公开(公告)号：WO2020040929A1

公开(公告)日：2020-02-27

申请号：PCT/US2019/043544

申请日：2019-07-26

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： SHARMA, Gaurav ,  CHANDRAKER, Manmohan ,  CHOI, Jinwoo

IPC: G06K9/00 ,  G06N3/02

Abstract: A method is provided for drone- video-based action recognition. The method learns (220) 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 (225) 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 (230) 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 (240) 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：WO2021242520A1

公开(公告)日：2021-12-02

申请号：PCT/US2021/031929

申请日：2021-05-12

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： SHARMA, Gaurav ,  CHOI, Jinwoo

IPC: G06N3/08 ,  G06N3/04

Abstract: A method is provided for Cross Video Temporal Difference (CVTD) learning. The method adapts (540) a source domain video to a target domain video using a CVTD loss. The source domain video is annotated, and the target domain video is unannotated. The CVTD loss is computed by quantizing (510A) clips derived from the source and target domain videos by dividing the source domain video into source domain clips and the target domain video into target domain clips. The CVTD loss is further computed by sampling (510B) two clips from each of the source domain clips and the target domain clips to obtain four sampled clips including a first source domain clip, a second source domain clip, a first target domain clip, and a second target domain clip. The CVTD loss is computed (510D) as | (second source domain clip – first source domain clip) – (second target domain clip – first target domain clip).

公开(公告)号：WO2021041176A1

公开(公告)日：2021-03-04

申请号：PCT/US2020/047312

申请日：2020-08-21

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： SHARMA, Gaurav ,  SCHULTER, Samuel ,  CHOI, Jinwoo

IPC: G06K9/00 ,  G06N10/00 ,  G06N5/04

Abstract: A method for performing video domain adaptation for human action recognition is presented. The method includes using (701) annotated source data from a source video and unannotated target data from a target video in an unsupervised domain adaptation setting, identifying and aligning (703) discriminative clips in the source and target videos via an attention mechanism, and learning (705) 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：WO2021243029A1

公开(公告)日：2021-12-02

申请号：PCT/US2021/034528

申请日：2021-05-27

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： CHANDRAKER, Manmohan ,  WANG, Ting ,  XU, Xiang ,  PITTALUGA, Francesco ,  SHARMA, Gaurav ,  TSAI, Yi-Hsuan ,  FARAKI, Masoud ,  CHEN, Yuheng ,  TIAN, Yue ,  HUANG, Ming-Fang ,  FANG, Jian

IPC: G06K9/00 ,  G06N3/08

Abstract: Methods and systems for training a neural network include generating (801) an image of a mask. A copy of an image is generated (302) from an original set of training data. The copy is altered (302) to add the image of a mask to a face detected within the copy. An augmented set of training data is generated (302) that includes the original set of training data and the altered copy. A neural network model is trained (304) to recognize masked faces using the augmented set of training data.

公开(公告)号：WO2021097048A1

公开(公告)日：2021-05-20

申请号：PCT/US2020/060169

申请日：2020-11-12

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： SCHULTER, Samuel ,  SHARMA, Gaurav ,  TSAI, Yi-hsuan ,  CHANDRAKER, Manmohan ,  ZHAO, Xiangyun

IPC: G06T7/187 ,  G06T7/11 ,  G06K9/00

Abstract: Methods and systems for object detection include training (204) dataset- specific object detectors using respective annotated datasets, each of the annotated datasets including annotations for a respective set of one or more object classes. The annotated datasets are cross-annotated (206) using the dataset-specific object detectors. A unified object detector is trained (208), using the cross-annotated datasets, to detect all of the object classes of the annotated datasets. Objects are detected (210) in an input image using the unified object detector.