公开(公告)号：US20240169502A1

公开(公告)日：2024-05-23

申请号：US18058630

申请日：2022-11-23

申请人： Adobe Inc.

发明人： Scott Cohen ,  Zhe Lin ,  Zhihong Ding ,  Luis Figueroa ,  Kushal Kafle

IPC分类号： G06T5/00 ,  G06F3/04842 ,  G06F3/04845 ,  G06T3/20 ,  G06V10/70 ,  G06V10/86

CPC分类号： G06T5/005 ,  G06F3/04842 ,  G06F3/04845 ,  G06T3/20 ,  G06V10/768 ,  G06V10/86 ,  G06T2200/24 ,  G06T2207/20084 ,  G06T2207/20104

摘要： The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For instance, in one or more embodiments, the disclosed systems detect, via a graphical user interface of a client device, a user selection of an object portrayed within a digital image. The disclosed systems determine, in response to detecting the user selection of the object, a relationship between the object and an additional object portrayed within the digital image. The disclosed systems receive one or more user interactions for modifying the object. The disclosed systems modify the digital image in response to the one or more user interactions by modifying the object and the additional object based on the relationship between the object and the additional object.

公开(公告)号：US20240029422A1

公开(公告)日：2024-01-25

申请号：US17871335

申请日：2022-07-22

申请人： Robert Bosch GmbH

发明人： Ehsan QASEMI ,  Alessandro OLTRAMARI

IPC分类号： G06V10/94 ,  G06V10/764 ,  G06V20/40 ,  G06V20/52 ,  H04N7/18 ,  G06V10/86 ,  G06F40/20

CPC分类号： G06V10/945 ,  G06V10/764 ,  G06V20/41 ,  G06V20/52 ,  H04N7/183 ,  G06V10/86 ,  G06F40/20 ,  G06V2201/07 ,  G08G1/0125

摘要： A human-assisted neuro-symbolic system for outputting fine-grained classifications and corresponding images or video of a desired object or scene. The system includes one or more cameras configured to generate a video feed of a scene. One or more processors are programmed to generate video analytics data from the video feed, including coarse-grained classification data regarding one or more objects in the scene. A knowledge graph is built with instantiated (e.g., time-based) domain ontology of the one or more objects in the scene. The domain ontology can be augmented via human-in-the-loop. Once augmented, the knowledge graph can be infused into a deep learning model, such as a natural language model. An input (e.g., in natural language) can seek fine-grained input characteristics, and the deep learning model infused with the knowledge graph retrieves a corresponding portion of the video feed with the fine-grained input characteristics.

公开(公告)号：US20240013768A1

公开(公告)日：2024-01-11

申请号：US17810765

申请日：2022-07-05

申请人： Capital One Services, LLC

发明人： Michael MOSSOBA ,  Abdelkader M'Hamed BENKREIRA ,  Noel LYLES ,  Joshua EDWARDS

IPC分类号： G10L13/047 ,  G06V10/764 ,  G06T7/194 ,  G06V10/86 ,  G10L13/08 ,  G09B21/00

CPC分类号： G10L13/047 ,  G06V10/764 ,  G06T7/194 ,  G06V10/86 ,  G10L13/08 ,  G09B21/006

摘要： In some implementations, a browser extension may receive a setting indicating a level of verbosity and may receive an image and a set of words associated with the image. The browser extension may identify a foreground of the image and a background of the image and may identify, within the foreground of the image, a set of objects. The browser extension may rank the set of objects based on one or more properties of the set of objects and the set of words and may select a subset of objects from the set of objects based on the setting and the ranking. Accordingly, the browser extension may generate descriptions of the selected subset of objects based on the setting and may input the generated descriptions to a text to speech algorithm.

公开(公告)号：US11783584B2

公开(公告)日：2023-10-10

申请号：US17691526

申请日：2022-03-10

申请人： Adobe Inc.

发明人： Niyati Himanshu Chhaya ,  Tripti Shukla ,  Jeevana Kruthi Karnuthala ,  Bhanu Prakash Reddy Guda ,  Ayudh Saxena ,  Abhinav Bohra ,  Abhilasha Sancheti ,  Aanisha Bhattacharyya

IPC分类号： G06V20/40 ,  G06N20/00 ,  G06F16/73 ,  G06V10/86 ,  G06F40/166

CPC分类号： G06V20/47 ,  G06F16/73 ,  G06F40/166 ,  G06N20/00 ,  G06V10/86 ,  G06V20/41

摘要： Techniques are described that support automated generation of a digital document from digital videos using machine learning. The digital document includes textual components that describe a sequence of entity and action descriptions from the digital video. These techniques are usable to generate a single digital document based on a plurality of digital videos as well as incorporate user-specified constraints in the generation of the digital document.

公开(公告)号：US20230282245A1

公开(公告)日：2023-09-07

申请号：US18103101

申请日：2023-01-30

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Mikita DVORNIK ,  Isma Hadji ,  Allan Douglas Jepson

IPC分类号： G11B27/34 ,  G06F16/732 ,  G11B27/10 ,  G06V20/40 ,  G06V10/86

CPC分类号： G11B27/34 ,  G06F16/7328 ,  G11B27/102 ,  G06V20/44 ,  G06V10/86

摘要： A first graph which is a flow graph is converted into a second graph using a first algorithm. The second graph, combined with a second algorithm using a dynamic programming recursion, is compared with a video and a best matching thread, with respect to the video, is found through the second graph. The best matching thread may then be used for a user-assistance function. The dynamic programming recursion reduces computational effort needed by the computer performing the matching.

公开(公告)号：US20230281999A1

公开(公告)日：2023-09-07

申请号：US18188701

申请日：2023-03-23

申请人： NEC Laboratories America, Inc.

