中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

215 records (took 0.021 seconds)

    Moving Object Localization in 3D Using a Single Camera
    41.
    发明申请
    Moving Object Localization in 3D Using a Single Camera 有权
    使用单个相机在3D中移动对象本地化

    公开(公告)号：US20140270484A1

    公开(公告)日：2014-09-18

    申请号：US14184766

    申请日：2014-02-20

    Applicant: NEC Laboratories America, Inc.

    Inventor： Manmohan Chandraker ,  Shiyu Song ,  Yuanqing Lin ,  Xiaoyu Wang

    IPC: G06K9/00

    CPC classification number: G06T7/2033 ,  G06K9/00805 ,  G06T7/246 ,  G06T7/277 ,  G06T7/579 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30252

    Abstract: Systems and methods are disclosed for autonomous driving with only a single camera by moving object localization in 3D with a real-time framework that harnesses object detection and monocular structure from motion (SFM) through the ground plane estimation; tracking feature points on moving cars a real-time framework to and use the feature points for 3D orientation estimation; and correcting scale drift with ground plane estimation that combines cues from sparse features and dense stereo visual data.

    Abstract translation: 公开的系统和方法仅用单个摄像机进行自主驾驶，通过利用来自运动（SFM）的对象检测和单目结构通过接地平面估计的实时框架来移动3D物体定位; 跟踪移动汽车上的特征点实时框架并使用特征点进行3D定位估计; 并且通过地面平面估计来校正尺度漂移，其结合来自稀疏特征和密集立体视觉数据的线索。

    OPTIMIZING MODELS FOR OPEN-VOCABULARY DETECTION
    42.
    发明申请
    OPTIMIZING MODELS FOR OPEN-VOCABULARY DETECTION 有权

    公开(公告)号：US20240378454A1

    公开(公告)日：2024-11-14

    申请号：US18659738

    申请日：2024-05-09

    Applicant: NEC Laboratories America, Inc.

    Inventor： Samuel Schulter ,  Yumin Suh ,  Manmohan Chandraker ,  Vijay Kumar Baikampady Gopalkrishna

    IPC: G06N3/096

    Abstract: Systems and methods for optimizing models for open-vocabulary detection. Region proposals can be obtained by employing a pre-trained vision-language model and a pre-trained region proposal network. Object feature predictions can be obtained by employing a trained teacher neural network with the region proposals. Object feature predictions can be filtered above a threshold to obtain pseudo labels. A student neural network with a split-and-fusion detection head can be trained by utilizing the region proposals, base ground truth class labels and the pseudo labels. The pseudo labels can be optimized by reducing the noise from the pseudo labels by employing the trained split-and-fusion detection head of the trained student neural network to obtain optimized object detections. An action can be performed relative to a scene layout based on the optimized object detections.

    Domain adaptation for structured output via disentangled representations
    48.
    发明授权
    Domain adaptation for structured output via disentangled representations 有权

    公开(公告)号：US11604943B2

    公开(公告)日：2023-03-14

    申请号：US16400376

    申请日：2019-05-01

    Applicant: NEC Laboratories America, Inc.

    Inventor： Yi-Hsuan Tsai ,  Samuel Schulter ,  Kihyuk Sohn ,  Manmohan Chandraker

    IPC: G06K9/62 ,  G06N3/08

    Abstract: Systems and methods for domain adaptation for structured output via disentangled representations are provided. The system receives a ground truth of a source domain. The ground truth is used in a task loss function for a first convolutional neural network that predicts at least one output based on inputs from the source domain and a target domain. The system clusters the ground truth of the source domain into a predetermined number of clusters, and predicts, via a second convolutional neural network, a structure of label patches. The structure includes an assignment of each of the at least one output of the first convolutional neural network to the predetermined number of clusters. A cluster loss is computed for the predicted structure of label patches, and an adversarial loss function is applied to the predicted structure of label patches to align the source domain and the target domain on a structural level.

    VOTING-BASED APPROACH FOR DIFFERENTIALLY PRIVATE FEDERATED LEARNING
    50.
    发明申请
    VOTING-BASED APPROACH FOR DIFFERENTIALLY PRIVATE FEDERATED LEARNING 有权

    公开(公告)号：US20220108226A1

    公开(公告)日：2022-04-07

    申请号：US17491663

    申请日：2021-10-01

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xiang Yu ,  Yi-Hsuan Tsai ,  Francesco Pittaluga ,  Masoud Faraki ,  Manmohan Chandraker ,  Yuqing Zhu

    IPC: G06N20/20 ,  G06N5/02 ,  G06N5/04

    Abstract: A method for employing a general label space voting-based differentially private federated learning (DPFL) framework is presented. The method includes labeling a first subset of unlabeled data from a first global server, to generate first pseudo-labeled data, by employing a first voting-based DPFL computation where each agent trains a local agent model by using private local data associated with the agent, labeling a second subset of unlabeled data from a second global server, to generate second pseudo-labeled data, by employing a second voting-based DPFL computation where each agent maintains a data-independent feature extractor, and training a global model by using the first and second pseudo-labeled data to provide provable differential privacy (DP) guarantees for both instance-level and agent-level privacy regimes.

Patent Agency Ranking