-
公开(公告)号：US20170228641A1
公开(公告)日：2017-08-10
申请号：US15385283
申请日：2016-12-20
Applicant: NEC Laboratories America, Inc.
Inventor： Kihyuk Sohn
CPC classification number: G06N3/08 , G06F17/11 , G06N3/04 , G06N3/0454 , G06N7/005
Abstract: A method includes receiving N pairs of training examples and class labels therefor. Each pair includes a respective anchor example, and a respective non-anchor example capable of being a positive or a negative training example. The method further includes extracting features of the pairs by applying a DHCNN, and calculating, for each pair based on the features, a respective similarly measure between the respective anchor and no example. The method additionally includes calculating a similarity score based on the respective similarity measure for each pair. The score represents similarities between all anchor points and positive training examples in the pairs relative to similarities between all anchor points and negative training examples in the pairs. The method further includes maximizing the similarity score for the anchor example for each pair to pull together the training examples from a same class while pushing apart the training examples from different classes.
-
42.发明授权公开(公告)号：US11049265B2
公开(公告)日：2021-06-29
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：US20210142043A1
公开(公告)日：2021-05-13
申请号：US17091011
申请日：2020-11-06
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Manmohan Chandraker , Kihyuk Sohn , Yichun Shi
Abstract: A computer-implemented method for implementing face recognition includes receiving training data including a plurality of augmented images each corresponding to a respective one of a plurality of input images augmented by one of a plurality of variations, splitting a feature embedding generated from the training data into a plurality of sub-embeddings each associated with one of the plurality of variations, associating each of the plurality of sub-embeddings with respective ones of a plurality of confidence values, and applying a plurality of losses including a confidence-aware identification loss and a variation-decorrelation loss to the plurality of sub-embeddings and the plurality of confidence values to improve face recognition performance by learning the plurality of sub-embeddings.
-
公开(公告)号：US10915792B2
公开(公告)日：2021-02-09
申请号：US16535681
申请日：2019-08-08
Applicant: NEC Laboratories America, Inc.
Inventor： Yi-Hsuan Tsai , Kihyuk Sohn , Buyu Liu , Manmohan Chandraker , Jong-Chyi Su
Abstract: Systems and methods for domain adaptation are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.
-
公开(公告)号：US10885383B2
公开(公告)日：2021-01-05
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：US10853655B2
公开(公告)日：2020-12-01
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：US10796135B2
公开(公告)日：2020-10-06
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：US10796134B2
公开(公告)日：2020-10-06
申请号：US16145257
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：US10740596B2
公开(公告)日：2020-08-11
申请号：US15803318
申请日：2017-11-03
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Kihyuk Sohn , Manmohan Chandraker
IPC: G06K9/00 , G06K9/62 , G06N3/04 , G06N3/08 , G08B13/196
Abstract: A computer-implemented method, system, and computer program product is provided for video security. The method includes monitoring an area with a camera. The method also includes capturing, by the camera, live video to provide a live video stream. The method additionally includes detecting and identifying, by a processor using a recognition neural network feeding into a Siamese reconstruction network, a user in the live video stream by employing one or more pose-invariant features. The method further includes controlling, by the processor, an operation of a processor-based machine to change a state of the processor-based machine, responsive to the identified user in the live video stream.
-
公开(公告)号：US10740595B2
公开(公告)日：2020-08-11
申请号：US16145578
申请日：2018-09-28
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Xi Yin , Kihyuk Sohn , Manmohan Chandraker
IPC: A61B5/00 , G06K9/00 , G06N3/08 , G06K9/62 , G06Q20/40 , G06Q30/02 , G08B13/196 , G08B15/00 , G06F3/00 , H04N7/18
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.
-
-
-
-
-
-
-
-
-
Search Results
57
records
(took 0.017 seconds)
