公开(公告)号：US20240333762A1

公开(公告)日：2024-10-03

申请号：US18192453

申请日：2023-03-29

Applicant: Cisco Technology, Inc.

Inventor： Tomas Sixta ,  Filip Srajer

IPC: H04L9/40 ,  G06F40/30 ,  G06V10/40

CPC classification number: H04L63/1483 ,  G06F40/30 ,  G06V10/40 ,  G06V2201/09

Abstract: In some aspects, the techniques described herein relate to a method for detecting malicious emails, the method including: receiving an email, wherein the email is associated with a markup payload; determining, based on the markup payload, text data associated with the email; determining, using the text data and a first machine learning model, a first representation of the email representing text associated with the email; rendering the email to generate image data that represents a rendering of the email; determining, using the image data and a second machine learning model, a second representation of the email that represents at least the rendering of the email; and determining a prediction for the email based on the first representation and the second representation, wherein the prediction represents whether the email is predicted to be malicious based on the first representation and the second representation.

公开(公告)号：US20240303442A1

公开(公告)日：2024-09-12

申请号：US18319214

申请日：2023-05-17

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Tom HIRSHBERG ,  Yonit HOFFMAN ,  Zvi FIGOV ,  Maayan YEDIDIA

IPC: G06F40/40 ,  G06V10/764 ,  G06V20/62 ,  G06V30/10

CPC classification number: G06F40/40 ,  G06V10/764 ,  G06V20/63 ,  G06V30/10 ,  G06V2201/07 ,  G06V2201/09

Abstract: Systems and method are provided for extracting and processing terms referenced in multimedia content with the use of different term extraction models to determine the relevance of categories to the referenced terms and to rank the categories by relative dominance for the multimedia content. The most dominant category for the multimedia content and/or particular segment(s) of the multimedia content can then be identified and used to link to supplemental content and/or to identify multimedia content related to topics of interest.

公开(公告)号：US20240290093A1

公开(公告)日：2024-08-29

申请号：US18173779

申请日：2023-02-23

Applicant: SIT Autonomous AG ,  Constructor Education and Research Genossenschaft

Inventor： Andrei Boiarov ,  Ilya Shimchik ,  Nikita Firsakov ,  Pavlo Bredikhin ,  Sergey Ulasen ,  Serg Bell ,  Stanislav Protasov ,  Nikolay Dobrovolskiy

IPC: G06V20/40 ,  G06V10/774 ,  G06V10/94 ,  G06V20/70

CPC classification number: G06V20/41 ,  G06V10/774 ,  G06V10/945 ,  G06V20/48 ,  G06V20/49 ,  G06V20/70 ,  G06V20/44 ,  G06V2201/09

Abstract: A system and method for performing brand detection in a video is disclosed herein. The method comprises receiving the video for performing the brand detection thereon; splitting the video for obtaining a plurality of video frames; performing an open set detection on each input video frame from the plurality of video frames, which comprises proposing one or more bounding boxes on the input video frames on regions of the video frame that potentially include brand media; cropping the one or more bounding boxes; providing the cropped bounding boxes to a classification module for obtaining embedding vectors corresponding to each of the cropped bounding boxes; and comparing the embedding vectors of the cropped bounding boxes with embedding vectors of one or more brand reference images provided by a user for computing instances of brand detection in each video frame of the plurality of video frames.

公开(公告)号：US20240278952A1

公开(公告)日：2024-08-22

申请号：US18571524

申请日：2022-02-08

Applicant: Siemens Aktiengesellschaft

Inventor： Annemarie Breu ,  Joseph Tylka ,  Baris Erol ,  Philip Gregor ,  Dominic Trinko

IPC: B65C9/06 ,  B65C9/04 ,  B65C9/40 ,  B65G43/08 ,  B65G47/244 ,  G06T7/00 ,  G06T7/73 ,  G06V10/764 ,  G06V10/771 ,  G06V10/774

CPC classification number: B65C9/06 ,  B65C9/04 ,  B65C9/40 ,  B65G43/08 ,  B65G47/244 ,  G06T7/001 ,  G06T7/74 ,  G06V10/764 ,  G06V10/771 ,  G06V10/774 ,  B65G2201/0235 ,  B65G2203/0225 ,  B65G2203/041 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V2201/09

Abstract: A computer-implemented method for automatically orienting product containers includes acquiring a reference product label image associated with a batch of product containers on a production line and using a trained deep learning model to compute a perceptual center of the reference product label image based on perceptually relevant label features of the reference product label image. A production line camera acquires an image slice of the respective product label of individual product containers in the batch of product containers. A rotation angle for rotating an individual product container is computed based on the acquired image slice of the respective product label and a label center determined based on the computed perceptual center of the reference product label image. The computed rotation angle is communicated to a controller to effect a rotation of the individual product container.

