-
21.发明申请Dimension-Wise Spatial Layout Importance Selection: An Alternative Way to Handle Object Deformation 有权维度精细空间布局重要性选择：处理对象变形的另一种方法公开(公告)号：US20140270366A1
公开(公告)日：2014-09-18
申请号：US14108212
申请日：2013-12-16
Applicant: NEC Laboratories America, Inc.
Inventor： Xiaoyu Wang , Shenghuo Zhu , Ming Yang , Yuanqing Lin
IPC: G06K9/62
CPC classification number: G06K9/6232 , G06K9/4614 , G06K9/4676 , G06K9/6257
Abstract: Systems and methods are disclosed for object detection by receiving an image; segmenting the image; extracting features from the image; and performing a dimension-wise spatial layout selection to pick up dimensions inside a discriminative spatial region for classification.
Abstract translation: 公开了通过接收图像进行物体检测的系统和方法; 分割图像; 从图像中提取特征; 以及执行维度空间布局选择以拾取鉴别空间区域内的维度以进行分类。
-
公开(公告)号：US20140050391A1
公开(公告)日：2014-02-20
申请号：US13858044
申请日：2013-04-06
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： Anelia Angelova , Shenghuo Zhu , Yuanqing Lin
IPC: G06K9/62
CPC classification number: G06K9/6267 , G06K9/00624 , G06T7/11 , G06T7/194 , G06T2207/10004 , G06T2207/20084 , G06T2207/30188
Abstract: A method for fine-grained image classification on an image includes automatically segmenting one or more objects of interest prior to classification; and combining segmented and original image features before performing final classification.
Abstract translation: 用于图像上的细粒度图像分类的方法包括在分类之前自动分割一个或多个感兴趣对象; 并在执行最终分类之前组合分段和原始图像特征。
-
公开(公告)号：US10074041B2
公开(公告)日：2018-09-11
申请号：US15095260
申请日：2016-04-11
Applicant: NEC Laboratories America, Inc.
Inventor： Feng Zhou , Yuanqing Lin
CPC classification number: G06K9/66 , G06K9/469 , G06K9/6267 , G06K9/627 , G06N3/0454 , G06N3/084 , G06T7/0004 , G06T2207/30128
Abstract: Systems and methods are disclosed for deep learning and classifying images of objects by receiving images of objects for training or classification of the objects; producing fine-grained labels of the objects; providing object images to a multi-class convolutional neural network (CNN) having a softmax layer and a final fully connected layer to explicitly model bipartite-graph labels (BGLs); and optimizing the CNN with global back-propagation.
-
公开(公告)号：US09665802B2
公开(公告)日：2017-05-30
申请号：US14884963
申请日：2015-10-16
Applicant: NEC Laboratories America, Inc.
Inventor： Xiaoyu Wang , Tianbao Yang , Yuanqing Lin
CPC classification number: G06K9/66 , G06K9/4671 , G06K9/52 , G06K9/6256 , G06K9/6267 , G06K9/6273 , G06K2009/4666 , G06N3/0454
Abstract: Systems and methods are disclosed for classifying vehicles by performing scale aware detection; performing detection assisted sampling for convolutional neural network (CNN) training, and performing deep CNN fine-grained image classification to classify the vehicle type.
-
公开(公告)号：US20170124415A1
公开(公告)日：2017-05-04
申请号：US15342823
申请日：2016-11-03
Applicant: NEC Laboratories America, Inc.
Inventor： Wongun Choi , Yuanqing Lin , Yu Xiang , Silvio Savarese
CPC classification number: G06N3/08 , G06K9/3233 , G06K9/628 , G06N3/0454 , G06T7/73 , G06T2207/20084 , G06T2207/30261
Abstract: A computer-implemented method for detecting objects by using subcategory-aware convolutional neural networks (CNNs) is presented. The method includes generating object region proposals from an image by a region proposal network (RPN) which utilizes subcategory information, and classifying and refining the object region proposals by an object detection network (ODN) that simultaneously performs object category classification, subcategory classification, and bounding box regression. The image is an image pyramid used as input to the RPN and the ODN. The RPN and the ODN each include a feature extrapolating layer to detect object categories with scale variations among the objects.
-
Patent Agency Ranking
公开(公告)号：US20160140424A1
公开(公告)日：2016-05-19
申请号：US14884963
申请日：2015-10-16
Applicant: NEC Laboratories America, Inc.
Inventor： Xiaoyu Wang , Tianbao Yang , Yuanqing Lin
CPC classification number: G06K9/66 , G06K9/4671 , G06K9/52 , G06K9/6256 , G06K9/6267 , G06K9/6273 , G06K2009/4666 , G06N3/0454
Abstract: Systems and methods are disclosed for classifying vehicles by performing scale aware detection; performing detection assisted sampling for convolutional neural network (CNN) training, and performing deep CNN fine-grained image classification to classify the vehicle type.
