公开(公告)号：US20220144256A1

公开(公告)日：2022-05-12

申请号：US17521139

申请日：2021-11-08

Applicant: NEC Laboratories America, Inc.

Inventor： Sriram Nochur Narayanan ,  Ramin Moslemi ,  Francesco Pittaluga ,  Buyu Liu ,  Manmohan Chandraker

IPC: B60W30/09 ,  G06F16/29 ,  G06N3/08 ,  B60W30/095 ,  G08G1/16

Abstract: A method for driving path prediction is provided. The method concatenates past trajectory features and lane centerline features in a channel dimension at an agent's respective location in a top view map to obtain concatenated features thereat. The method obtains convolutional features derived from the top view map, the concatenated features, and a single representation of the training scene the vehicle and agent interactions. The method extracts hypercolumn descriptor vectors which include the convolutional features from the agent's respective location in the top view map. The method obtains primary and auxiliary trajectory predictions from the hypercolumn descriptor vectors. The method generates a respective score for each of the primary and auxiliary trajectory predictions. The method trains a vehicle trajectory prediction neural network using a reconstruction loss, a regularization loss objective, and an IOC loss objective responsive to the respective score for each of the primary and auxiliary trajectory predictions.

公开(公告)号：US20220121953A1

公开(公告)日：2022-04-21

申请号：US17496214

申请日：2021-10-07

Applicant: NEC Laboratories America, Inc.

Inventor： Yumin Suh ,  Xiang Yu ,  Masoud Faraki ,  Manmohan Chandraker ,  Weijian Deng

IPC: G06N3/08 ,  G06N3/04

Abstract: A method for multi-task learning via gradient split for rich human analysis is presented. The method includes extracting images from training data having a plurality of datasets, each dataset associated with one task, feeding the training data into a neural network model including a feature extractor and task-specific heads, wherein the feature extractor has a feature extractor shared component and a feature extractor task-specific component, dividing filters of deeper layers of convolutional layers of the feature extractor into N groups, N being a number of tasks, assigning one task to each group of the N groups, and manipulating gradients so that each task loss updates only one subset of filters.

公开(公告)号：US11301716B2

公开(公告)日：2022-04-12

申请号：US16515593

申请日：2019-07-18

Applicant: NEC Laboratories America, Inc.

Inventor： Gaurav Sharma ,  Manmohan Chandraker ,  Jinwoo Choi

IPC: G06T7/20 ,  G06K9/00 ,  G06K9/62 ,  G06T7/33 ,  G06K9/03

Abstract: A method is provided for unsupervised domain adaptation for video classification. The method learns a transformation for each 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 domain corresponding to target video clips and a source 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 extracted to obtain transformed features for the plurality of 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 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：US11222409B2

公开(公告)日：2022-01-11

申请号：US16867805

申请日：2020-05-06

Applicant: NEC Laboratories America, Inc.

Inventor： Quoc-Huy Tran ,  Bingbing Zhuang ,  Pan Ji ,  Manmohan Chandraker

IPC: G06T5/00 ,  G06T7/50 ,  G06N3/04

Abstract: A method for correcting blur effects is presented. The method includes generating a plurality of images from a camera, synthesizing blurred images from sharp image counterparts to generate training data to train a structure-and-motion-aware convolutional neural network (CNN), and predicting a camera motion and a depth map from a single blurred image by employing the structure-and-motion-aware CNN to remove blurring from the single blurred image.

公开(公告)号：US11087142B2

公开(公告)日：2021-08-10

申请号：US16567236

申请日：2019-09-11

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Manmohan Chandraker ,  Shuyang Dai ,  Kihyuk Sohn

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62

Abstract: Systems and methods for recognizing fine-grained objects are provided. The system divides unlabeled training data from a target domain into two or more target subdomains using an attribute annotation. The system ranks the target subdomains based on a similarity to the source domain. The system applies multiple domain discriminators between each of the target subdomains and a mixture of the source domain and preceding target domains. The system recognizes, using the multiple domain discriminators for the target domain, fine-grained objects.

公开(公告)号：US20210110210A1

公开(公告)日：2021-04-15

申请号：US17128535

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 ,  G06K9/00 ,  G06K9/32 ,  B60W30/095 ,  B60W30/09 ,  B60W10/20 ,  B60W10/18 ,  B60W50/00 ,  G08G1/16 ,  G06N3/08

Abstract: Systems and methods for lane marking and road sign recognition 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 one or more road scenes having lane markings and road signs. 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：US20210042937A1

公开(公告)日：2021-02-11

申请号：US16939604

申请日：2020-07-27

Applicant: NEC Laboratories America, Inc.

Inventor： Pan Ji ,  Quoc-Huy Tran ,  Manmohan Chandraker ,  Yuliang Zou

IPC: G06T7/246 ,  G06T7/579

Abstract: A computer-implemented method for implementing a self-supervised visual odometry framework using long-term modeling includes, within a pose network of the self-supervised visual odometry framework including a plurality of pose encoders, a convolution long short-term memory (ConvLSTM) module having a first-layer ConvLSTM and a second-layer ConvLSTM, and a pose prediction layer, performing a first stage of training over a first image sequence using photometric loss, depth smoothness loss and pose cycle consistency loss, and performing a second stage of training to finetune the second-layer ConvLSTM over a second image sequence longer than the first image sequence.

公开(公告)号：US10852749B2

公开(公告)日：2020-12-01

申请号：US16100445

申请日：2018-08-10

Applicant: NEC Laboratories America, Inc.

Inventor： Quoc-Huy Tran ,  Manmohan Chandraker ,  Hyo Jin Kim

IPC: G05D1/08 ,  G06T7/73 ,  G05D1/00 ,  G08G5/04 ,  B64C39/02 ,  G08G5/00 ,  G06N3/04 ,  G06N3/08 ,  G06N5/04 ,  G06T7/00 ,  G06F16/29 ,  G01C21/32

Abstract: A computer-implemented method, system, and computer program product are provided for pose estimation. The method includes receiving, by a processor, a plurality of images from one or more cameras. The method also includes generating, by the processor with a feature extraction convolutional neural network (CNN), a feature map for each of the plurality of images. The method additionally includes estimating, by the processor with a feature weighting network, a score map from a pair of the feature maps. The method further includes predicting, by the processor with a pose estimation CNN, a pose from the score map and a combined feature map. The method also includes controlling an operation of a processor-based machine to change a state of the processor-based machine, responsive to the pose.

公开(公告)号：US20200234467A1

公开(公告)日：2020-07-23

申请号：US16736451

申请日：2020-01-07

Applicant: NEC Laboratories America, Inc.

Inventor： Quoc-Huy Tran ,  Bingbing Zhuang ,  Pan Ji ,  Manmohan Chandraker

IPC: G06T7/80 ,  G06T7/64 ,  G06T5/00 ,  G06N3/08

Abstract: Systems and methods for camera self-calibration are provided. The method includes receiving real uncalibrated images, and estimating, using a camera self-calibration network, multiple predicted camera parameters corresponding to the real uncalibrated images. Deep supervision is implemented based on a dependence order between the plurality of predicted camera parameters to place supervision signals across multiple layers according to the dependence order. The method also includes determining calibrated images using the real uncalibrated images and the predicted camera parameters.

公开(公告)号：US10474883B2

公开(公告)日：2019-11-12

申请号：US15803292

申请日：2017-11-03

Applicant: NEC Laboratories America, Inc.

Inventor： Xiang Yu ,  Kihyuk Sohn ,  Manmohan Chandraker ,  Xi Peng

IPC: G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G08B13/196 ,  G06K9/62

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.