Patents by Inventor Khushi
Khushi 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: 11989900Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object recognition neural network for amodal center prediction. One of the methods includes receiving an image of an object captured by a camera. The image of the object is processed using an object recognition neural network that is configured to generate an object recognition output. The object recognition output includes data defining a predicted two-dimensional amodal center of the object, wherein the predicted two-dimensional amodal center of the object is a projection of a predicted three-dimensional center of the object under a camera pose of the camera that captured the image.Type: GrantFiled: June 24, 2021Date of Patent: May 21, 2024Assignee: Magic Leap, Inc.Inventors: Siddharth Mahendran, Nitin Bansal, Nitesh Sekhar, Manushree Gangwar, Khushi Gupta, Prateek Singhal
-
Publication number: 20240127538Abstract: This document describes scene understanding for cross reality systems using occupancy grids. In one aspect, a method includes recognizing one or more objects in a model of a physical environment generated using images of the physical environment. For each object, a bounding box is fit around the object. An occupancy grid that includes a multiple cells is generated within the bounding box around the object. A value is assigned to each cell of the occupancy grid based on whether the cell includes a portion of the object. An object representation that includes information describing the occupancy grid for the object is generated. The object representations are sent to one or more devices.Type: ApplicationFiled: February 3, 2022Publication date: April 18, 2024Inventors: Divya Ramnath, Shiyu Dong, Siddharth Choudhary, Siddharth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta
-
Patent number: 11907531Abstract: Some techniques described herein relate to determining how to optimally store datasets in a multi-tiered storage device with compression. In one example, a method includes assigning, to a data partition of a dataset, a priority based on access patterns of the data partition. Compression data is accessed describing results of compressing a data sample associated with the data partition using multiple compression schemes. Based both on the priority of the data partition and the compression data, a storage tier is determined for storing the data partition in the multi-tiered storage device. Further, based both on the priority of the data partition and the compression data, a compression scheme is determined for compressing the data partition for storage in the multi-tiered storage device. The data partition is compressed using the compression scheme to produce a compressed data partition, and the compressed data partition is stored in the storage tier.Type: GrantFiled: June 28, 2022Date of Patent: February 20, 2024Assignee: Adobe Inc.Inventors: Raunak Shah, Koyel Mukherjee, Khushi, Kavya Barnwal, Karanpreet Singh, Harsh Kesarwani, Ayush Chauhan
-
Publication number: 20240008725Abstract: Medical devices and methods for using medical devices are disclosed. An example fluid reservoir and tube set arranged and configured to couple to an endoscope for use in an endoscopic procedure includes a fluid supply tube wherein the fluid supply tube includes an extendable region positioned along a length of the fluid supply tube, and a lumen in fluid communication with the fluid reservoir. Further, the extendable region is configured to shift between a first configuration having a first length and a second extended configuration having a second length longer than the first length.Type: ApplicationFiled: July 10, 2023Publication date: January 11, 2024Applicant: Boston Scientific Scimed, Inc.Inventor: Khushi Soni
-
Publication number: 20230418468Abstract: Some techniques described herein relate to determining how to optimally store datasets in a multi-tiered storage device with compression. In one example, a method includes assigning, to a data partition of a dataset, a priority based on access patterns of the data partition. Compression data is accessed describing results of compressing a data sample associated with the data partition using multiple compression schemes. Based both on the priority of the data partition and the compression data, a storage tier is determined for storing the data partition in the multi-tiered storage device. Further, based both on the priority of the data partition and the compression data, a compression scheme is determined for compressing the data partition for storage in the multi-tiered storage device. The data partition is compressed using the compression scheme to produce a compressed data partition, and the compressed data partition is stored in the storage tier.Type: ApplicationFiled: June 28, 2022Publication date: December 28, 2023Inventors: Raunak Shah, Koyel Mukherjee, Khushi, Kavya Barnwal, Karanpreet Singh, Harsh Kesarwani, Ayush Chauhan
-
