中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

57 records (took 0.02 seconds)

    Viewpoint invariant object recognition by synthesization and domain adaptation
    21.
    发明授权
    Viewpoint invariant object recognition by synthesization and domain adaptation 有权

    公开(公告)号：US11055989B2

    公开(公告)日：2021-07-06

    申请号：US16051924

    申请日：2018-08-01

    Applicant: NEC Laboratories America, Inc.

    Inventor： Kihyuk Sohn ,  Luan Tran ,  Xiang Yu ,  Manmohan Chandraker

    IPC: G08G1/017 ,  G06K9/62 ,  G06K9/00 ,  G06N3/08 ,  G06N3/04 ,  G06N5/04 ,  G06T17/00 ,  G06N20/00 ,  G08G1/01 ,  G08G1/04 ,  G08G1/048 ,  G06K9/46

    Abstract: Systems and methods for performing domain adaptation include collecting a labeled source image having a view of an object. Viewpoints of the object in the source image are synthesized to generate view augmented source images. Photometrics of each of the viewpoints of the object are adjusted to generate lighting and view augmented source images. Features are extracted from each of the lighting and view augmented source images with a first feature extractor and from captured images captured by an image capture device with a second feature extractor. The extracted features are classified using domain adaptation with domain adversarial learning between extracted features of the captured images and extracted features of the lighting and view augmented source images. Labeled target images are displayed corresponding to each of the captured images including labels corresponding to classifications of the extracted features of the captured images.

    DOMAIN ADAPTATION FOR INSTANCE DETECTION AND SEGMENTATION
    23.
    发明申请
    DOMAIN ADAPTATION FOR INSTANCE DETECTION AND SEGMENTATION 审中-公开

    公开(公告)号：US20200082221A1

    公开(公告)日：2020-03-12

    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

    IPC: G06K9/62 ,  G06T7/11

    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.

    Video retrieval system based on larger pose face frontalization
    24.
    发明授权
    Video retrieval system based on larger pose face frontalization 有权

    公开(公告)号：US10474881B2

    公开(公告)日：2019-11-12

    申请号：US15888693

    申请日：2018-02-05

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xiang Yu ,  Kihyuk Sohn ,  Manmohan Chandraker

    IPC: G06K9/00 ,  G06T19/20 ,  G06K9/46 ,  G06K9/62 ,  G06F16/71 ,  G06F16/74 ,  G06F16/783

    Abstract: A video retrieval system is provided that includes a server for retrieving video sequences from a remote database responsive to a text specifying a face recognition result as an identity of a subject of an input image. The face recognition result is determined by a processor of the server, which estimates, using a 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 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 a decision of whether the synthetic image subject is an actual person and provides the identity of the subject in the input image based on the synthetic and input images.

    VIDEO REPRESENTATION OF FIRST-PERSON VIDEOS FOR ACTIVITY RECOGNITION WITHOUT LABELS
    25.
    发明申请
    VIDEO REPRESENTATION OF FIRST-PERSON VIDEOS FOR ACTIVITY RECOGNITION WITHOUT LABELS 审中-公开

    公开(公告)号：US20190138811A1

    公开(公告)日：2019-05-09

    申请号：US16111298

    申请日：2018-08-24

    Applicant: NEC Laboratories America, Inc.

    Inventor： Kihyuk Sohn ,  Manmohan Chandraker ,  Xiang Yu

    IPC: G06K9/00 ,  G06K9/62

    Abstract: A computer-implemented method, system, and computer program product are provided for activity recognition. The method includes receiving, by a processor, a plurality of videos, the plurality of videos including labeled videos and unlabeled videos. The method also includes extracting, by the processor with a feature extraction convolutional neural network (CNN), frame features for frames from each of the plurality of videos. The method additionally includes estimating, by the processor with a feature aggregation system, a vector representation for one of the plurality of videos responsive to the frame features. The method further includes classifying, by the processor, an activity from the vector representation. The method also includes controlling an operation of a processor-based machine to react in accordance with the activity.

    Human detection in scenes
    28.
    发明授权
    Human detection in scenes 有权

    公开(公告)号：US11610420B2

    公开(公告)日：2023-03-21

    申请号：US17128565

    申请日：2020-12-21

    Applicant: NEC Laboratories America, Inc.

    Inventor： Yi-Hsuan Tsai ,  Kihyuk Sohn ,  Buyu Liu ,  Manmohan Chandraker ,  Jong-Chyi Su

    IPC: G06K9/00 ,  G06V40/10 ,  G06K9/62 ,  G06N3/04 ,  G06N3/088 ,  G06V10/25

    Abstract: Systems and methods for human detection 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 target domain includes humans in one or more different scenes. 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.

    DEEP FACE RECOGNITION BASED ON CLUSTERING OVER UNLABELED FACE DATA
    29.
    发明申请
    DEEP FACE RECOGNITION BASED ON CLUSTERING OVER UNLABELED FACE DATA 有权

    公开(公告)号：US20210142046A1

    公开(公告)日：2021-05-13

    申请号：US17091066

    申请日：2020-11-06

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xiang Yu ,  Manmohan Chandraker ,  Kihyuk Sohn ,  Aruni RoyChowdhury

    IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04

    Abstract: A computer-implemented method for implementing face recognition includes obtaining a face recognition model trained on labeled face data, separating, using a mixture of probability distributions, a plurality of unlabeled faces corresponding to unlabeled face data into a set of one or more overlapping unlabeled faces that include overlapping identities to those in the labeled face data and a set of one or more disjoint unlabeled faces that include disjoint identities to those in the labeled face data, clustering the one or more disjoint unlabeled faces using a graph convolutional network to generate one or more cluster assignments, generating a clustering uncertainty associated with the one or more cluster assignments, and retraining the face recognition model on the labeled face data and the unlabeled face data to improve face recognition performance by incorporating the clustering uncertainty.

    CONSTRUCTION ZONE SEGMENTATION
    30.
    发明申请
    CONSTRUCTION ZONE SEGMENTATION 有权

    公开(公告)号：US20210110209A1

    公开(公告)日：2021-04-15

    申请号：US17128612

    申请日：2020-12-21

    Applicant: NEC Laboratories America, Inc.

    Inventor： Yi-Hsuan Tsai ,  Kihyuk Sohn ,  Buyu Liu ,  Manmohan Chandraker ,  Jong-Chyi Su

    IPC: G06K9/62 ,  G06T7/11 ,  G06K9/00 ,  G06K9/32 ,  G06N3/08

    Abstract: Systems and methods for construction zone segmentation 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 target domain includes construction zones scenes having various objects. 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.

Patent Agency Ranking