公开(公告)号：US20230171508A1

公开(公告)日：2023-06-01

申请号：US17856395

申请日：2022-07-01

Applicant: Unity Technologies SF

Inventor： Joseph W. Marks ,  Luca Fascione ,  Kimball D. Thurston, III ,  Millie Maier ,  Kenneth Gimpelson ,  Dejan Momcilovic ,  Keith F. Miller ,  Peter M. Hillman ,  Jonathan S. Swartz

IPC: H04N5/235 ,  H04N5/222 ,  G06T5/00 ,  G06V10/60 ,  G06T7/174 ,  G06V10/70 ,  G06K9/62 ,  G06T7/70 ,  G09G5/10 ,  H04N5/232 ,  H04N5/92 ,  G06T5/50 ,  G06T9/00 ,  G06T1/60 ,  H04N7/18 ,  H04N5/91 ,  H04N5/04 ,  G06V10/22 ,  G06T7/10 ,  G06T7/80

CPC classification number: H04N5/2355 ,  G06K9/6215 ,  G06T1/60 ,  G06T5/005 ,  G06T5/007 ,  G06T5/50 ,  G06T7/10 ,  G06T7/70 ,  G06T7/80 ,  G06T7/174 ,  G06T9/00 ,  G06V10/22 ,  G06V10/60 ,  G06V10/70 ,  G09G5/10 ,  H04N5/04 ,  H04N5/91 ,  H04N5/92 ,  H04N5/2224 ,  H04N5/2352 ,  H04N5/2354 ,  H04N5/23229 ,  H04N5/23232 ,  H04N5/23235 ,  H04N7/183 ,  G06T2207/20021 ,  G06T2207/20056 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20208 ,  G06T2207/20221 ,  G06T2207/30244 ,  G09G2320/0626 ,  G09G2320/0686

Abstract: A processor performing postprocessing obtains an input image containing both bright and dark regions. The processor obtains a threshold between a first pixel value of the virtual production display and a second pixel value of the virtual production display. The processor modifies the region according to predetermined steps producing a pattern unlikely to occur within the input image, where the pattern corresponds to a difference between the original pixel value and the threshold. The processor can replace the region of the input image with the pattern to obtain a modified image. The virtual production display can present the modified image. A processor performing postprocessing detects the pattern within the modified image displayed on the virtual production display. The processor calculates the original pixel value of the region by reversing the predetermined steps. The processor replaces the pattern in the modified image with the original pixel value.

公开(公告)号：US20230162830A1

公开(公告)日：2023-05-25

申请号：US17576055

申请日：2022-01-14

Applicant: Express Scripts Strategic Development, Inc.

Inventor： Viswanathan Subramanian ,  Mahipal Singareddy ,  Vincenzo N. Desantis ,  Sreenivasa Chennuru ,  Sravan Kumar Goud Golla ,  Camille Patel

IPC: G16H20/10 ,  G06V30/19 ,  G06V10/70 ,  G06V30/41

CPC classification number: G16H20/10 ,  G06V30/1916 ,  G06V10/70 ,  G06V30/19147 ,  G06V30/41

Abstract: A computer system includes memory hardware configured to store a machine learning model, a record database, and historical feature vector inputs. Processor hardware is configured to execute instructions which include training the machine learning model to generate an entity field output, and for each of multiple database entities, scanning the database entity to generate a feature vector input, and processing the feature vector input to generate the entity field output. In response to determining that the entity field output includes at least one missing field value, the instructions include accessing the record database to identify a predicted value for the missing field value, analyzing the structured scan data or rescanning the database entity to determine whether the predicted value is present in the database entity, and assigning the database entity to the validated subset of the multiple database entities when the predicted value is present in the database entity.