Patent number: 11816452Abstract: Systems and methods for providing enterprise-level application content customization are described herein. A method includes executing an enterprise application (from a suite of enterprise applications that are utilized by the enterprise) on a remote computing system operated by an enterprise administrator. The method includes surfacing a content customization UI on a display device of the remote computing system during execution of the enterprise application. The content customization UI includes UI elements that enable the specification of parameters for providing enterprise-specific customized content during execution of enterprise application(s) from the suite of enterprise applications on remote computing system(s) operated by enterprise user(s). The method also includes receiving, via the content customization UI, user input including the specification of parameters and generating the customized content based on the specified parameters.Type: GrantFiled: April 4, 2022Date of Patent: November 14, 2023Assignee: Microsoft Technology Licensing, LLC.Inventors: Jesse H. Stein, Brian H. Burks, Lu Han, Shilpi Sinha, Antoine Haas, Gaurav Bindlish, Srinivasa Raghavan Santhanam, Harish Jayanti, Brent E. Ford, Cristian M. Matesan, Willis Fung, Sarvesh Surana, Ling-Ya Huang, Magdalena Dakeva, Peter John Richards, Fengna Gu, Andrew N. Dwersteg, Julio Cesar Gutierrez, Abhishek Mondal, William P. Dinkuhn, Shiyuan Zhao, Jonathan I. Reyes Spezzia, Woo Ram Lee, Aayushi Chowdhary, Conner Brennick, Khushi Hitendra Patel, Michael J. Krejcik, Amber Jerica McRae
-
Publication number: 20230315398Abstract: Systems and methods for providing enterprise-level application content customization are described herein. A method includes executing an enterprise application (from a suite of enterprise applications that are utilized by the enterprise) on a remote computing system operated by an enterprise administrator. The method includes surfacing a content customization UI on a display device of the remote computing system during execution of the enterprise application. The content customization UI includes UI elements that enable the specification of parameters for providing enterprise-specific customized content during execution of enterprise application(s) from the suite of enterprise applications on remote computing system(s) operated by enterprise user(s). The method also includes receiving, via the content customization UI, user input including the specification of parameters and generating the customized content based on the specified parameters.Type: ApplicationFiled: April 4, 2022Publication date: October 5, 2023Applicant: Microsoft Technology Licensing, LLCInventors: Jesse H. STEIN, Brian H. BURKS, Lu HAN, Shilpi SINHA, Antoine HAAS, Gaurav BINDLISH, Srinivasa Raghavan SANTHANAM, Harish JAYANTI, Brent E. FORD, Cristian M. MATESAN, Willis FUNG, Sarvesh SURANA, Ling-Ya HUANG, Magdalena DAKEVA, Peter John RICHARDS, Fengna GU, Andrew N. DWERSTEG, Julio Cesar GUTIERREZ, Abhishek MONDAL, William P. DINKUHN, Shiyuan ZHAO, Jonathan I. REYES SPEZZIA, Woo Ram LEE, Aayushi CHOWDHARY, Conner BRENNICK, Khushi Hitendra PATEL, Michael J. KREJCIK, Amber Jerica MCRAE
-
Publication number: 20230290132Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object recognition neural network using multiple data sources. One of the methods includes receiving training data that includes a plurality of training images from a first source and images from a second source. A set of training images are obtained from the training data. For each training image in the set of training images, contrast equalization is applied to the training image to generate a modified image. The modified image is processed using the neural network to generate an object recognition output for the modified image. A loss is determined based on errors between, for each training image in the set, the object recognition output for the modified image generated from the training image and ground-truth annotation for the training image. Parameters of the neural network are updated based on the determined loss.Type: ApplicationFiled: July 28, 2021Publication date: September 14, 2023Inventors: Siddharth MAHENDRAN, Nitin BANSAL, Nitesh SEKHAR, Manushree GANGWAR, Khushi GUPTA, Prateek SINGHAL, Tarrence VAN AS, Adithya Shricharan Srinivasa RAO
-
Patent number: 11704806Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.Type: GrantFiled: January 12, 2022Date of Patent: July 18, 2023Assignee: Magic Leap, Inc.Inventors: Siddharth Choudhary, Divya Ramnath, Shiyu Dong, Siddharth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta, Nitesh Sekhar, Manushree Gangwar
-
Publication number: 20220396823Abstract: Disclosed herein are glyco-decoy acceptor compositions that sidetrack or inhibit the activity of biosynthetic enzymes participating in synthesis of ligands binding at selectin, galectin and siglecs receptors; methods of their preparation and uses in drug discovery and in treatments of diseases.Type: ApplicationFiled: December 20, 2021Publication date: December 15, 2022Applicant: TUMOREND, LLCInventor: Khushi L. MATTA
-
Publication number: 20220139057Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.Type: ApplicationFiled: January 12, 2022Publication date: May 5, 2022Inventors: Siddharth Choudhary, Divya Ramnath, Shiyu Dong, Siddharth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta, Nitesh Sekhar, Manushree Gangwar
-
Patent number: 11257300Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.Type: GrantFiled: June 12, 2020Date of Patent: February 22, 2022Assignee: Magic Leap, Inc.Inventors: Siddharth Choudhary, Divya Ramnath, Shiyu Dong, Siddharth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta, Nitesh Sekhar, Manushree Gangwar