发明人： Samuel Schulter ,  Sparsh Garg

IPC分类号： G06V20/54 ,  G06V20/70 ,  G06V10/774 ,  G06V10/26 ,  G06V10/74 ,  G06V10/86 ,  G08G1/16 ,  G08G1/09

CPC分类号： G06V20/54 ,  G06V20/70 ,  G06V10/774 ,  G06V10/26 ,  G06V10/761 ,  G06V10/86 ,  G08G1/16 ,  G08G1/09 ,  G06V10/82

摘要： Methods and systems identifying road hazards include capturing an image of a road scene using a camera. The image is embedded using a segmentation model that includes an image branch having an image embedding layer that embeds images into a joint latent space and a text branch having a text embedding layer that embeds text into the joint latent space. A mask is generated for an object within the image using the segmentation model. A probability is determined that the object matches a road hazard using the segmentation mode. A signal is generated responsive to the probability to ameliorate a danger posed by the road hazard.

公开(公告)号：US20230215135A1

公开(公告)日：2023-07-06

申请号：US18009160

申请日：2020-06-10

申请人： NEC Corporation

发明人： Ryo KAWAI ,  Noboru YOSHIDA ,  Yadong PAN ,  Shoji NISHIMURA ,  Jianquan LIU

IPC分类号： G06V10/74 ,  G06V40/10 ,  G06V10/94 ,  G06V10/86 ,  G06F16/58 ,  G06F16/535

CPC分类号： G06V10/761 ,  G06V40/10 ,  G06V10/945 ,  G06V10/86 ,  G06F16/5866 ,  G06F16/535 ,  G06V20/50

摘要： The present invention provides an image processing apparatus (100) including an image acquisition unit (101) that acquires a query image, based on an input keyword, a skeleton structure detection unit (102) that detects a two-dimensional skeleton structure of a person included in the query image, a feature value computation unit (103) that computes a feature value of the detected two-dimensional skeleton structure, and a search unit (105) that searches, based on a degree of similarity of the computed feature value, for an analysis target image including a person in a state similar to a state of a person included in the query image from the analysis target image.

公开(公告)号：US20240311990A1

公开(公告)日：2024-09-19

申请号：US18601083

申请日：2024-03-11

申请人： Pilz GmbH & Co. KG

发明人： Florian ROTZINGER

IPC分类号： G06T7/00 ,  G05B19/042 ,  G06T7/70 ,  G06V10/75 ,  G06V10/764 ,  G06V10/86 ,  G06V20/50 ,  H04N7/18

CPC分类号： G06T7/0002 ,  G05B19/0428 ,  G06T7/70 ,  G06V10/75 ,  G06V10/764 ,  G06V10/86 ,  G06V20/50 ,  H04N7/183 ,  G05B2219/24024 ,  G06T2207/30242 ,  G06V2201/02

摘要： A method for detecting a configuration of a modular safety controller includes generating a digital image of a module block of the modular safety controller, and evaluating the digital image with an evaluation device using image recognition. A logic code is generated which is compared with a plurality of configuration codes in order to determine the current configuration of the modular safety controller.

公开(公告)号：US20240303977A1

公开(公告)日：2024-09-12

申请号：US18443381

申请日：2024-02-16

申请人： Keyence Corporation

发明人： Yasuhisa IKUSHIMA

IPC分类号： G06V10/776 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V10/86 ,  G06V10/94 ,  G06V20/50

CPC分类号： G06V10/776 ,  G06V10/764 ,  G06V10/774 ,  G06V10/86 ,  G06V10/945 ,  G06V20/50 ,  G06V10/82

摘要： A processor: executes classification of classifying a plurality of validation images into a plurality of classes with a machine learning model trained with a plurality of training images; obtains a degree of separation between the plurality of classes by the classification of the plurality of validation images and evaluates accuracy of the classification of the plurality of validation images based on the obtained degree of separation between the plurality of classes; and evaluates whether re-training of the machine learning model is necessary based on an evaluation result of the accuracy of classification of the plurality of validation images, extracts an validation image whose classification result has a relatively high possibility to be erroneous from among the plurality of validation images to automatically re-train the machine learning model if it is evaluated that the re-training of the machine learning model is necessary.

公开(公告)号：US20240303959A1

公开(公告)日：2024-09-12

申请号：US18120404

申请日：2023-03-12

申请人： ZAZZLE INC.

发明人： Robert I. Beaver, III ,  Leslie Young Harvill ,  Matthew DiFonzo ,  Brent Burgess

IPC分类号： G06V10/44 ,  G06Q30/0601 ,  G06T11/60 ,  G06V10/75 ,  G06V10/86 ,  G06V20/30

CPC分类号： G06V10/443 ,  G06Q30/0621 ,  G06Q30/0629 ,  G06Q30/0643 ,  G06T11/60 ,  G06V10/751 ,  G06V10/86 ,  G06V20/30 ,  G06Q10/103 ,  G06Q30/0639 ,  G06Q50/01

摘要： In some embodiments, a computer-implemented method comprises: preloading and updating, on a user device, a set of graphs of transform invariant features product-token pairs (GTIF product-token pairs); wherein the set of GTIF product-token pairs comprises one or more of: a pair comprising a known GTIF product-token and a location data determined for a location of a user device, or others; receiving, using a client application executing on the user device, a user request for additional contents related to an object; constructing, for the object, an object GTIF product-token capturing transform invariant features identified for the object; determining whether the object GTIF product-token matches a particular pair of the set of GTIF product-token pairs; in response to determining that the object GTIF product-token matches the particular pair, determining particular additional content based on the particular pair, and displaying the particular additional content on the user device.