公开(公告)号：US12112572B2

公开(公告)日：2024-10-08

申请号：US17106900

申请日：2020-11-30

申请人： Rovi Guides, Inc.

发明人： Gyanveer Singh ,  Charishma Chundi ,  Sriram Ponnuswamy

IPC分类号： G06V40/16 ,  G06N20/00 ,  G06V20/00 ,  G06V20/40 ,  H04L67/55 ,  H04N21/454 ,  H04N21/488

CPC分类号： G06V40/172 ,  G06N20/00 ,  G06V20/35 ,  G06V20/41 ,  G06V40/174 ,  H04L67/55 ,  H04N21/4542 ,  H04N21/4882

摘要： Systems and methods for warning a user that media assets associated with another user depict the user with an undesired expression are provided. A plurality of media assets associated with a first user and depicting a second user may be identified. A set of expressions of the second user that the second user has indicated as undesirable may be retrieved. The depictions of the second user in the plurality of media assets and the expressions that the second user has indicated are undesirable may be compared. If it is determined that one or more of the media assets depict the second user with an undesirable expression, a notification may be generated to the second user indicating that one or more media assets of the first user depict the second user with an expression that the second user has indicated as undesirable.

公开(公告)号：US20240290092A1

公开(公告)日：2024-08-29

申请号：US18688741

申请日：2022-06-16

申请人： SHANGHAI BILIBILI TECHNOLOGY CO., LTD.

发明人： Cong RAO ,  Xinbo WANG ,  Ziyi SHEN

IPC分类号： G06V20/00 ,  G06V10/762 ,  G06V10/764

CPC分类号： G06V20/35 ,  G06V10/762 ,  G06V10/764

摘要： This application provides an image scene recognition method and apparatus. The image scene recognition method includes: obtaining a to-be-recognized image, inputting the to-be-recognized image into a target visual element detection model and determining at least one target visual element comprised in the to-be-recognized image by the target visual element detection model, and inputting the at least one target visual element into a scene recognition model and generating a scene category corresponding to the to-be-recognized image by the scene recognition model. In this way, a bottom-up scene recognition method is used to infer, based on microscopic visual elements, a macroscopic scene category in which the microscopic visual elements may coexist, thereby implementing scene recognition, and greatly improving recognition precision and accuracy during image scene recognition.

公开(公告)号：US12067774B2

公开(公告)日：2024-08-20

申请号：US18341528

申请日：2023-06-26

申请人： Procore Technologies, Inc.

发明人： Florian Winterstein ,  Raf Colasante

IPC分类号： G06V20/20 ,  G06F40/205 ,  G06F40/295 ,  G06T7/00 ,  G06V20/00 ,  G10L15/26

CPC分类号： G06V20/20 ,  G06F40/205 ,  G06F40/295 ,  G06T7/0004 ,  G06V20/35 ,  G10L15/26

摘要： In order to improve a user's task of documenting items that are identified by the user while at a construction site, a computing system may be configured to (i) receive, from a first client station associated with a first user, media content that is descriptive of a given on-site item of a construction site, (ii) apply a speech recognition technique to transcribe audio data included in the media content into text that is descriptive of the given on-site item, (iii) generate a data record for the given on-site item, (iv) pre-populate at least a portion of the transcribed text into one or more fields of the data record for the given on-site item, and (v) cause a second client station to display the data record to a second user for review.

公开(公告)号：US12056925B2

公开(公告)日：2024-08-06

申请号：US17299188

申请日：2019-01-15

申请人： Google LLC

发明人： Ryan Geiss ,  Ruiduo Yang ,  Marc Levoy

IPC分类号： G06K9/62 ,  G06N20/00 ,  G06V10/56 ,  G06V20/00 ,  H04N23/80

CPC分类号： G06V20/35 ,  G06N20/00 ,  G06V10/56 ,  H04N23/80 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Apparatus and methods related to photography are provided. A computing device can receive an input image. An object detector of the computing device can determine an object region of interest of the input image that is associated with an object detected in the input image. A trained machine learning algorithm can determine an output photographic region of interest for the input image based on the object region of interest and the input image. The machine learning algorithm can be trained to identify an output photographic region of interest that is suitable for use by a photographic function for image generation. The computing device can generate an output related to the output photographic region of interest.

公开(公告)号：US12026863B2

公开(公告)日：2024-07-02

申请号：US17230169

申请日：2021-04-14

申请人： Huawei Technologies Co., Ltd.

发明人： Yu Li ,  Feilong Ma ,  Tizheng Wang ,  Xiujie Huang

IPC分类号： G06T7/194 ,  G06F18/214 ,  G06N3/08 ,  G06T5/20 ,  G06T5/70 ,  G06T5/94 ,  G06V20/00 ,  H04N5/262 ,  H04N23/61

CPC分类号： G06T5/94 ,  G06F18/214 ,  G06N3/08 ,  G06T5/20 ,  G06T5/70 ,  G06T7/194 ,  G06V20/35 ,  H04N5/2621 ,  H04N23/61

摘要： An image processing method includes determining a target area and a background area in an image by performing mask segmentation on the image. Different color processing modes are applied to the target area and the background area, so that luminance of the target area is greater than luminance of the background area, or chrominance of the target area is greater than chrominance of the background area, and a main object corresponding to the target area is more prominently highlighted.