-
Publication number: 20210407125Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object recognition neural network for amodal center prediction. One of the methods includes receiving an image of an object captured by a camera. The image of the object is processed using an object recognition neural network that is configured to generate an object recognition output. The object recognition output includes data defining a predicted two-dimensional amodal center of the object, wherein the predicted two-dimensional amodal center of the object is a projection of a predicted three-dimensional center of the object under a camera pose of the camera that captured the image.Type: ApplicationFiled: June 24, 2021Publication date: December 30, 2021Inventors: Siddharth Mahendran, Nitin Bansal, Nitesh Sekhar, Manushree Gangwar, Khushi Gupta, Prateek Singhal
-
Patent number: 11203776Abstract: Disclosed herein are glyco-decoy acceptor compositions that sidetrack or inhibit the activity of biosynthetic enzymes participating in synthesis of ligands binding at selectin, galectin and siglecs receptors; methods of their preparation and uses in drug discovery and in treatments of diseases.Type: GrantFiled: November 12, 2015Date of Patent: December 21, 2021Assignee: TumorEnd, LLCInventor: Khushi L. Matta
-
Publication number: 20200394848Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.Type: ApplicationFiled: June 12, 2020Publication date: December 17, 2020Inventors: Siddharth Choudhary, Divya Ramnath, Shiyu Dong, Siddarth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta, Nitesh Sekhar, Manushree Gangwar
-
Publication number: 20190017095Abstract: Disclosed herein are glyco-decoy acceptor compositions that sidetrack or inhibit the activity of biosynthetic enzymes participating in synthesis of ligands binding at selectin, galectin and siglecs receptors; methods of their preparation and uses in drug discovery and in treatments of diseases.Type: ApplicationFiled: November 12, 2015Publication date: January 17, 2019Applicant: TUMOREND, LLCInventor: Khushi L. MATTA
-
Patent number: 9426170Abstract: A system and method for stemming flow of information from a negative campaign are described. A status for each node of a set of preselected nodes in a social network graph is identified. The status indicates whether a node has been infected with information from a negative campaign. A source and a flow of the negative campaign are identified based on the status of the nodes from the set of preselected nodes and a topology of the social network graph. A susceptibility score is computed for one or more nodes of the social network. The susceptibility score is computed using a measure of vulnerability of nodes that have not received the information based on the flow of the negative campaign, and a measure of reachability of nodes from the source. Nodes susceptible to adopting and spreading the information from the negative campaign are identified based on the susceptibility score.Type: GrantFiled: October 17, 2013Date of Patent: August 23, 2016Assignee: ADOBE SYSTEMS INCORPORATEDInventors: Balaji Vasan Srinivasan, Akshay Kumar, Shubham Gupta, Khushi Gupta
-
Publication number: 20150113056Abstract: A system and method for stemming flow of information from a negative campaign are described. A status for each node of a set of preselected nodes in a social network graph is identified. The status indicates whether a node has been infected with information from a negative campaign. A source and a flow of the negative campaign are identified based on the status of the nodes from the set of preselected nodes and a topology of the social network graph. A susceptibility score is computed for one or more nodes of the social network. The susceptibility score is computed using a measure of vulnerability of nodes that have not received the information based on the flow of the negative campaign, and a measure of reachability of nodes from the source. Nodes susceptible to adopting and spreading the information from the negative campaign are identified based on the susceptibility score.Type: ApplicationFiled: October 17, 2013Publication date: April 23, 2015Applicant: Adobe Systems IncorporatedInventors: Balaji Vasan Srinivasan, Akshay Kumar, Shubham Gupta, Khushi Gupta
-
Patent number: 8278072Abstract: A method for producing sialylated molecules based on reverse sialylation that catalytically transfers the sialic acid moiety of sialylated donors to nucleotide monophosphates or transfer sialic acid moieties from sialylated donors to acceptor glycoproteins or glycolipids.Type: GrantFiled: November 19, 2008Date of Patent: October 2, 2012Assignees: Health Research, Inc., The Research Foundation of State University of New YorkInventors: Khushi L. Matta, Edaya V. Chandrasekaran, Sriram Neelamegham, Jun Xue
-
Publication number: 20100221763Abstract: A method for determining substrates specific for a transferase enzyme selected from the group consisting of glycosyltransferases and sulfotransferases.Type: ApplicationFiled: October 17, 2006Publication date: September 2, 2010Applicant: Health Research, IncInventors: Khushi L. Matta, E.V. Chandrasekaran