. The method includes: acquiring a machine-detected radiation image (22) obtained by scanning a container (20) loaded with an article; acquiring a declaration information (21) for declaring the article in the container (20); performing an identification on an image information of the article in the machine-detected radiation image (22) to obtain an image feature corresponding to the machine-detected radiation image (22); performing an identification on a text information of the article in the declaration information (21) to obtain a text feature corresponding to the declaration information (21); screening a declaration category of the article in the container (20) by taking the image feature as an input information and the text feature as an external introduction feature; and determining that the declaration information (21) is in doubt when a declaration category of at least one article in the container (20) does not belong to a declaration category in the declaration information (21).

14. 发明授权

EP3695342B1 METHOD AND SYSTEM FOR FINGERPRINT IMAGE ENHANCEMENT 有权转让
公开(公告)号：EP3695342B1
公开(公告)日：2024-09-25
申请号：EP18865664.9
申请日：2018-10-02
IPC分类号： G06V40/12 , G06V10/80 , G06F18/25 , G06T5/20
CPC分类号： G06T5/20 , G06V40/1359 , G06V10/806 , G06F18/253

15. 发明公开

EP4425353A2 GRAPH NEURAL NETWORK GENERATION METHOD, APPARATUS AND SYSTEM, MEDIUM AND ELECTRONIC DEVICE 审中-实审
公开(公告)号：EP4425353A2
公开(公告)日：2024-09-04
申请号：EP22901924.5
申请日：2022-11-04
申请人： Lemon Inc.
发明人： ZHU, Yibo , CHEN, Yangrui , HE, Jun , PENG, Yanghua , GUO, Chuanxiong , WANG, Jian
IPC分类号： G06F18/214 , G06N3/08 , G06N3/04 , G06F18/25
摘要： The disclosure relates to a method, apparatus, system, medium and electronic device for graph neural network generation. The method includes: obtaining a subgraph structure, the subgraph structure being configured to reflect a graph structure of a corresponding subgraph, and the subgraph comprising a plurality of nodes and edges between the plurality of nodes; obtaining, based on the subgraph structure and according to a predetermined priority, node features of the plurality of nodes and edge features of the edges from a plurality of memories; the predetermined priority being obtained by sorting the plurality of memories in accordance with memory size in an ascending order; fusing, based on the subgraph structure, the node features of the plurality of nodes and the edge features of the edges to obtain subgraph data; and training, based on the subgraph data, the graph neural network. The method for graph neural network generation of the present disclosure may improve the efficiency of graph neural network training.

16. 发明授权

EP3706443B1 METHOD AND APPARATUS FOR SOUND OBJECT FOLLOWING 有权
公开(公告)号：EP3706443B1
公开(公告)日：2024-07-31
申请号：EP20160914.6
申请日：2020-03-04
IPC分类号： H04S7/00 , G06V10/80 , G06V20/40 , G06V40/20 , G06V20/17 , G06F18/22 , G06V10/75 , G06V40/16 , G06F18/25 , H04H20/89 , H04H20/95
CPC分类号： H04S2400/1120130101 , H04S7/30 , H04R2499/1520130101 , H04R2499/1320130101 , H04H20/89 , H04H20/95 , G06V40/171 , G06V40/20 , G06V20/46 , G06V10/806 , G06V10/75 , G06F18/22 , G06F18/253

17. 发明授权

EP4231267B1 TRANSPORTATION VEHICLE TYPE IDENTIFICATION METHOD AND APPARATUS 有权
公开(公告)号：EP4231267B1
公开(公告)日：2024-07-17
申请号：EP22888631.3
申请日：2022-12-15
IPC分类号： H04W4/02 , G06F18/25 , G10L15/26 , G08G1/133 , G08G1/005 , G08G1/00
CPC分类号： Y02D30/70 , H04W4/027 , G10L15/26 , G08G1/005 , G08G1/133 , G08G1/20

18. 发明授权

EP3525133B1 APPARATUS AND METHOD WITH LIVENESS VERIFICATION 有权
公开(公告)号：EP3525133B1
公开(公告)日：2024-07-03
申请号：EP19151612.9
申请日：2019-01-14
IPC分类号： G06V10/143 , G06V10/764 , G06V10/82 , G06V40/19 , G06V40/40 , G06F18/25
CPC分类号： G06F21/32 , G06N3/084 , G06V40/19 , G06V40/45 , G06V10/143 , G06V10/82 , G06V10/80 , G06V10/764 , G06N3/045 , G06F18/25

19. 发明公开

EP4379580A2 RADAR DEEP LEARNING 审中-实审
公开(公告)号：EP4379580A2
公开(公告)日：2024-06-05
申请号：EP24156992.0
申请日：2019-11-29
申请人： QUALCOMM Incorporated
发明人： FONTIJNE, Daniel Hendricus Franciscus , ANSARI, Amin , MAJOR, Bence , SUKHAVASI, Ravi Teja , GOWAIKAR, Radhika Dilip , WU, Xinzhou , SUBRAMANIAN, Sundar , HAMILTON, Michael John
IPC分类号： G06F18/25
CPC分类号： G01S13/931 , G01S17/89 , G01S13/865 , G01S17/931 , G01S13/89 , G01S13/867 , G01S7/417 , G01S7/2955 , G06N3/08 , G06V20/10 , G06V20/58 , G06V20/70 , G06V10/82 , G06V10/803 , G06V10/764 , G06N3/044 , G06N3/045 , G06F18/251
摘要： Disclosed are techniques for employing deep learning to analyze radar signals. In an aspect, an on-board computer of a host vehicle receives, from a radar sensor of the vehicle, a plurality of radar frames, executes a neural network on a subset of the plurality of radar frames, and detects one or more objects in the subset of the plurality of radar frames based on execution of the neural network on the subset of the plurality of radar frames. Further, techniques for transforming polar coordinates to Cartesian coordinates in a neural network are disclosed. In an aspect, a neural network receives a plurality of radar frames in polar coordinate space, a polar-to-Cartesian transformation layer of the neural network transforms the plurality of radar frames to Cartesian coordinate space, and the neural network outputs the plurality of radar frames in the Cartesian coordinate space.

20. 发明公开

EP4379577A1 A COMPUTER-IMPLEMENTED METHOD FOR REDUCING FALSE POSITIVES IN A COMPUTER VISION TASK AND APPLICATION THEREOF TO MOTOR VEHICLE EXTERIOR MONITORING 审中-公开
公开(公告)号：EP4379577A1
公开(公告)日：2024-06-05
申请号：EP23187723.4
申请日：2023-07-26
申请人： Continental Autonomous Mobility Germany GmbH
发明人： Padiri, Bhanu Prakash
IPC分类号： G06F18/21 , G06F18/25 , G06V10/20 , G06V10/774 , G06V10/776 , G06V10/98 , G06V20/58
CPC分类号： G06V20/58 , G06V10/98 , G06F18/256 , G06V10/255 , G06V10/774 , G06V10/993 , G06F18/217 , G06V10/776
摘要： In order to improve real-time false positive reduction, first and second sensor data of a potential object in a common portion of an environment of a motor vehicle are compared (S2). Upon determining that there is a discrepancy in the first and second sensor data in relation to the object, an analysis by synthesis (ABS) is performed on the first sensor data (S3 to S5). If the ABS results in a match, then the first sensor data are validated and can be used for generating a control signal for an autonomous vehicle (S7). If the ABS results in a mismatch, the first sensor data are excluded from generating the control signal (S6). In case of no discrepancy between the first and second sensor data, both are used in generating the control signal (S8). In a variant, the ABS is performed only on first sensor data independent of other sensor data.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式