公开(公告)号：WO2014198055A1

公开(公告)日：2014-12-18

申请号：PCT/CN2013/077228

申请日：2013-06-14

Applicant: INTEL CORPORATION ,  WANG, Tao ,  FU, Lianrui ,  LI, Qiang ,  LI, Jianguo ,  CHEN, Yurong ,  PENG, Ya-ti ,  ZHANG, Yimin ,  YAO, Anbang

Inventor： WANG, Tao ,  FU, Lianrui ,  LI, Qiang ,  LI, Jianguo ,  CHEN, Yurong ,  PENG, Ya-ti ,  ZHANG, Yimin ,  YAO, Anbang

IPC: G06T7/00

CPC classification number: G06K9/6211 ,  G06K9/68

Abstract: Apparatuses, methods and storage medium associated with processing an image are disclosed herein. In embodiments, a method for processing one or more images may include generating a plurality of pairs of keypoint features for a pair of images. Each pair of keypoint features may include a keypoint feature from each image. Further, for each pair of keypoint features, corresponding adjoin features may be generated. Additionally, for each pair of keypoint features, whether the adjoin features are similar may be determined. Whether the pair of images have at least one similar object may also be determined, based at least in part on a result of the determination of similarity between the corresponding adjoin features. Other embodiments may be described and claimed.

Abstract translation: 本文公开了与处理图像相关联的装置，方法和存储介质。 在实施例中，用于处理一个或多个图像的方法可以包括为一对图像生成多对关键点特征。 每对关键点特征可以包括来自每个图像的关键点特征。 此外，对于每对关键点特征，可以生成相应的邻接特征。 此外，对于每对关键点特征，可以确定邻接特征是否相似。 至少部分地基于相应邻接特征之间的相似性的确定结果，也可以确定该对图像是否具有至少一个相似对象。 可以描述和要求保护其他实施例。

公开(公告)号：WO2022047783A1

公开(公告)日：2022-03-10

申请号：PCT/CN2020/113760

申请日：2020-09-07

Applicant: INTEL CORPORATION ,  YAO, Anbang ,  ZHOU, Xiao ,  ZHANG, Guangli ,  ZHANG, Yu ,  GU, Dian

Inventor： YAO, Anbang ,  ZHOU, Xiao ,  ZHANG, Guangli ,  ZHANG, Yu ,  GU, Dian

IPC: G06N3/08 ,  G06T3/40

Abstract: Techniques related to poly-scale kernel-wise convolutional neural network layers are discussed. A poly-scale kernel-wise convolutional neural network layer is applied to an input volume to generate an output volume and include filters each having a number of filter kernels with the same sample rate and differing dilation rates optionally in a repeating pattern of dilation rate groups within each of filters with the pattern of dilation rate groups offset between the filters the poly-scale kernel-wise convolutional neural network layer.

公开(公告)号：WO2021253148A1

公开(公告)日：2021-12-23

申请号：PCT/CN2020/096035

申请日：2020-06-15

Applicant: INTEL CORPORATION ,  YAO, Anbang ,  WANG, Yikai ,  LU, Ming ,  WANG, Shandong ,  CHEN, Feng

Inventor： YAO, Anbang ,  WANG, Yikai ,  LU, Ming ,  WANG, Shandong ,  CHEN, Feng

IPC: G06K9/62

Abstract: Techniques related to implementing and training image classification networks are discussed. Such techniques include applying shared convolutional layers to input images regardless of resolution and applying normalization selectively based on the input image resolution. Such techniques further include training using mixed image size parallel training and mixed image size ensemble distillation.

公开(公告)号：WO2019068215A1

公开(公告)日：2019-04-11

申请号：PCT/CN2017/105248

申请日：2017-10-03

Applicant: INTEL CORPORATION ,  YANG, Wenlong ,  YAO, Anbang ,  NAHMIAS, Avi

Inventor： YANG, Wenlong ,  YAO, Anbang ,  NAHMIAS, Avi

IPC: G06T11/00

CPC classification number: G06T11/206 ,  G06T2200/24

Abstract: Techniques are disclosed for analyzing a graph image in a disconnected mode, e.g., when a graph is rendered as. jpeg,. gif,. png, and so on, and identifying a portion of the graph image associated with a plot/curve of interest. The identified portion of the graph image may then be utilized to generate an adjusted image. The adjusted image may therefore dynamically increase visibility of the plot/curve of interest relative to other plots/curves, and thus the present disclosures provides additional graph functionalities without access to the data originally used to generate the graph. The disconnected graph functionalities disclosed herein may be implemented within an Internet browser or other "app" that may present images depicting graphs to a user.

