公开(公告)号：EP4462376A1

公开(公告)日：2024-11-13

申请号：EP24174841.7

申请日：2024-05-08

申请人： Siemens Healthineers AG

发明人： GIBSON, Eli ,  MAILHE, Boris

IPC分类号： G06V10/24 ,  G06V10/30 ,  G06V10/774 ,  G06V10/82 ,  G06N3/08 ,  G06T11/60 ,  G06T5/70

摘要： Systems and methods for generating augmented images are provided. One or more input medical images are received. At least one of noise and one or more transformations are applied to the one or more input medical images to generate one or more noisy augmented images. The one or more noisy augmented images are denoised using a diffusion-based denoising system to generate one or more denoised augmented images. The applying and the denoising are repeated for one or more iterations using the one or more denoised augmented images as the one or more input medical images to generate one or more final augmented images. The one or more final augmented images are output.

公开(公告)号：EP4462374A1

公开(公告)日：2024-11-13

申请号：EP23172034.3

申请日：2023-05-08

申请人： Elektrobit Automotive GmbH

发明人： Chandrasekaran, Kavin ,  Nourbakhsh, Seyed Hami

IPC分类号： G06V10/143 ,  G06V10/24 ,  G06V10/75 ,  G06V10/774 ,  G06V10/80 ,  G06V10/82 ,  G06V20/56 ,  G06V20/64 ,  G06V20/70 ,  G06N3/08

摘要： The present disclosure relates to a vehicle, an autonomous/assisted driving system (ADS) a computer program, an apparatus (600), and a method (100) for an autonomous/assisted driving system. The method (100) comprises obtaining (110) a top view representation of labels of a traffic environment in Cartesian coordinates from sample data. The method (100) also comprises obtaining (120) a transformation matrix for transforming Cartesian coordinates in an observation coordinate system of a perspective of an environmental sensor of the ADS. Further, the method (100) provides for applying (130) the transformation matrix to the top view representation of the labels to obtain a perspective representation of the traffic environment in the observation coordinate system.

公开(公告)号：EP3791319B1

公开(公告)日：2024-11-06

申请号：EP19724984.0

申请日：2019-05-01

发明人： EBSTYNE, Michael ,  ESCOS, Pedro Urbina ,  PEKELNY, Yuri ,  CHAN, Jonathan Chi Hang ,  SHALEV, Emanuel ,  KIPMAN, Alex ,  FLICK, Mark

IPC分类号： G06V10/774 ,  G06F18/21

公开(公告)号：EP4453906A1

公开(公告)日：2024-10-30

申请号：EP22838884.9

申请日：2022-12-23

申请人： Centre National de la Recherche Scientifique ,  Ecole Polytechnique ,  Ecole Normale Supérieure ,  Sorbonne Université

发明人： MOSCHOS, Evangelos ,  STEGNER, Alexandre ,  LE VU, Briac ,  SCHWANDER, Olivier

IPC分类号： G06V10/82 ,  G06V20/13 ,  G06V10/774

公开(公告)号：EP4453903A1

公开(公告)日：2024-10-30

申请号：EP22835061.7

申请日：2022-12-15

申请人： Bayer Aktiengesellschaft

发明人： SCHAEFER, Dirk ,  HOETTER, Benjamin ,  FISCHER, Gregor ,  RUELBERG, Klaus

IPC分类号： G06V10/778 ,  G06V20/68 ,  G06V10/10 ,  G06K7/10 ,  G06K7/14 ,  B23K26/18 ,  G06K19/06 ,  G06V10/24 ,  G06V10/774 ,  G06V10/82 ,  G06N3/02 ,  G06N3/0464

公开(公告)号：EP4453901A1

公开(公告)日：2024-10-30

申请号：EP22851059.0

申请日：2022-12-01

申请人： Ventana Medical Systems, Inc.

