公开(公告)号：US11250573B2

公开(公告)日：2022-02-15

申请号：US16515713

申请日：2019-07-18

Applicant: NEC Laboratories America, Inc.

Inventor： Gaurav Sharma ,  Manmohan Chandraker ,  Jinwoo Choi

IPC: G06T7/20 ,  G06K9/00

Abstract: A method is provided for drone-video-based action recognition. The method learns a transformation for each of target video clips taken from a set of target videos, responsive to original features extracted from the target video clips. The transformation corrects differences between a target drone domain corresponding to the target video clips and a source non-drone domain corresponding to source video clips taken from a set of source videos. The method adapts the target to the source domain by applying the transformation to the original features to obtain transformed features for the target video clips. The method converts the original and transformed features of same ones of the target video clips into a single classification feature for each of the target videos. The method classifies a human action in a new target video relative to the set of source videos using the single classification feature for each of the target videos.

公开(公告)号：US20210064883A1

公开(公告)日：2021-03-04

申请号：US16998404

申请日：2020-08-20

Applicant: NEC Laboratories America, Inc.

Inventor： Gaurav Sharma ,  Samuel Schulter ,  Jinwoo Choi

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

Abstract: A method for performing video domain adaptation for human action recognition is presented. The method includes using annotated source data from a source video and unannotated target data from a target video in an unsupervised domain adaptation setting, identifying and aligning discriminative clips in the source and target videos via an attention mechanism, and learning spatial-background invariant human action representations by employing a self-supervised clip order prediction loss for both the annotated source data and the unannotated target data.

公开(公告)号：US20200151457A1

公开(公告)日：2020-05-14

申请号：US16673156

申请日：2019-11-04

Applicant: NEC Laboratories America, Inc.

Inventor： Gaurav Sharma ,  Manmohan Chandraker

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08

Abstract: A computer-implemented method is provided for domain adaptation between a source domain and a target domain. The method includes applying, by a hardware processor, an attention network to features extracted from images included in the source and target domains to provide attended features relating to a given task to be domain adapted between the source and target domains. The method further includes applying, by the hardware processor, a deformation network to at least some of the attended features to align the attended features between the source and target domains using warping to provide attended and warped features. The method also includes training, by the hardware processor, a target domain classifier using the images from the source domain. The method additionally includes classifying, by the hardware processor using the trained target domain classifier, at least one image from the target domain.

公开(公告)号：US20200065975A1

公开(公告)日：2020-02-27

申请号：US16515713

申请日：2019-07-18

Applicant: NEC Laboratories America, Inc.

Inventor： Gaurav Sharma ,  Manmohan Chandraker ,  Jinwoo Choi

IPC: G06T7/20 ,  G06K9/00

Abstract: A method is provided for drone-video-based action recognition. The method learns a transformation for each of target video clips taken from a set of target videos, responsive to original features extracted from the target video clips. The transformation corrects differences between a target drone domain corresponding to the target video clips and a source non-drone domain corresponding to source video clips taken from a set of source videos. The method adapts the target to the source domain by applying the transformation to the original features to obtain transformed features for the target video clips. The method converts the original and transformed features of same ones of the target video clips into a single classification feature for each of the target videos. The method classifies a human action in a new target video relative to the set of source videos using the single classification feature for each of the target videos.