WO2024134433 - HYBRID MACHINE LEARNING ARCHITECTURE FOR VISUAL CONTENT PROCESSING AND USES THEREOF
National phase entry is expected:
Publication Number
WO/2024/134433
Publication Date
27.06.2024
International Application No.
PCT/IB2023/062807
International Filing Date
15.12.2023
Title **
[English]
HYBRID MACHINE LEARNING ARCHITECTURE FOR VISUAL CONTENT PROCESSING AND USES THEREOF
[French]
ARCHITECTURE D'APPRENTISSAGE MACHINE HYBRIDE POUR TRAITEMENT DE CONTENU VISUEL ET SES UTILISATIONS
Applicants **
LUMANA INC.
Inventors
MULLA, Ofir
ROTSTEIN, Noam
BRACHA, Amit
KIMMEL, Ron
ZABATANI, Aviad
SLOSSBERG, Ron
BEN MOSHE, Sagi
Priority Data
18/145,301
22.12.2022
US
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
ILPO
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| Translation |
|
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing, Examination, Granting | 2239 | |
| EPO | Filing, Examination, Granting | 13650 | |
| Japan | Filing, Examination, Granting | 2279 | |
| South Korea | Filing, Examination, Granting | 2403 | |
| USA | Filing, Examination, Granting | 5340 |
Total:
25,911
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Contact Us
Abstract[English]
Systems and methods for visual content processing. A method includes obtaining a subset of media content selected based on outputs of a first machine learning model, wherein the first machine learning model is produced by training a student model using outputs of a teacher model, wherein the outputs of the first machine learning model include a plurality of first predictions for a plurality of portions of the media content; and applying a second machine learning model to the obtained subset of media content, wherein the second machine learning model outputs a plurality of second predictions for respective portions of the plurality of portions, wherein a domain used by the first machine learning model is a subset of a domain used by the second machine learning model.[French]
L'invention concerne des systèmes et des procédés de traitement de contenu visuel. Un procédé consiste à obtenir un sous-ensemble de contenu multimédia sélectionné sur la base de sorties d'un premier modèle d'apprentissage machine, le premier modèle d'apprentissage machine étant produit par entraînement d'un modèle étudiant à l'aide de sorties d'un modèle enseignant, les sorties du premier modèle d'apprentissage machine comprenant une pluralité de premières prédictions pour une pluralité de parties du contenu multimédia ; et à appliquer un second modèle d'apprentissage machine au sous-ensemble obtenu de contenu multimédia, le second modèle d'apprentissage machine délivrant une pluralité de secondes prédictions pour des parties respectives de la pluralité de parties, un domaine utilisé par le premier modèle d'apprentissage machine étant un sous-ensemble d'un domaine utilisé par le second modèle d'apprentissage machine.