Abstract translation: 公开了通过执行尺度感知检测对车辆进行分类的系统和方法; 执行卷积神经网络（CNN）训练的检测辅助采样，并进行深CNN细粒度图像分类，对车辆类型进行分类。
-
公开(公告)号：US20150371397A1
公开(公告)日：2015-12-24
申请号：US14716435
申请日：2015-05-19
Applicant: NEC Laboratories America, Inc.
Inventor： Xiaoyu Wang , Yuanqing Lin
CPC classification number: G06K9/6256 , G01B11/14 , G06K9/3241 , G06K9/4652 , G06T7/77 , G06T2207/10024 , G06T2207/20081
Abstract: An object detector includes a bottom-up object hypotheses generation unit; a top-down object search with supervised descent unit; and an object re-localization unit with a localization model.
Abstract translation: 物体检测器包括自底向上物体假设生成单元; 从下到上的对象搜索与监督下降单位; 以及具有定位模型的对象重新定位单元。
-
28.发明申请公开(公告)号：US20150117764A1
公开(公告)日：2015-04-30
申请号：US14524441
申请日：2014-10-27
Applicant: NEC Laboratories America, Inc.
Inventor： Shenghuo Zhu , Yuanqing Lin , Qi Qian
IPC: G06K9/62
CPC classification number: G06K9/6201 , G06K9/6232 , G06K9/6251
Abstract: Methods and systems for distance metric learning include generating two random projection matrices of a dataset from a d-dimensional space into an m-dimensional sub-space, where m is smaller than d. An optimization problem is solved in the m-dimensional subspace to learn a distance metric based on the random projection matrices. The distance metric is recovered in the d-dimensional space.
Abstract translation: 用于距离度量学习的方法和系统包括从d维空间向m维子空间生成数据集的两个随机投影矩阵，其中m小于d。 在m维子空间中解决了优化问题，以便基于随机投影矩阵来学习距离度量。 距离度量在d维空间中被恢复。
-
29.发明申请Window Dependent Feature Regions and Strict Spatial Layout for Object Detection 有权窗口相关特征区域和对象检测的严格空间布局公开(公告)号：US20140241623A1
公开(公告)日：2014-08-28
申请号：US14108280
申请日：2013-12-16
Applicant: NEC Laboratories America, Inc.
Inventor： Xiaoyu Wang , Ming Yang , Yuanqing Lin , Shenghuo Zhu
IPC: G06K9/62
CPC classification number: G06K9/6257 , G06K9/4642 , G06K9/6202 , G06K9/6211 , G06K9/6212
Abstract: Systems and methods for object detection by receiving an image; segmenting the image and identifying candidate bounding boxes which may contain an object; for each candidate bounding box, dividing the box into overlapped small patches, and extracting dense features from the patches; during a training phase, applying a learning process to learn one or more discriminative classification models to classify negative boxes and positive boxes; and during an operational phase, for a new box generated from the image, applying the learned classification model to classify whether the box contains an object.
Abstract translation: 通过接收图像进行物体检测的系统和方法; 分割图像并识别可能包含对象的候选边界框; 对于每个候选边界框，将框分成重叠的小块，并从补丁中提取密集特征; 在培训阶段，应用学习过程学习一个或多个歧视性分类模型，以对负面框和正面框进行分类; 并且在操作阶段期间，对于从图像生成的新框，应用所学习的分类模型来分类所述框是否包含对象。
-
公开(公告)号：US08761510B2
公开(公告)日：2014-06-24
申请号：US13676494
申请日：2012-11-14
Applicant: NEC Laboratories America, Inc.
Inventor： Olga Russakovsky , Yuanqing Lin , Kai Yu , Fei-Fei Li
CPC classification number: G06K9/62 , G06K9/00624 , G06K9/3233 , G06K9/46 , G06K9/6256
Abstract: A method is provided for classifying an image. The method includes inferring location information of an object of interest in an input representation of the image. The method further includes determining foreground object features and background object features from the input representation of the image. The method additionally includes pooling the foreground object features separately from the background object features using the location information to form a new representation of the image. The new representation is different than the input representation of the image. The method also includes classifying the image based on the new representation of the image.
Abstract translation: 提供了一种用于对图像进行分类的方法。 该方法包括在图像的输入表示中推断感兴趣对象的位置信息。 该方法还包括从图像的输入表示中确定前景对象特征和背景对象特征。 该方法还包括使用位置信息与背景对象特征分开地集合前景对象特征以形成图像的新表示。 新的表示与图像的输入表示不同。 该方法还包括基于图像的新表示对图像进行分类。
-
-
-
-
-
-
-
-
-
Search Results
30
records
(took 0.031 seconds)
