公开(公告)号：US20240331371A1

公开(公告)日：2024-10-03

申请号：US18573973

申请日：2021-11-30

Applicant: Intel Corporation

Inventor： Yurong Chen ,  Anbang Yao ,  Ming Lu ,  Dongqi Cai ,  Xiaolong Liu

IPC: G06V10/82

CPC classification number: G06V10/82

Abstract: Methods and apparatus to perform parallel double-batched self-distillation in resource-constrained image recognition environments are disclosed herein. Example apparatus disclosed herein are to identify a source data batch and an augmented data batch, the augmented data generated based on at least one data augmentation technique. Disclosed example apparatus is also to share one or more parameters between a student neural network corresponding to the source data batch and a teacher neural network corresponding to the augmented data batch, the one or more parameters including one or more convolution layers to be shared between the teacher neural network and the student neural network. Disclosed example apparatus is further to align knowledge corresponding to the teacher neural network and the student neural network, the knowledge corresponding to the one or more parameters shared between the student neural network and the teacher neural network.

公开(公告)号：US12079914B2

公开(公告)日：2024-09-03

申请号：US17914314

申请日：2020-04-23

Applicant: Intel Corporation

Inventor： Shandong Wang ,  Yangyuxuan Kang ,  Anbang Yao ,  Ming Lu ,  Yurong Chen

IPC: G06T13/40 ,  G06T7/246 ,  G06T7/70 ,  G06T17/00

CPC classification number: G06T13/40 ,  G06T7/70 ,  G06T7/251 ,  G06T17/00 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196

Abstract: Techniques are disclosed for providing improved pose tracking of a subject using a 2D camera and generating a 3D image that recreates the pose of the subject. A 3D skeleton map is estimated from a 2D skeleton map of the subject using, for example, a neural network. A template 3D skeleton map is accessed or generated having bone segments that have lengths set using, for instance, anthropometry statistics based on a given height of the template 3D skeleton map. An improved 3D skeleton map is then produced by at least retargeting one or more of the plurality of bone segments of the estimated 3D skeleton map to more closely match the corresponding template bone segments of the template 3D skeleton map. The improved 3D skeleton map can then be animated in various ways (e.g., using various skins or graphics) to track corresponding movements of the subject.

公开(公告)号：US20240119625A1

公开(公告)日：2024-04-11

申请号：US18283414

申请日：2021-06-16

Applicant: Intel Corporation

Inventor： Ming Lu ,  Liwei Liao ,  Haihua Lin ,  Xiaofeng Tong ,  Wenlong Li ,  Jiansheng Chen ,  Yiwei He

IPC: G06T7/73 ,  G06V20/40

CPC classification number: G06T7/73 ,  G06V20/42 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06T2207/30224 ,  G06T2207/30242

Abstract: A method and system of automatically estimating a ball carrier in team sports.

公开(公告)号：US11704569B2

公开(公告)日：2023-07-18

申请号：US16615097

申请日：2018-05-23

Applicant: INTEL CORPORATION

Inventor： Yiwen Guo ,  Anbang Yao ,  Hao Zhao ,  Ming Lu ,  Yurong Chen

IPC: G06N3/08 ,  G06N3/082 ,  G06N3/042 ,  G06N3/044 ,  G06N5/01

CPC classification number: G06N3/082 ,  G06N3/042 ,  G06N3/044 ,  G06N5/01

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：US11514704B2

公开(公告)日：2022-11-29

申请号：US17057020

申请日：2018-10-02

Applicant: Intel Corporation

Inventor： Chen Ling ,  Ming Lu ,  Qiang Li ,  Wenlong Li ,  Xiaofeng Tong ,  Yikai Fang ,  Yumeng Wang

IPC: G06K9/00 ,  G06V40/10 ,  G06V20/40 ,  G06V40/20

Abstract: A video capture and processing system includes a memory configured to store a pose database. The pose database includes poses that indicate a start or stoppage in an event. The system also includes a processor operatively coupled to the memory. The processor is configured to generate a pose of an individual in a video frame of captured video of the event. The pose can be three-dimensional pose or a two-dimensional pose. The processor is also configured to determine, based on the pose database, whether the pose of the individual indicates a start or a stoppage in the event. The processor is further configured to control an upload of video of the event based on the determination of whether the pose indicates the start or the stoppage in the event.