公开(公告)号：US20240273136A1

公开(公告)日：2024-08-15

申请号：US18643980

申请日：2024-04-23

Applicant: Snap Inc.

Inventor： Jonathan Brody

IPC: G06F16/58 ,  G06F16/9038 ,  G06F18/24 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N5/022 ,  G06T1/00 ,  G06V10/75 ,  G06V10/764 ,  G06V10/82 ,  H04N23/63

CPC classification number: G06F16/5866 ,  G06F16/9038 ,  G06F18/24 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06T1/0007 ,  G06V10/751 ,  G06V10/764 ,  G06V10/82 ,  H04N23/63 ,  G06N5/022 ,  G06V2201/09

Abstract: Systems, methods, devices, media, and computer-readable instructions are described for local image tagging and processing in a resource-constrained environment such as a mobile device. In some embodiments, characteristics associated with images are used to determine whether to store content (e.g., images and video clips) as ephemeral content or non-ephemeral content. Based on the determination, the image is stored in a non-ephemeral camera roll storage of the mobile device, or an ephemeral local application storage. Additional storage operations such as encryption or backup copying may additionally be determined and performed based on the analysis of the content. In some embodiments, such images may be indexed, sorted, and searched based on the image tagging operations used to characterize the content.

公开(公告)号：US12046033B2

公开(公告)日：2024-07-23

申请号：US17512345

申请日：2021-10-27

Applicant: Pinfinity, LLC

Inventor： Caleb John Paullus

IPC: G06V20/20 ,  G06T7/73 ,  G06T15/10 ,  G06T19/00

CPC classification number: G06V20/20 ,  G06T7/73 ,  G06T15/10 ,  G06T19/006 ,  G06T2215/16 ,  G06V2201/09

Abstract: Systems and methods disclosed in this application are directed to augmented reality for used with pin badges. Pin badges can be worn, held, or set within view of an AR device having a camera. The AR device sends images or video from its camera to a platform server that determines whether a pin badge exists in view of the camera. If a pin badge exists, it is identified and augmented reality imagery related to the pin badge is transmitted back to the AR device so that the AR device can incorporate that augmented reality imagery into a video stream from its camera as shown on its display.

公开(公告)号：US20240127266A1

公开(公告)日：2024-04-18

申请号：US18542074

申请日：2023-12-15

Applicant: SEPIO PRODUCTS PRIVATE LIMITED

Inventor： Murad Nathani ,  Paul Abner Noronha ,  Darshan Dhruman Gandhi ,  Dattaprasad Narayan Kamat

IPC: G06Q30/018 ,  G06F16/955 ,  G06V10/70

CPC classification number: G06Q30/0185 ,  G06F16/9566 ,  G06V10/70 ,  G06V2201/09

Abstract: The present disclosure relates to the field of product authentication and verification and discloses a system (100) and method (200) to authenticate a product. The system (100) comprises a memory (102), a scanning module (104), a product identification module (108), a first re-direction module (106) and a second re-direction module (110). The product identification module (108) detects a design printed on the packaging of products and identifies products based on pre-trained machine learning model and detected design. The scanning module (104) facilitates user to scan visual codes printed on products and extracts UIDs and verification URLs from scanned visual code. The first re-direction module (106) receives extracted UID and verification URL if product is identified and screens extracted URL to identify its authenticity. The second re-direction module (110) re-directs users to a third-party verification platform at the embedded URL for product verification if product is not identified.

公开(公告)号：US11924246B2

公开(公告)日：2024-03-05

申请号：US18104487

申请日：2023-02-01

Applicant: Proofpoint, Inc.

Inventor： Brian Sanford Jones ,  Zachary Mitchell Abzug ,  Jeremy Thomas Jordan ,  Giorgi Kvernadze ,  Dallan Quass

IPC: H04L9/40 ,  G06F16/51 ,  G06F16/955 ,  G06F18/21 ,  G06F18/213 ,  G06F21/56 ,  G06N3/08 ,  G06N20/00 ,  G06N20/10

CPC classification number: H04L63/1483 ,  G06F16/51 ,  G06F16/9566 ,  G06F18/213 ,  G06F18/217 ,  G06F21/56 ,  G06N3/08 ,  G06N20/00 ,  G06N20/10 ,  H04L63/1408 ,  H04L63/1416 ,  H04L63/1441 ,  G06V2201/09

Abstract: Aspects of the disclosure relate to detecting and identifying malicious sites using machine learning. A computing platform may receive a uniform resource locator (URL). The computing platform may parse and/or tokenize the URL to reduce the URL into a plurality of components. The computing platform may identify human-engineered features of the URL. The computing platform may compute a vector representation of the URL to identify deep learned features of the URL. The computing platform may concatenate the human-engineered features of the URL to the deep learned features of the URL, resulting in a concatenated vector representation. By inputting the concatenated vector representation of the URL to a URL classifier, the computing platform may compute a phish classification score. In response to determining that the phish classification score exceeds a first phish classification threshold, the computing platform may cause a cybersecurity server to perform a first action.