发明人： BA, Qinle ,  KIM, Jungwon ,  MARTIN, Jim F. ,  SCHIMID, Joachim ,  WANG, Xingwei

IPC分类号： G06V10/774 ,  G06V10/82

公开(公告)号：EP4452070A1

公开(公告)日：2024-10-30

申请号：EP22836260.4

申请日：2022-12-20

申请人： Guerbet ,  Institut Gustave-Roussy

发明人： BONE, Alexandre ,  ROHÉ, Marc-Michel ,  LASSAU, Nathalie ,  AMMARI, Samy ,  ROBERT, Philippe

IPC分类号： A61B6/00 ,  G06V10/774 ,  G06V10/82 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G16H50/50 ,  G16H50/70 ,  G01R33/56

公开(公告)号：EP4451230A1

公开(公告)日：2024-10-23

申请号：EP23168202.2

申请日：2023-04-17

申请人： TOYOTA JIDOSHA KABUSHIKI KAISHA ,  Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V.

发明人： OLMEDA REINO, Daniel ,  DAS, Anurag ,  DAI, Dengxin ,  SCHIELE, Bernt ,  XIAN, Yongqin

IPC分类号： G06V10/774 ,  G06V10/26

摘要： The present invention relates to a method for training an image segmentation model (ISM) for segmenting images (IMG) of a second type, the model (ISM) having been trained (T100) using a first set ( X s ) of images of a first type and having labels ( Y s ), the method comprising training (T200) the model (ISM) using at least a second set ( X t ) of images of the second type and having weak-labels ( Y t ), the weakly-labeled images comprising unlabeled pixels, wherein said training (T200) is performed using a loss function ( ) based on: similarity measures ( f t i ⋅ η t k ) between class prototypes ( η t k ) and features ( f t i ) of the images of the second set ( X t ); and on the weak-labels ( y t i k ) of the images of the second set ( X t ).

公开(公告)号：EP4018358B1

公开(公告)日：2024-10-23

申请号：EP20735819.3

申请日：2020-06-17

发明人： NIR, Oron ,  ZONTAK, Maria ,  BURNS, Tucker, Cunningham ,  SINGHAL, Apar ,  ZHANG, Lei ,  OFER, Irit ,  LEVI, Avner ,  SABO, Haim ,  BAR-MENACHEM, Ika ,  AMI, Eylon ,  BEN TOV, Ella ,  ZAMAN, Anika

IPC分类号： G06V10/25 ,  G06V10/774 ,  G06V20/40

公开(公告)号：EP4432128A1

公开(公告)日：2024-09-18

申请号：EP23862051.2

申请日：2023-07-18

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： SHU, Xiujun ,  WEN, Wei ,  QIAO, Ruizhi

IPC分类号： G06F16/583 ,  G06F16/538 ,  G06F16/532 ,  G06V10/40 ,  G06V10/74 ,  G06V10/774

CPC分类号： G06V10/40 ,  G06V10/74 ,  G06F16/532 ,  G06F16/583 ,  G06V10/774 ,  G06F16/538 ,  G06V10/82 ,  G06F16/55 ,  G06V10/44 ,  G06V10/761

摘要： An image retrieval method and apparatus, and an electronic device and a storage medium. The image retrieval method comprises: acquiring a candidate image set, and data to be retrieved of a plurality of modalities, wherein the candidate image set comprises a plurality of candidate images; performing feature extraction on said data on the basis of a target model, so as to obtain a first feature of said data; performing feature extraction on the candidate images multiple times on the basis of the target model, so as to obtain a second feature after the candidate images are aligned with said data of the plurality of modalities; determining a first similarity between each candidate image and each piece of said data of the plurality modalities according to the first feature and the second feature; determining, according to the first similarity and from the candidate image set, a plurality of result image sets corresponding to a retrieval data combination, wherein the retrieval data combination comprises data to be retrieved of at least one modality; and merging the plurality of result image sets, so as to obtain an image retrieval result.