Patents by Inventor Arunkumar Mohananchettiar

Arunkumar Mohananchettiar 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).

  • PLACEMENT OF REPAIR PACKETS IN MULTIMEDIA DATA STREAMS
    Publication number: 20250096938
    Abstract: In an example, a method for delivering a multimedia data stream includes determining a frequency for generating one or more repair packets and a placement for positioning the one or more repair packets in the multimedia data stream based on a configuration parameter related to the multimedia data stream. The frequency and the placement may be determined based on a priority derived from a multimedia delivery use-case. Further, the method includes generating the one or more repair packets by network coding source packets of the multimedia data stream based on the determined frequency and the placement and transmitting the network coded multimedia data stream with the repair packets to a receiving device.
    Type: Application
    Filed: June 24, 2022
    Publication date: March 20, 2025
    Inventors: SHAILESH RAMAMURTHY, SWAPAN KUMAR KUNDU, MURALI BABU MUTHUKRISHNAN, ARUNKUMAR MOHANANCHETTIAR
  • MULTI-LEVEL LATENT FUSION IN NEURAL NETWORKS FOR IMAGE AND VIDEO CODING
    Publication number: 20240357112
    Abstract: Methods, systems, and bitstream syntax are described for the fusion of latent features in multi-level, end-to-end, neural networks used in image and video compression. The fused architecture may be static or dynamic based on image characteristics (e.g., natural images versus screen content images) or other coding parameters, such as bitrate constrains or rate-distortion optimization. A variety of multi-level fusion architectures are discussed.
    Type: Application
    Filed: August 3, 2022
    Publication date: October 24, 2024
    Applicant: Dolby Laboratories Licensing Corporation
    Inventors: Arunkumar MOHANANCHETTIAR, Jay Nitin SHINGALA, Pankaj SHARMA, Nijil KOLLERI, Peng YIN, Arjun ARORA, Fangjun PU, Taoran LU, Sean Thomas MCCARTHY, Walter J. HUSAK
  • MULTI-DISTRIBUTION ENTROPY MODELING OF LATENT FEATURES IN IMAGE AND VIDEO CODING USING NEURAL NETWORKS
    Publication number: 20240163485
    Abstract: Methods, systems, and bitstream syntax are described for the entropy modeling of latent features in image and video coding using a combination of probability density functions. Using high-level syntax elements, an encoder may signal to compliant decoders the multi-distribution entropy model using: the number of one or more PDFs being used, an identifier of each PDF being used among a list of available PDFs, the number of PDF parameters in each PDF, and syntax elements indicating which PDF parameters across two or more PDFs being used are being shared.
    Type: Application
    Filed: March 24, 2022
    Publication date: May 16, 2024
    Applicant: Dolby Laboratories Licensing Corporation
    Inventors: Arunkumar MOHANANCHETTIAR, Jay Nitin SHINGALA, Peng YIN, Sean Thomas MCCARTHY
  • System and method for class-specific object segmentation of image data
    Patent number: 8107726
    Abstract: Systems and methods for processing an image to determine whether segments of the image belong to an object class are disclosed.
    Type: Grant
    Filed: June 18, 2008
    Date of Patent: January 31, 2012
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Ning Xu, Arunkumar Mohananchettiar
  • SYSTEM AND METHOD FOR CLASS-SPECIFIC OBJECT SEGMENTATION OF IMAGE DATA
    Publication number: 20090316988
    Abstract: Systems and methods for processing an image to determine whether segments of the image belong to an object class are disclosed.
    Type: Application
    Filed: June 18, 2008
    Publication date: December 24, 2009
    Applicant: Samsung Electronics Co., Ltd.
    Inventors: Ning Xu, Arunkumar Mohananchettiar