公开(公告)号：US11810344B2

公开(公告)日：2023-11-07

申请号：US17401814

申请日：2021-08-13

Applicant: NIKE, Inc.

Inventor： Jason Lee Ertle ,  Kevin L. Hofstee ,  Shane K. Luke

IPC: G06T7/73 ,  G06V20/10 ,  G06V10/28 ,  G06V10/44 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/141 ,  G06V10/143 ,  G06F18/243

CPC classification number: G06V20/10 ,  G06F18/2413 ,  G06T7/74 ,  G06V10/28 ,  G06V10/44 ,  G06V10/764 ,  G06F18/24323 ,  G06T2200/24 ,  G06V10/141 ,  G06V10/143 ,  G06V2201/09

Abstract: Systems and methods for predicting items within content and using improved, fine-grained image classification techniques to produce images used to identify consumer products in the real-world by allowing for the recognition of a product using an image captured under a variety of conditions and environments, such as angles, lighting, camera settings, and the like.

公开(公告)号：US11687865B2

公开(公告)日：2023-06-27

申请号：US17661929

申请日：2022-05-04

Applicant: Trax Technology Solutions Pte Ltd.

Inventor： Youval Bronicki

IPC: G06Q10/0639 ,  G06Q30/0208 ,  G06Q10/0631 ,  G06T7/70 ,  H04W4/029 ,  G06Q30/02 ,  G06Q30/0601 ,  G06T7/73 ,  G06N5/04 ,  G06Q30/0201 ,  G01G19/52 ,  G06Q10/0637 ,  G06T7/50 ,  G06T7/00 ,  G06Q30/018 ,  H04L67/303 ,  G06V20/10 ,  G06V20/20 ,  G06V20/52 ,  G06T7/80 ,  H04W4/024 ,  G06N20/00 ,  G01C21/20 ,  G05D1/02 ,  G06F18/25 ,  G06F18/20 ,  G06F18/2431 ,  G06V10/82 ,  G06V20/00 ,  G06Q10/087 ,  H04N7/18 ,  G01G19/14 ,  A47L11/40 ,  G01G23/18 ,  G01J1/42 ,  G01L1/00

CPC classification number: G06Q10/06395 ,  G01C21/206 ,  G01G19/52 ,  G05D1/0219 ,  G05D1/0246 ,  G06F18/2431 ,  G06F18/253 ,  G06F18/285 ,  G06N5/04 ,  G06N20/00 ,  G06Q10/0639 ,  G06Q10/06311 ,  G06Q10/06315 ,  G06Q10/06375 ,  G06Q30/018 ,  G06Q30/0201 ,  G06Q30/0208 ,  G06Q30/0281 ,  G06Q30/0601 ,  G06Q30/0609 ,  G06Q30/0623 ,  G06Q30/0639 ,  G06Q30/0643 ,  G06T7/0002 ,  G06T7/50 ,  G06T7/70 ,  G06T7/73 ,  G06T7/80 ,  G06T7/97 ,  G06V10/82 ,  G06V20/10 ,  G06V20/20 ,  G06V20/36 ,  G06V20/52 ,  H04L67/303 ,  H04W4/024 ,  H04W4/029 ,  A47L11/4011 ,  A47L2201/04 ,  G01G19/14 ,  G01G23/18 ,  G01J1/4204 ,  G01L1/00 ,  G05D2201/0203 ,  G06Q10/087 ,  G06Q30/0633 ,  G06T2207/30242 ,  G06V2201/09 ,  H04N7/188

Abstract: A method for reacting to changes of items hanging on peg-hooks connected to pegboards may include: determining a location of a store shelf within a retail store; obtaining a first coverage parameter corresponding to a first product type and a second coverage parameter corresponding to a second product type; accessing a database to determine a first height of products of the first product type and a second height of products of the second product type; determining a position for placing a camera configured to capture images of at least a portion of the store shelf by analyzing the location of the store shelf, the first coverage parameter, the second coverage parameter, the first height, and the second height; and providing, to a user interface of a user device, information relating to the determined position of the camera.