-
51.发明申请公开(公告)号：US20190355134A1
公开(公告)日：2019-11-21
申请号：US16406242
申请日：2019-05-08
Applicant: NEC Laboratories America, Inc.
Inventor： Paul Vernaza , Nicholas Rhinehart , Anqi Liu , Kihyuk Sohn
Abstract: Systems and methods for training and evaluating a deep generative model with an architecture consisting of two complementary density estimators are provided. The method includes receiving a probabilistic model of vehicle motion, and training, by a processing device, a first density estimator and a second density estimator jointly based on the probabilistic model of vehicle motion. The first density estimator determines a distribution of outcomes and the second density estimator estimates sample quality. The method also includes identifying by the second density estimator spurious modes in the probabilistic model of vehicle motion. The probabilistic model of vehicle motion is adjusted to eliminate the spurious modes.
-
公开(公告)号：US20190354801A1
公开(公告)日：2019-11-21
申请号：US16400429
申请日：2019-05-01
Applicant: NEC Laboratories America, Inc.
Inventor： Kihyuk Sohn , Manmohan Chandraker , Xiang Yu
Abstract: A method for implementing an unsupervised cross-domain distance metric adaptation framework with a feature transfer network for enhancing facial recognition includes recursively training a feature transfer network and automatic labeling of target domain data using a clustering method, and implementing the feature transfer network and the automatic labeling to perform a facial recognition task.
-
Patent Agency Ranking
公开(公告)号：US20190138812A1
公开(公告)日：2019-05-09
申请号：US16112040
申请日：2018-08-24
Applicant: NEC Laboratories America, Inc.
Inventor： Kihyuk Sohn , Manmohan Chandraker , Xiang Yu
Abstract: A computer-implemented method, system, and computer program product are provided for activity recognition in a mobile device. The method includes receiving a plurality of unlabeled videos from one or more cameras. The method also includes generating a classified video for each of the plurality of unlabeled videos by classifying an activity in each of the plurality of unlabeled videos. The method additionally includes storing the classified video in a location in a memory designated for videos of the activity in each of the classified videos.
-
公开(公告)号：US20190095705A1
公开(公告)日：2019-03-28
申请号：US16145537
申请日：2018-09-28
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Xi Yin , Kihyuk Sohn , Manmohan Chandraker
Abstract: A computer-implemented method, system, and computer program product are provided for facial recognition. The method includes receiving, by a processor device, a plurality of images. The method also includes extracting, by the processor device with a feature extractor utilizing a convolutional neural network (CNN) with an enlarged intra-class variance of long-tail classes, feature vectors for each of the plurality of images. The method additionally includes generating, by the processor device with a feature generator, discriminative feature vectors for each of the feature vectors. The method further includes classifying, by the processor device utilizing a fully connected classifier, an identity from the discriminative feature vector. The method also includes control an operation of a processor-based machine to react in accordance with the identity.
-
公开(公告)号：US20190095700A1
公开(公告)日：2019-03-28
申请号：US16145608
申请日：2018-09-28
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Xi Yin , Kihyuk Sohn , Manmohan Chandraker
Abstract: A computer-implemented method, system, and computer program product are provided for facial recognition. The method includes receiving, by a processor device, a plurality of images. The method also includes extracting, by the processor device with a feature extractor utilizing a convolutional neural network (CNN) with an enlarged intra-class variance of long-tail classes, feature vectors for each of the plurality of images. The method additionally includes generating, by the processor device with a feature generator, discriminative feature vectors for each of the feature vectors. The method further includes classifying, by the processor device utilizing a fully connected classifier, an identity from the discriminative feature vector. The method also includes control an operation of a processor-based machine to react in accordance with the identity.
-
公开(公告)号：US20180268202A1
公开(公告)日：2018-09-20
申请号：US15888747
申请日：2018-02-05
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Kihyuk Sohn , Manmohan Chandraker
CPC classification number: G06K9/00288 , G06F16/71 , G06F16/743 , G06F16/784 , G06K9/00201 , G06K9/00208 , G06K9/00214 , G06K9/00255 , G06K9/00275 , G06K9/00771 , G06K9/00899 , G06K9/4628 , G06K9/6256 , G06T19/20 , G06T2210/44
Abstract: A video surveillance system is provided. The system includes a device configured to capture an input image of a subject located in an area. The system further includes a processor. The processor estimates, using a three-dimensional Morphable Model (3DMM) conditioned Generative Adversarial Network, 3DMM coefficients for the subject of the input image. The subject varies from an ideal front pose. The processor produces, using an image generator, a synthetic frontal face image of the subject of the input image based on the input image and coefficients. An area spanning the frontal face of the subject is made larger in the synthetic than in the input image. The processor provides, using a discriminator, a decision of whether the subject of the synthetic image is an actual person. The processor provides, using a face recognition engine, an identity of the subject in the input image based on the synthetic and input images.
-
57.发明申请公开(公告)号：US20180129869A1
公开(公告)日：2018-05-10
申请号：US15803292
申请日：2017-11-03
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Kihyuk Sohn , Manmohan Chandraker , Xi Peng
CPC classification number: G06K9/00295 , G06K9/00241 , G06K9/00255 , G06K9/00275 , G06K9/00288 , G06K9/00771 , G06K9/62 , G06N3/04 , G06N3/0454 , G06N3/08 , G08B13/19617 , G08B13/19697
Abstract: A computer-implemented method, system, and computer program product is provided for pose-invariant facial recognition. The method includes generating, by a processor using a recognition neural network, a rich feature embedding for identity information and non-identity information for each of one or more images. The method also includes generating, by the processor using a Siamese reconstruction network, one or more pose-invariant features by employing the rich feature embedding for identity information and non-identity information. The method additionally includes identifying, by the processor, a user by employing the one or more pose-invariant features. The method further includes controlling an operation of a processor-based machine to change a state of the processor-based machine, responsive to the identified user in the one or more images.
-
-
-
-
-
-
Search Results
57
records
(took 0.021 seconds)
