Patents Assigned to Clearview AI, Inc.
  • METHODS FOR PROVIDING INFORMATION ABOUT A PERSON BASED ON FACIAL RECOGNITION
    Publication number: 20250200157
    Abstract: This disclosure provides methods for providing information about a person based on facial recognition and various applications thereof, including face-based check-in, face-based personal identification, face-based identification verification, face-based background checks, facial data collaborative network, correlative face search, and personal face-based identification. The disclosed methods are able to provide accurate information about a person in a real-time manner.
    Type: Application
    Filed: June 21, 2024
    Publication date: June 19, 2025
    Applicant: Clearview AI, Inc.
    Inventor: Cam-Hoan Ton-That
  • Methods and systems for indexing embedding vectors representing disjoint classes at above-billion scale for fast high-recall retrieval
    Patent number: 12315220
    Abstract: This disclosure provides novel methods and systems for indexing embedding vectors representing disjoint classes at above-billion scale for fast high-recall retrieval. The disclosed methods and systems solved above-billion scale image (e.g., face image) search problems by building a new vector database, the new Nearest Neighbor Database (NNDB) based on a novel architecture for indexing vectors.
    Type: Grant
    Filed: June 27, 2023
    Date of Patent: May 27, 2025
    Assignee: Clearview AI, Inc.
    Inventor: Zhi Liu
  • METHODS AND SYSTEMS FOR INDEXING EMBEDDING VECTORS REPRESENTING DISJOINT CLASSES AT ABOVE-BILLION SCALE FOR FAST HIGH-RECALL RETRIEVAL
    Publication number: 20250005896
    Abstract: This disclosure provides novel methods and systems for indexing embedding vectors representing disjoint classes at above-billion scale for fast high-recall retrieval. The disclosed methods and systems solved above-billion scale image (e.g., face image) search problems by building a new vector database, the new Nearest Neighbor Database (NNDB) based on a novel architecture for indexing vectors.
    Type: Application
    Filed: June 27, 2023
    Publication date: January 2, 2025
    Applicant: Clearview AI, Inc.
    Inventor: Zhi Liu
  • Methods for providing information about a person based on facial recognition
    Patent number: 12050673
    Abstract: This disclosure provides methods for providing information about a person based on facial recognition and various applications thereof, including face-based check-in, face-based personal identification, face-based identification verification, face-based background checks, facial data collaborative network, correlative face search, and personal face-based identification. The disclosed methods are able to provide accurate information about a person in a real-time manner.
    Type: Grant
    Filed: January 3, 2022
    Date of Patent: July 30, 2024
    Assignee: Clearview AI, Inc.
    Inventor: Cam-Hoan Ton-That
  • Efficient distributed trainer with gradient accumulation on sampled weight for deep neural networks in facial recognition
    Patent number: 11694477
    Abstract: This disclosure provides a highly scalable training data preparation pipeline for data cleaning and augmentation with the aim of extracting the most meaningful information while keeping the noise level low, as well as a highly efficient distributed trainer for the deep neural networks suitable for facial recognition. The goal is to train deeper and larger neural networks with larger and higher quality facial image datasets iteratively and frequently without incurring prohibitive costs and drastic delays.
    Type: Grant
    Filed: August 10, 2022
    Date of Patent: July 4, 2023
    Assignee: Clearview AI, Inc.
    Inventor: Zhi Liu
  • Scalable training data preparation pipeline and efficient distributed trainer for deep neural networks in facial recognition
    Patent number: 11443553
    Abstract: This disclosure provides a highly scalable training data preparation pipeline for data cleaning and augmentation with the aim of extracting the most meaningful information while keeping the noise level low, as well as a highly efficient distributed trainer for the deep neural networks suitable for facial recognition. The goal is to train deeper and larger neural networks with larger and higher quality facial image datasets iteratively and frequently without incurring prohibitive costs and drastic delays.
    Type: Grant
    Filed: February 22, 2022
    Date of Patent: September 13, 2022
    Assignee: Clearview AI, Inc.
    Inventors: Zhi Liu, Cam-Hoan Ton-That
  • METHODS FOR PROVIDING INFORMATION ABOUT A PERSON BASED ON FACIAL RECOGNITION
    Publication number: 20220122356
    Abstract: This disclosure provides methods for providing information about a person based on facial recognition and various applications thereof, including face-based check-in, face-based personal identification, face-based identification verification, face-based background checks, facial data collaborative network, correlative face search, and personal face-based identification. The disclosed methods are able to provide accurate information about a person in a real-time manner.
    Type: Application
    Filed: January 3, 2022
    Publication date: April 21, 2022
    Applicant: Clearview AI, Inc.
    Inventor: Cam-Hoan Ton-That
  • Methods for providing information about a person based on facial recognition
    Patent number: 11250266
    Abstract: This disclosure provides methods for providing information about a person based on facial recognition and various applications thereof, including face-based check-in, face-based personal identification, face-based identification verification, face-based background checks, facial data collaborative network, correlative face search, and personal face-based identification. The disclosed methods are able to provide accurate information about a person in a real-time manner.
    Type: Grant
    Filed: August 7, 2020
    Date of Patent: February 15, 2022
    Assignee: Clearview AI, Inc.
    Inventor: Cam-Hoan Ton-That