-
公开(公告)号：US20220292306A1
公开(公告)日：2022-09-15
申请号：US17201816
申请日：2021-03-15
Applicant: NVIDIA Corporation
Inventor： Subhashree Radhakrishnan , Partha Sriram , Farzin Aghdasi , Seunghwan Cha , Zhiding Yu
Abstract: In various examples, training methods as described to generate a trained neural network that is robust to various environmental features. In an embodiment, training includes modifying images of a dataset and generating boundary boxes and/or other segmentation information for the modified images which is used to train a neural network.
-
公开(公告)号：US11205086B2
公开(公告)日：2021-12-21
申请号：US16678100
申请日：2019-11-08
Applicant: NVIDIA Corporation
Inventor： Parthasarathy Sriram , Fnu Ratnesh Kumar , Anil Ubale , Farzin Aghdasi , Yan Zhai , Subhashree Radhakrishnan
Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.
-
公开(公告)号：US20250029409A1
公开(公告)日：2025-01-23
申请号：US18354431
申请日：2023-07-18
Applicant: Nvidia Corporation
Inventor： Subhashree Radhakrishnan , Ramanathan Arunachahalam , Farzin Aghdasi , Zhiding Yu , Shiyi Lan
Abstract: Approaches are disclosed herein for an automatic segmentation labeling system that identifies objects for potential open-class categories and generates segmentation masks for objects. The disclosed system may use a training pipeline that trains two segmentation models. The training pipeline may take, as input, a set of images with bounding boxes and class labels. The set of images may be fed into a first segmentation network with the bounding boxes used as ground truth for weak supervision. The first segmentation network may be trained to generate pseudo segmentation masks. In a second stage, the trained first segmentation network is used to generate pseudo masks for a set of input images. The generated pseudo masks are provided as input, along with the corresponding images, to a second segmentation network to be used as a type of ground truth data for training the second segmentation network to generate high-quality segmentation masks.
-
公开(公告)号：US11741736B2
公开(公告)日：2023-08-29
申请号：US17556451
申请日：2021-12-20
Applicant: NVIDIA Corporation
Inventor： Parthasarathy Sriram , Fnu Ratnesh Kumar , Anil Ubale , Farzin Aghdasi , Yan Zhai , Subhashree Radhakrishnan
CPC classification number: G06V40/103 , G06N3/045 , G06N3/08 , G06T7/248 , G06V10/26 , G06V10/454 , G06V10/82 , G06V20/52 , G06V40/10 , G06T2207/10016 , G06T2207/20084 , G06T2207/30196 , G06T2207/30232 , G06T2207/30241
Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.
-
公开(公告)号：US20220327318A1
公开(公告)日：2022-10-13
申请号：US17225924
申请日：2021-04-08
Applicant: NVIDIA Corporation
Inventor： Subhashree Radhakrishnan , Farzin Aghdasi
Abstract: Apparatuses, systems, and techniques to perform action recognition. In at least one embodiment, action recognition is performed using one or more neural networks and hardware accelerators, in which the one or more neural networks are processed based on, for example, one or more quantization and pruning processes.
-
Patent Agency Ranking
公开(公告)号：US12087077B2
公开(公告)日：2024-09-10
申请号：US18347471
申请日：2023-07-05
Applicant: NVIDIA Corporation
Inventor： Parthasarathy Sriram , Fnu Ratnesh Kumar , Anil Ubale , Farzin Aghdasi , Yan Zhai , Subhashree Radhakrishnan
CPC classification number: G06V40/103 , G06N3/045 , G06N3/08 , G06T7/248 , G06V10/26 , G06V10/454 , G06V10/82 , G06V20/52 , G06V40/10 , G06T2207/10016 , G06T2207/20084 , G06T2207/30196 , G06T2207/30232 , G06T2207/30241
Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.
-
公开(公告)号：US11899749B2
公开(公告)日：2024-02-13
申请号：US17201816
申请日：2021-03-15
Applicant: NVIDIA Corporation
Inventor： Subhashree Radhakrishnan , Partha Sriram , Farzin Aghdasi , Seunghwan Cha , Zhiding Yu
CPC classification number: G06F18/214 , G06T3/0006 , G06T7/12 , G06V10/22 , G06V10/242 , G06V20/40 , G06T2207/20081 , G06T2207/20084
Abstract: In various examples, training methods as described to generate a trained neural network that is robust to various environmental features. In an embodiment, training includes modifying images of a dataset and generating boundary boxes and/or other segmentation information for the modified images which is used to train a neural network.
-
公开(公告)号：US20230351795A1
公开(公告)日：2023-11-02
申请号：US18347471
申请日：2023-07-05
Applicant: NVIDIA Corporation
Inventor： Parthasarathy Sriram , Fnu Ratnesh Kumar , Anil Ubale , Farzin Aghdasi , Yan Zhai , Subhashree Radhakrishnan
CPC classification number: G06V40/103 , G06N3/08 , G06T7/248 , G06V10/26 , G06V20/52 , G06V40/10 , G06N3/045 , G06V10/82 , G06V10/454 , G06T2207/30232 , G06T2207/10016 , G06T2207/20084 , G06T2207/30196 , G06T2207/30241
Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.
-
公开(公告)号：US20230078218A1
公开(公告)日：2023-03-16
申请号：US17477370
申请日：2021-09-16
Applicant: NVIDIA Corporation
Inventor： Yu Wang , Farzin Aghdasi , Parthasarathy Sriram , Subhashree Radhakrishnan
Abstract: Apparatuses, systems, and techniques for training an object detection model using transfer learning.
-
公开(公告)号：US20220114800A1
公开(公告)日：2022-04-14
申请号：US17556451
申请日：2021-12-20
Applicant: NVIDIA Corporation
Inventor： Parthasarathy Sriram , Fnu Ratnesh Kumar , Anil Ubale , Farzin Aghdasi , Yan Zhai , Subhashree Radhakrishnan
Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.
-
-
-
-
-
-
-
-
-
Search Results
15
records
(took 0.032 seconds)