公开(公告)号：US20220207293A1

公开(公告)日：2022-06-30

申请号：US17482875

申请日：2021-09-23

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Ming Lu ,  Yikai Wang ,  Scott Janus ,  Sungye Kim

IPC: G06K9/62 ,  G06T11/00

Abstract: Embodiments are generally directed to methods and apparatuses of spatially sparse convolution module for visual rendering and synthesis. An embodiment of a method for image processing, comprising: receiving an input image by a convolution layer of a neural network to generate a plurality of feature maps; performing spatially sparse convolution on the plurality of feature maps to generate spatially sparse feature maps; and upsampling the spatially sparse feature maps to generate an output image.

公开(公告)号：US20220180103A1

公开(公告)日：2022-06-09

申请号：US17485411

申请日：2021-09-25

Applicant: Intel Corporation

Inventor： Haihua Lin ,  Xiaofeng Tong ,  Wenlong Li ,  Ming Lu ,  Jiansheng Chen ,  Liwei Liao

IPC: G06K9/00 ,  G06T7/246 ,  G06K9/46

Abstract: Embodiments are generally directed to methods and apparatuses for determining a game status. An embodiment of a method for determining a game status comprises: detecting players and a ball in a plurality of continuous frames captured by a plurality of cameras; obtaining tracking data of the players and the ball of the plurality of continuous frames; and determining a game status for each of the plurality of continuous frames based on the tracking data of the players and the ball of the plurality of continuous frames.

公开(公告)号：US12079713B2

公开(公告)日：2024-09-03

申请号：US18142997

申请日：2023-05-03

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Hao Zhao ,  Ming Lu ,  Yiwen Guo ,  Yurong Chen

IPC: G06V10/82 ,  G06F18/214 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06V10/44 ,  G06V10/764 ,  G06V10/94 ,  G06V20/10 ,  G06V20/40 ,  G06V20/70

CPC classification number: G06N3/063 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V10/955 ,  G06V20/10 ,  G06V20/41 ,  G06V20/70

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：US20240257316A1

公开(公告)日：2024-08-01

申请号：US18615050

申请日：2024-03-25

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Ming Lu ,  Yikai Wang ,  Shandong Wang ,  Yurong Chen ,  Sungye Kim ,  Attila Tamas Afra

IPC: G06T5/50 ,  G06N3/02 ,  G06T7/13 ,  G06V40/16

CPC classification number: G06T5/50 ,  G06N3/02 ,  G06T7/13 ,  G06V40/161 ,  G06V40/171 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: The present disclosure provides an apparatus and method of guided neural network model for image processing. An apparatus may comprise a guidance map generator, a synthesis network and an accelerator. The guidance map generator may receive a first image as a content image and a second image as a style image, and generate a first plurality of guidance maps and a second plurality of guidance maps, respectively from the first image and the second image. The synthesis network may synthesize the first plurality of guidance maps and the second plurality of guidance maps to determine guidance information. The accelerator may generate an output image by applying the style of the second image to the first image based on the guidance information.

公开(公告)号：US20240242462A1

公开(公告)日：2024-07-18

申请号：US18270823

申请日：2021-02-02

Applicant: Intel Corporation

Inventor： Liwei Liao ,  Ming Lu ,  Xiaofeng Tong ,  Wenlong Li

IPC: G06V10/25 ,  G06T7/246 ,  G06T7/292 ,  G06V10/82 ,  G06V20/40

CPC classification number: G06V10/25 ,  G06T7/246 ,  G06T7/292 ,  G06V10/82 ,  G06V20/42 ,  G06V20/46 ,  G06T2207/20072 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06T2207/30224 ,  G06T2207/30242

Abstract: Techniques related to game focus estimation in team sports for multi-camera immersive video are discussed. Such techniques include selecting regions of a scene comprising a sporting event, generating a node graph and sets of features for the selected regions, and determining a game focus region of the selected regions by applying a graph node classification model based on the node graph and sets of features.