-
公开(公告)号：US20230196617A1
公开(公告)日：2023-06-22
申请号：US17559364
申请日：2021-12-22
Inventor： Meng Zheng , Srikrishna Karanam , Ziyan Wu
CPC classification number: G06T7/75 , G06N3/0454 , G06V40/10 , G06T7/50 , G06T2207/20081 , G06T2207/20084
Abstract: Human model recovery may be realized utilizing pre-trained artificially neural networks. A first neural network may be trained to determine body keypoints of a person based on image(s) of a person. A second neural network may be trained to predict pose parameters associated with the person based on the body keypoints. A third neural network may be trained to predict shape parameters associated with the person based on depth image(s) of the person. A 3D human model may then be generated based on the pose and shape parameters respectively predicted by the second and third neural networks. The training of the second neural network may be conducted using synthetically generated body keypoints and the training of the third neural network may be conducted using normal maps. The pose and shape parameters predicted by the second and third neural networks may be further optimized through an iterative optimization process.
-
公开(公告)号：US20230153658A1
公开(公告)日：2023-05-18
申请号：US17525313
申请日：2021-11-12
Inventor： Ziyan Wu , Yunhao Ge , Meng Zheng , Srikrishna Karanam , Terrence Chen
CPC classification number: G06N5/045 , G06F11/302 , G06F11/3086
Abstract: Automatically generating an explanation for a decision prediction from a machine learning algorithm includes using a first processor of a computing device to run the machine learning algorithm using one or more input data; generating a decision prediction output based on the one or more input data; using a second processor to access the decision prediction output of the first processor; generating additional information that identifies one or more causal relationships between the prediction of the first algorithm and the one or more input data; and providing the additional information as the explanation in a user-understandable format on a display of the computing device.
-
公开(公告)号：US20230141392A1
公开(公告)日：2023-05-11
申请号：US18095857
申请日：2023-01-11
Inventor： Ziyan Wu , Srikrishna Karanam , Changjiang Cai , Georgios Georgakis
IPC: A61B5/00 , G16H30/40 , G06T7/00 , G06T7/90 , G06T17/00 , G06T7/50 , G06T7/70 , G06T17/20 , G16H10/60 , G16H30/20 , G06V20/64 , G06V40/10 , G06V40/20 , G06V20/62 , G06F18/21 , G06F18/214 , G06V10/764 , G06V10/774 , G06V10/778 , G06V10/82 , G06V10/42 , G06V10/40
CPC classification number: A61B5/0077 , G16H30/40 , G06T7/0012 , G06T7/90 , G06T17/00 , G06T7/50 , G06T7/70 , G06T17/20 , G16H10/60 , G16H30/20 , A61B5/0035 , A61B5/70 , G06V20/64 , G06V40/10 , G06V40/20 , G06V20/62 , G06F18/21 , G06F18/214 , G06F18/2193 , G06V10/764 , G06V10/774 , G06V10/7796 , G06V10/82 , G06V10/42 , G06V10/40 , G06T2207/30004 , G06T2200/08 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G06T2207/30196 , G06V2201/033
Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.
-
公开(公告)号：US11604984B2
公开(公告)日：2023-03-14
申请号：US16686539
申请日：2019-11-18
Inventor： Abhishek Sharma , Arun Innanje , Ziyan Wu , Shanhui Sun , Terrence Chen
Abstract: A system comprising a first computing apparatus in communication with multiple second computing apparatuses. The first computing apparatus may obtain a plurality of first trained machine learning models for a task from the multiple second computing apparatuses. At least a portion of parameter values of the plurality of first trained machine learning models may be different from each other. The first computing apparatus may also obtain a plurality of training samples. The first computing apparatus may further determine, based on the plurality of training samples, a second trained machine learning model by learning from the plurality of first trained machine learning models.
-
公开(公告)号：US20230013508A1
公开(公告)日：2023-01-19
申请号：US17378495
申请日：2021-07-16
Inventor： Abhishek Sharma , Arun Innanje , Ziyan Wu
Abstract: Image-based key points detection using a convolutional neural network (CNN) may be impacted if the key points are occluded in the image. Images obtained from additional imaging modalities such as depth and/or thermal images may be used in conjunction with RGB images to reduce or minimize the impact of the occlusion. The additional images may be used to determine adjustment values that are then applied to the weights of the CNN so that the convolution operations may be performed in a modality aware manner to increase the robustness, accuracy, and efficiency of key point detection.