公开(公告)号：US20230162440A1

公开(公告)日：2023-05-25

申请号：US18156111

申请日：2023-01-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Vipul GUPTA ,  Abhinav GABA ,  Rahul AGRAWAL ,  Govind MAHESHWARI ,  Nitesh GOYAL ,  Kalgesh SINGH

IPC: G06T17/00 ,  G06T7/60 ,  G06V10/70 ,  H04N23/63

CPC classification number: G06T17/00 ,  G06T7/60 ,  G06V10/70 ,  H04N23/632

Abstract: A method for generating a virtual model of objects is provided. The method includes detecting, by a first electronic device, a communication session with a second electronic device, obtaining a first set of objects displayed on the first electronic device and a second set of objects displayed on the second electronic device based on the detection of the communication session, determining a first object from the first set of objects to be mapped to a second object from the second set of objects, predicting attributes of visible portions of the first object and the second object by mapping the first object to the second object, obtaining depth information related to the first object and the second object, and generating a virtual model of the first object and the second object based on the attributes of the visible portions of the first object and the second object and the depth information related to the first object and the second object.

公开(公告)号：US12130887B2

公开(公告)日：2024-10-29

申请号：US17515180

申请日：2021-10-29

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Peng Sun ,  Jiaxiang Wu

IPC: G06K9/62 ,  G06F18/21 ,  G06F18/214 ,  G06F18/25 ,  G06N3/04 ,  G06N3/082 ,  G06T7/70 ,  G06V10/26 ,  G06V10/70 ,  G06V10/80 ,  G06V10/82 ,  G06V20/40 ,  G06V20/70

CPC classification number: G06F18/214 ,  G06F18/217 ,  G06F18/253 ,  G06N3/04 ,  G06N3/082 ,  G06T7/70 ,  G06V10/267 ,  G06V10/70 ,  G06V10/806 ,  G06V10/82 ,  G06V20/41 ,  G06V20/70 ,  G06T2207/20084

Abstract: This application provides a semantic segmentation network structure generation method performed by an electronic device, and a non-transitory computer-readable storage medium. The method includes: generating a corresponding architectural parameter for cells that form a super cell in a semantic segmentation network structure; optimizing the semantic segmentation network structure based on image samples, and removing a redundant cell from a super cell to which a target cell pertains, to obtain an improved semantic segmentation network structure; performing, by an aggregation cell in the improved semantic segmentation network structure, feature fusion on an output of the super cell; performing recognition processing on a fused feature map, to determine positions corresponding to objects that are in the image samples; and training the improved semantic segmentation network structure based on the positions corresponding to the objects that are in the image samples and annotations corresponding to the image samples, to obtain a trained semantic segmentation network structure.

公开(公告)号：US20240357060A1

公开(公告)日：2024-10-24

申请号：US18634280

申请日：2024-04-12

Applicant: Video Notebook Inc.

Inventor： Michael LANZA ,  Eran STEINBERG

IPC: H04N7/15 ,  G06V10/70

CPC classification number: H04N7/155 ,  G06V10/70

Abstract: generally comprises obtaining one or more images from the video as the video is played, locating a presence of a shape or text from each of the one or more images, determining whether the shape or text corresponds to a prior shape or text from a prior base image, determining whether each of the one or more images comprises a corresponding slide, presenting the one or more images as one or more slides upon an interface displayed to a user, providing a timestamp upon each of the one or more slides, whereby selection of the timestamp by the user plays the video at a location which correlates to the timestamp within the video, and presenting the one or more slides including the timestamp to the user.

公开(公告)号：US20240354969A1

公开(公告)日：2024-10-24

申请号：US18304549

申请日：2023-04-21

Applicant: QUALCOMM Incorporated

Inventor： Chanchal Raj ,  Mayank Mishra ,  Pradeep Veeramalla ,  Sandeep Ramisetty

IPC: G06T7/262 ,  G06T7/13 ,  G06T7/246 ,  G06V10/70

CPC classification number: G06T7/262 ,  G06T7/13 ,  G06T7/248 ,  G06V10/70 ,  G06T2207/10016 ,  G06T2207/20048

Abstract: This disclosure provides systems, methods, and devices for image signal processing that support efficient motion estimation. In a first aspect, a method of image processing includes determining first and second sets of correlation parameters for respective first and second frames, generating a transform matrix indicating motion from the first frame to the second frame in accordance with the correlation parameters, and inverting the transform matrix to produce an inverted transform matrix. Other aspects and features are also claimed and described.