公开(公告)号：US11954142B2

公开(公告)日：2024-04-09

申请号：US18323796

申请日：2023-05-25

申请人： Snow Corporation

发明人： Junghwan Jin ,  Sungwook Kim ,  Sangho Choi ,  Byung-Sun Park ,  Wonhyo Yi ,  Seongyeop Jeong ,  Noah Hahm ,  Jimin Kim ,  Hyeongbae Shin

IPC分类号： G06F16/438 ,  G06N20/00 ,  G06V20/00 ,  G06V20/40

CPC分类号： G06F16/4393 ,  G06N20/00 ,  G06V20/35 ,  G06V20/41 ,  G06V20/47

摘要： A method and a system for producing a story video are provided. A method for producing a story video, according to one embodiment, can produce a specific story video by determining a theme of a story that is suitable for collected videos and selecting and arranging an appropriate video for each frame of a template associated with the theme.

公开(公告)号：US11876941B1

公开(公告)日：2024-01-16

申请号：US17540726

申请日：2021-12-02

申请人： Pipbin, inc.

发明人： Maximillian John Suiter ,  Sean Patrick Suiter ,  Ian Padraic Suiter ,  Valerie Michele Morrison ,  Scott David Morrison

IPC分类号： H04N1/21 ,  H04N1/00 ,  G06F16/78 ,  G06F3/01 ,  G06F3/04817 ,  H04W4/02 ,  G06T19/00 ,  G06Q30/08 ,  G06Q30/0601 ,  G06F40/169 ,  G06V20/20 ,  G06V20/00 ,  H04N23/63

CPC分类号： H04N1/2125 ,  G06F3/011 ,  G06F3/04817 ,  G06F16/78 ,  G06F40/169 ,  G06Q30/0639 ,  G06Q30/08 ,  G06T19/006 ,  G06V20/20 ,  G06V20/35 ,  H04N1/00244 ,  H04N1/212 ,  H04N23/63 ,  H04W4/025 ,  H04N23/633 ,  H04N2201/0084

摘要： A system for collection and distribution of curated tagged content includes a server or collection of servers in communication with one or more networks. The servers receive moment files generated by recording users via recording devices; each moment file is associated with a tagged object (e.g., physical or virtual) and includes associated media content. Each moment file is associated with recorder-side filtering via which a potential reader may be defined as an eligible or ineligible reader of the moment file. The server stores the received moment files to memory and receives indications of reading devices near an associated tagged object. The server receives indications of reading devices near a tagged object associated with a moment file; for those reading users determined eligible to read a moment file, the server forwards to their associated reading devices associated media content for display in response to engagement by the reading user.

公开(公告)号：US20240004497A1

公开(公告)日：2024-01-04

申请号：US18466701

申请日：2023-09-13

申请人： GoPro, Inc

发明人： Sylvain Leroy

IPC分类号： G06F3/041 ,  G06T7/90 ,  G06V20/00 ,  H04N23/51 ,  H04N23/54 ,  H04N23/55 ,  H04N23/63

CPC分类号： G06F3/0418 ,  G06T7/90 ,  G06V20/35 ,  H04N23/51 ,  H04N23/54 ,  H04N23/55 ,  H04N23/631

摘要： An image capture device may include a touchscreen display, which may be used to receive user input. The image capture device may determine whether it is under water based on analysis of visual content captured by the image capture device. Responsive to determination that it is under water, the image capture device may change operation with respect to the touchscreen display.

公开(公告)号：US11841922B2

公开(公告)日：2023-12-12

申请号：US17330135

申请日：2021-05-25

申请人： Awoo Intelligence, Inc.

发明人： Szu-Wu Lin ,  Gang-Feng Ho ,  Kuo Ming Lin

IPC分类号： G06V20/70 ,  G06F18/214 ,  G06V10/40 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/774 ,  G06V20/00

CPC分类号： G06F18/214 ,  G06F18/2413 ,  G06V10/40 ,  G06V10/764 ,  G06V10/774 ,  G06V20/35 ,  G06V20/70

摘要： Method and system for classifying and labeling images, which can perform segmentation based on features of each part of images, classify and match the image and the segmented image based on a classification model built by the machine learning method. Meanwhile, each image is assigned with labels and text descriptions. The system also includes a string module assigning the image with a plurality of matching labels and text descriptions that are the most relevant in recent times. Furthermore, the classification model is trained by machine learning method such as an unsupervised learning, a self-supervised learning, or a heuristic algorithms. In addition, a character recognition module is provided to extract characters in the image for comprehensive learning and calculations to facilitate classification and labeling of the image.

公开(公告)号：US11816887B2

公开(公告)日：2023-11-14

申请号：US16984934

申请日：2020-08-04

申请人： FISHER-ROSEMOUNT SYSTEMS, INC.

发明人： Yicheng Peter Pan ,  Anna Velena ,  David R. Denison ,  Manikandan Nambiar ,  Kuo-Lung Chin ,  Guido Maria Re

IPC分类号： G06V20/20 ,  G06K7/14 ,  G06T19/00 ,  G06N20/00 ,  G06V20/00

CPC分类号： G06V20/20 ,  G06K7/1417 ,  G06N20/00 ,  G06T19/003 ,  G06T19/006 ,  G06V20/35

摘要： An augmented reality (AR) node location and activation technique for use in an AR system in a process plant or other field environment quickly and easily detects an AR node in a real-world environment and is then able to activate an AR scene within the AR system, which improves the usability and user experience of the AR system. The AR node location and activation system generally enables users to connect to and view an AR scene within an AR system or platform even when the user is not directly at an existing AR node, when the user is experiencing poor lighting conditions in the real-world environment and in situations in which the user is unfamiliar with the AR nodes that are in the AR system database. As a result, the user can quickly and easily activate the AR system and connect to an AR scene for an AR node close to the user in the field environment under varying weather and lighting conditions in the field and without requiring a large amount of image processing to locate the correct AR scene based on photographic images provided by the user.