Patents by Inventor Stamatios Georgoulis

Stamatios Georgoulis has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12073322
    Abstract: A computer-implemented method for training a classifier (??), including: training a pretext model (??) to learn a pretext task, so as to minimize a distance between an output of a source sample via the pretext model (??) and an output of a corresponding transformed sample via the pretext model (??), the transformed sample being a sample obtained by applying a transformation (T) to the source sample; S20) determining a neighborhood (NXi) of samples (Xi) of a dataset (SD) in the embedding space; S30) training the classifier (??) to predict respective estimated probabilities ??j(Xi), j=1 . . . C, for a sample (Xi) to belong to respective clusters (Cj), by using a second training criterion which tends to: maximize a likelihood for a sample and its neighbors (Xj) of its neighborhood (Nxi) to belong to the same cluster; and force the samples to be distributed over several clusters.
    Type: Grant
    Filed: May 21, 2021
    Date of Patent: August 27, 2024
    Assignees: TOYOTA JIDOSHA KABUSHIKI KAISHA, KATHOLIEKE UNIVERSITEIT LEUVEN
    Inventors: Wim Abbeloos, Gabriel Othmezouri, Wouter Van Gansbeke, Simon Vandenhende, Marc Proesmans, Stamatios Georgoulis, Luc Van Gool
  • Patent number: 12062160
    Abstract: A system for image completion is disclosed. The system comprises a coordinate generation module configured to receive past frames and a present frame having a first field-of-view and to generate a set of coordinate maps, one for each of the received past frames; and a frame aggregation module configured to receive as input the past frames, the present frame, and the coordinate maps and to synthesize, based on said input, a present frame having a second field-of-view.
    Type: Grant
    Filed: September 17, 2021
    Date of Patent: August 13, 2024
    Assignees: TOYOTA JIDOSHA KABUSHIKI KAISHA, KATHOLIEKE UNIVERSITEIT LEUVEN, ETH ZURICH
    Inventors: Wim Abbeloos, Gabriel Othmezouri, Liqian Ma, Stamatios Georgoulis, Luc Van Gool
  • Patent number: 11669607
    Abstract: A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document and using automated verification of identification documents. Identification documents may be authenticated by validating security features. The system may determine features expected in a valid identification document and determine whether those features are present, employing techniques, such as determining whether direction-sensitive features are present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks.
    Type: Grant
    Filed: August 28, 2020
    Date of Patent: June 6, 2023
    Assignee: PXL Vision AG
    Inventors: Mikhail Vorobiev, Nevena Shamoska, Magdalena Polac, Benjamin Fankhauser, Michael Goettlicher, Marcus Hudritsch, Suman Saha, Stamatios Georgoulis, Luc van Gool
  • Patent number: 11443559
    Abstract: A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document, using automated verification of identification documents and detection that a live person identified by the document is present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks. The deep learning model may be trained using training data extracted from facial feature locations of training images.
    Type: Grant
    Filed: August 28, 2020
    Date of Patent: September 13, 2022
    Assignee: PXL Vision AG
    Inventors: Mikhail Vorobiev, Nevena Shamoska, Magdalena Polac, Benjamin Fankhauser, Michael Goettlicher, Marcus Hudritsch, Stamatios Georgoulis, Suman Saha, Luc van Gool
  • Publication number: 20220092746
    Abstract: A system for image completion is disclosed. The system comprises a coordinate generation module configured to receive past frames and a present frame having a first field-of-view and to generate a set of coordinate maps, one for each of the received past frames; and a frame aggregation module configured to receive as input the past frames, the present frame, and the coordinate maps and to synthesize, based on said input, a present frame having a second field-of-view.
    Type: Application
    Filed: September 17, 2021
    Publication date: March 24, 2022
    Inventors: Wim ABBELOOS, Gabriel OTHMEZOURI, Liqian MA, Stamatios GEORGOULIS, Luc VAN GOOL
  • Publication number: 20210365735
    Abstract: A computer-implemented method for training a classifier (??), including: training a pretext model (??) to learn a pretext task, so as to minimize a distance between an output of a source sample via the pretext model (??) and an output of a corresponding transformed sample via the pretext model (??), the transformed sample being a sample obtained by applying a transformation (T) to the source sample; S20) determining a neighborhood (NXi) of samples (Xi) of a dataset (SD) in the embedding space; S30) training the classifier (??) to predict respective estimated probabilities ??j(Xi), j=1 . . . C, for a sample (Xi) to belong to respective clusters (Cj), by using a second training criterion which tends to: maximize a likelihood for a sample and its neighbors (Xj) of its neighborhood (Nxi) to belong to the same cluster; and force the samples to be distributed over several clusters.
    Type: Application
    Filed: May 21, 2021
    Publication date: November 25, 2021
    Applicants: Toyota Jidosha Kabushiki Kaisha, Katholieke Universiteit Leuven
    Inventors: Wim Abbeloos, Gabriel Othmezouri, Wouter Van Gansbeke, Simon Vandenhende, Marc Proesmans, Stamatios Georgoulis, Luc Van Gool
  • Publication number: 20210064900
    Abstract: A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document and using automated verification of identification documents. Identification documents may be authenticated by validating security features. The system may determine features expected in a valid identification document and determine whether those features are present, employing techniques, such as determining whether direction-sensitive features are present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks.
    Type: Application
    Filed: August 28, 2020
    Publication date: March 4, 2021
    Inventors: Mikhail Vorobiev, Nevena Shamoska, Magdalena Polac, Benjamin Fankhauser, Michael Goettlicher, Marcus Hudritsch, Suman Saha, Stamatios Georgoulis, Luc van Goo
  • Publication number: 20210064901
    Abstract: A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document, using automated verification of identification documents and detection that a live person identified by the document is present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks. The deep learning model may be trained using training data extracted from facial feature locations of training images.
    Type: Application
    Filed: August 28, 2020
    Publication date: March 4, 2021
    Inventors: Mikhail Vorobiev, Nevena Shamoska, Magdalena Polac, Benjamin Fankhauser, Michael Goettlicher, Marcus Hudritsch, Stamatios Georgoulis, Suman Saha, Luc van Gool