Patents by Inventor Sumant Milind Hanumante

Sumant Milind Hanumante 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).

  • Publication number: 20200294195
    Abstract: Remote distribution of multiple neural network models to various client devices over a network can be implemented by identifying a native neural network and remotely converting the native neural network to a target neural network based on a given client device operating environment. The native neural network can be configured for execution using efficient parameters, and the target neural network can use less efficient but more precise parameters.
    Type: Application
    Filed: May 29, 2020
    Publication date: September 17, 2020
    Inventors: Guohui Wang, Sumant Milind Hanumante, Ning Xu, Yuncheng Li
  • Publication number: 20200258248
    Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.
    Type: Application
    Filed: April 27, 2020
    Publication date: August 13, 2020
    Inventors: Kun Duan, Daniel Ron, Chongyang Ma, Ning Xu, Shenlong Wang, Sumant Milind Hanumante, Dhritiman Sagar
  • Patent number: 10713754
    Abstract: Remote distribution of multiple neural network models to various client devices over a network can be implemented by identifying a native neural network and remotely converting the native neural network to a target neural network based on a given client device operating environment. The native neural network can be configured for execution using efficient parameters, and the target neural network can use less efficient but more precise parameters.
    Type: Grant
    Filed: February 28, 2018
    Date of Patent: July 14, 2020
    Assignee: Snap Inc.
    Inventors: Guohui Wang, Sumant Milind Hanumante, Ning Xu, Yuncheng Li
  • Patent number: 10672136
    Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.
    Type: Grant
    Filed: August 31, 2018
    Date of Patent: June 2, 2020
    Assignee: Snap Inc.
    Inventors: Kun Duan, Daniel Ron, Chongyang Ma, Ning Xu, Shenlong Wang, Sumant Milind Hanumante, Dhritiman Sagar
  • Publication number: 20200074653
    Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.
    Type: Application
    Filed: August 31, 2018
    Publication date: March 5, 2020
    Inventors: Kun Duan, Daniel Ron, Chongyang Ma, Ning Xu, Shenlong Wang, Sumant Milind Hanumante, Dhritiman Sagar
  • Publication number: 20190297461
    Abstract: A venue system of a client device can submit a location request to a server, which returns multiple venues that are near the client device. The client device can use one or more machine learning schemes (e.g., convolutional neural networks) to determine that the client device is located in one of specific venues of the possible venues. The venue system can further select imagery for presentation based on the venue selection. The presentation may be published as ephemeral message on a network platform.
    Type: Application
    Filed: March 7, 2019
    Publication date: September 26, 2019
    Inventors: Ebony James Charlton, Sumant Milind Hanumante, Zhou Ren, Dhritiman Sagar
  • Publication number: 20190069147
    Abstract: A venue system of a client device can submit a location request to a server, which returns multiple venues that, are near the client device. The client device can use one or more machine learning schemes (e.g., convolutional neural networks) to determine that the client device is located in one of specific venues of the possible venues. The venue system can further select imagery for presentation based on the venue selection. The presentation may be published as ephemeral message on a network platform.
    Type: Application
    Filed: April 30, 2018
    Publication date: February 28, 2019
    Inventors: Ebony James Charlton, Sumant Milind Hanumante, Zhou Ren, Dhritiman Sagar