公开(公告)号：US20240346835A1

公开(公告)日：2024-10-17

申请号：US18755769

申请日：2024-06-27

Applicant: DESIGNOVEL

Inventor： Woo Sang SONG ,  Ki Young SHIN ,  Jian Ri LI

IPC: G06V20/62 ,  G06V10/70

CPC classification number: G06V20/62 ,  G06V10/70

Abstract: The present disclosure relates to a method of matching a text with a design performed by an apparatus for matching a text with a design. According to an embodiment of the present disclosure, the method may comprise acquiring an image from information including images and texts; learning features of the acquired image; extracting texts from the information and performing learning about a pair of an extracted text and the acquired image; extracting a trend word extracted at least a predetermined reference number of times among the extracted texts; performing learning about a pair of the trend word and the acquired image; and identifying a design feature matched with the trend word among learned features of the image.

公开(公告)号：US12118467B2

公开(公告)日：2024-10-15

申请号：US18223081

申请日：2023-07-18

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Shunpei Yamazaki ,  Daisuke Kubota ,  Yoshiaki Oikawa ,  Kensuke Yoshizumi

IPC: G06N3/08 ,  G06N5/04 ,  G06V10/70 ,  G06V10/82 ,  G06V20/59 ,  G06V40/16

CPC classification number: G06N3/08 ,  G06N5/04 ,  G06V10/70 ,  G06V10/82 ,  G06V20/597 ,  G06V40/171 ,  G06V40/176

Abstract: A reduction in concentration due to a change in an emotion is inhibited. A change in an emotion of the human is suitably reduced. Part (in particular, an eye or an eye and its vicinity) or the whole of a user's face is detected, a feature of the user's face is extracted from data on the detected part or whole of the face, and an emotion of the user is estimated from the extracted feature of the face. In the case where the estimated emotion is an emotion that might reduce concentration, for example, a stimulus is applied to the sense of sight, the sense of hearing, the sense of touch, the sense of smell, or the like of the user to recover the concentration of the user.

公开(公告)号：US12118445B1

公开(公告)日：2024-10-15

申请号：US16219713

申请日：2018-12-13

Applicant: Zoox, Inc.

Inventor： Sarah Tariq

IPC: G06K9/62 ,  B60K31/00 ,  G06N3/084 ,  G06N20/10 ,  G06T7/20 ,  G06T7/254 ,  G06T7/70 ,  G06V10/24 ,  G06V10/36 ,  G06V10/44 ,  G06V10/70 ,  G06V10/75

CPC classification number: G06N20/10 ,  B60K31/0008 ,  G06N3/084 ,  G06T7/20 ,  G06T7/254 ,  G06T7/70 ,  G06V10/243 ,  G06V10/36 ,  G06V10/44 ,  G06V10/454 ,  G06V10/70 ,  G06V10/755 ,  B60K2031/0016 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Techniques are disclosed for implementing a convolutional neural network that determines an offset field for deforming a kernel to be used in a convolution. The offset field is temporally-based, at least in part, on data generated at an earlier time. Furthermore, techniques are disclosed for using sensor data to train a neural network to learn shapes or configurations of such deformed kernels. The temporal-based deformable convolutions may be used for object identification, object matching, object classification, segmentation, and/or object tracking, in various examples.

公开(公告)号：US20240331872A1

公开(公告)日：2024-10-03

申请号：US18623075

申请日：2024-04-01

Applicant: Qure.ai Technologies Private Limited

Inventor： Charu Arora ,  Preetham Putha ,  Manoj Tadepalli

IPC: G16H50/30 ,  G06V10/25 ,  G06V10/26 ,  G06V10/70 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20

CPC classification number: G16H50/30 ,  G06V10/25 ,  G06V10/26 ,  G06V10/70 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G06V2201/031

Abstract: A system and a method for detection of a heart failure risk is disclosed. The system may comprise a processor and a memory. The system (101) may receive one or more target chest X-ray image of a user. The system (101) may analyze one or more target chest X-ray image to identify and enhance one or more visual parameters of one or more RoI's. The system (101) may perform an anatomical segmentation on the one or more ROI's to detect one or more medical abnormalities from a set of medical abnormalities using the trained artificial intelligence model. The system (101) may calculate a confidence score of the heart failure risk in real time using a set of parameters corresponding to the detected one or more medical abnormalities from the set of medical abnormalities and further detect the heart failure risk for the user based on the confidence score.