-
Patent Agency Ranking
公开(公告)号：US11386537B2
公开(公告)日：2022-07-12
申请号：US16802989
申请日：2020-02-27
Inventor： Abhishek Sharma , Meng Zheng , Srikrishna Karanam , Ziyan Wu , Arun Innanje , Terrence Chen
Abstract: Abnormality detection within a defined area includes obtaining a plurality of images of the defined area from image-capture devices. An extent of deviation of one or more types of products from an inference of each of the plurality of images is determined using a trained neural network. A localized dimensional representation is generated in a portion of an input image associated with a first location of the plurality of locations, based on gradients computed from the determined extent of deviation. The generated localized dimensional representation provides a visual indication of an abnormality located in the first location within the defined area. An action associated with the first location is executed based on the generated dimensional representation for proactive control or prevention of occurrence of undesired event in the defined area.
-
公开(公告)号：US20210272258A1
公开(公告)日：2021-09-02
申请号：US16802989
申请日：2020-02-27
Inventor： Abhishek Sharma , Meng Zheng , Srikrishna Karanam , Ziyan Wu , Arun Innanje , Terrence Chen
Abstract: Abnormality detection within a defined area includes obtaining a plurality of images of the defined area from image-capture devices. An extent of deviation of one or more types of products from an inference of each of the plurality of images is determined using a trained neural network. A localized dimensional representation is generated in a portion of an input image associated with a first location of the plurality of locations, based on gradients computed from the determined extent of deviation. The generated localized dimensional representation provides a visual indication of an abnormality located in the first location within the defined area. An action associated with the first location is executed based on the generated dimensional representation for proactive control or prevention of occurrence of undesired event in the defined area.
-
公开(公告)号：US20210272014A1
公开(公告)日：2021-09-02
申请号：US16804907
申请日：2020-02-28
Inventor： Srikrishna Karanam , Ziyan Wu , Abhishek Sharma , Arun Innanje , Terrence Chen
Abstract: Data samples are transmitted from a central server to at least one local server apparatus. The central server receives a set of predictions from the at least one local server apparatus that are based on the transmitted set of data samples. The central server trains a central model based on the received set of predictions. The central model, or a portion of the central model corresponding to a task of interest, can then be sent to the at least one local server apparatus. Neither local data from local sites nor trained models from the local sites are transmitted to the central server. This ensures protection and security of data at the local sites.
-
公开(公告)号：US11080889B2
公开(公告)日：2021-08-03
申请号：US16580518
申请日：2019-09-24
Inventor： Srikrishna Karanam , Ziyan Wu
Abstract: Methods and systems for providing guidance for adjusting a target. For example, a computer-implemented method for providing guidance for adjusting a target includes: receiving, by a neural network, a reference image; receiving, by the neural network, the target image, the target image being related to a position of a target; determining a similarity metric based at least in part on information associated with the reference image and information associated with the target image by the neural network; generating a target attention map corresponding to the target image based at least in part on the similarity metric; outputting the target image and the target attention map; and providing a guidance for adjusting the position of the target based at least in part on the target image and the target attention map.
-
公开(公告)号：US20210158932A1
公开(公告)日：2021-05-27
申请号：US16814373
申请日：2020-03-10
Inventor： Srikrishna Karanam , Ziyan Wu
Abstract: A patient's healthcare experience may be enhanced utilizing a system that automatically recognizes the patient based on one or more images of the patient and generates personalized medical assistance information for the patient based on electronic medical records stored for the patient. Such electronic medical records may comprise imagery data and/or non-imagery associated with a medical procedure performed or to be performed for the patient. As such, the imagery and/or non-imagery data may be incorporated into the personalized medical assistance information to provide positioning and/or other types of diagnostic or treatment guidance to the patient or a service provider.
-
-
-
-
-
-
-
-
-
Search Results
101
records
(took 0.025 seconds)