公开(公告)号：WO2018184208A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079726

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  YANG, Liu ,  YAO, Anbang

Inventor： YANG, Liu ,  YAO, Anbang

IPC: G06F15/76

Abstract: Methods and systems are disclosed using an execution pipeline on a multi-processor platform for deep learning network execution. In one example, a network workload analyzer receives a workload, analyzes a computation distribution of the workload, and groups the network nodes into groups. A network executor assigns each group to a processing core of the multi-core platform so that the respective processing core handle computation tasks of the received workload for the respective group.

公开(公告)号：WO2018184195A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079683

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  YAO, Anbang ,  REN, Yun ,  ZHAO, Hao ,  KONG, Tao ,  CHEN, Yurlong

Inventor： YAO, Anbang ,  REN, Yun ,  ZHAO, Hao ,  KONG, Tao ,  CHEN, Yurlong

IPC: G06K9/00

CPC classification number: G06K9/6857 ,  G06K9/00664 ,  G06K9/4628 ,  G06K9/6274

Abstract: An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.

公开(公告)号：WO2018170815A1

公开(公告)日：2018-09-27

申请号：PCT/CN2017/077815

申请日：2017-03-23

Applicant: INTEL CORPORATION ,  YANG, Liu ,  YAO, Anbang

Inventor： YANG, Liu ,  YAO, Anbang

IPC: G06N3/08 ,  G06N3/02

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to improve deep learning resource efficiency. An example apparatus includes a graph monitor to select a candidate operation node in response to receiving an operation graph, the operation graph including one or more other operation nodes, a node rule evaluator to evaluate the candidate operation node based on an operating principle, the operating principle to determine an output storage destination of the candidate operation node based on a topology of the operation graph, and a tag engine to tag the candidate operation node with a memory tag value based on the determined output storage destination.

公开(公告)号：WO2018217863A1

公开(公告)日：2018-11-29

申请号：PCT/US2018/034088

申请日：2018-05-23

Applicant: INTEL CORPORATION

Inventor： GUO, Yiwen ,  YAO, Anbang ,  ZHAO, Hao ,  LU, Ming ,  CHEN, Yurong

IPC: G06N3/04 ,  G06N3/08

Abstract: Methods and apparatus are disclosed for enhancing a binary weight neural network using a dependency tree. A method of enhancing a convolutional neural network (CNN) having binary weights includes constructing a tree for obtained binary tensors, the tree having a plurality of nodes beginning with a root node in each layer of the CNN. A convolution is calculated of an input feature map with an input binary tensor at the root node of the tree. A next node is searched from the root node of the tree and a convolution is calculated at the next node using a previous convolution result calculated at the root node of the tree. The searching of a next node from root node is repeated for all nodes from the root node of the tree, and a convolution is calculated at each next node using a previous convolution result.

公开(公告)号：WO2018217828A1

公开(公告)日：2018-11-29

申请号：PCT/US2018/033986

申请日：2018-05-22

Applicant: INTEL CORPORATION

Inventor： YAO, Anbang ,  ZHAO, Hao ,  LU, Ming ,  GUO, Yiwen ,  CHEN, Yurong

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.

公开(公告)号：WO2015089436A1

公开(公告)日：2015-06-18

申请号：PCT/US2014/070083

申请日：2014-12-12

Applicant: INTEL CORPORATION

Inventor： YAO, Anbang ,  DU, Yangzhou ,  TONG, Xiaofeng ,  WANG, Tao ,  CHEN, Yurong ,  LI, Jianguo ,  YE, Jianbo ,  LI, Wenlong ,  ZHANG, Yimin

IPC: G06T7/20

CPC classification number: G06K9/00261 ,  G06K9/00281 ,  G06K9/00315 ,  G06K9/6207

Abstract: Disclosed in some examples are various modifications to the shape regression technique for use in real-time applications, and methods, systems, and machine readable mediums which utilize the resulting facial landmark tracking methods.

Abstract translation: 在一些示例中公开了对用于实时应用的形状回归技术的各种修改，以及利用所得到的面部地标跟踪方法的方法，系统和机器可读介质。