中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.018 seconds)

    METHODS AND SYSTEMS FOR BOOSTING DEEP NEURAL NETWORKS FOR DEEP LEARNING
    13.
    发明申请
    METHODS AND SYSTEMS FOR BOOSTING DEEP NEURAL NETWORKS FOR DEEP LEARNING 审中-公开

    公开(公告)号：US20200026999A1

    公开(公告)日：2020-01-23

    申请号：US16475076

    申请日：2017-04-07

    Applicant: INTEL CORPORATION

    Inventor： Libin Wang ,  Yiwen Guo ,  Anbang Yao ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shangong Wang ,  Wenhua Cheng ,  Yurong Chen

    IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063 ,  G06T1/20 ,  G06K9/62

    Abstract: Methods and systems are disclosed for boosting deep neural networks for deep learning. In one example, in a deep neural network including a first shallow network and a second shallow network, a first training sample is processed by the first shallow network using equal weights. A loss for the first shallow network is determined based on the processed training sample using equal weights. Weights for the second shallow network are adjusted based on the determined loss for the first shallow network. A second training sample is processed by the second shallow network using the adjusted weights. In another example, in a deep neural network including a first weak network and a second weak network, a first subset of training samples is processed by the first weak network using initialized weights. A classification error for the first weak network on the first subset of training samples is determined. The second weak network is boosted using the determined classification error of the first weak network with adjusted weights. A second subset of training samples is processed by the second weak network using the adjusted weights.

    METHOD, APPARATUS AND SYSTEM OF VIDEO AND AUDIO SHARING AMONG COMMUNICATION DEVICES
    14.
    发明申请
    METHOD, APPARATUS AND SYSTEM OF VIDEO AND AUDIO SHARING AMONG COMMUNICATION DEVICES 审中-公开
    通信设备中视频和音频共享的方法，装置和系统

    公开(公告)号：US20150281309A1

    公开(公告)日：2015-10-01

    申请号：US14128996

    申请日：2012-12-10

    Applicant: INTEL CORPORATION

    Inventor： Qiang Li ,  Yangzhou Du ,  Wenlong Li ,  Xiaofeng Tong ,  Wei Hu ,  Lin Xu ,  Yimin Zhang

    IPC: H04L29/06 ,  G10L19/04

    CPC classification number: H04L65/607 ,  G10L19/04 ,  H04N21/235 ,  H04N21/2368 ,  H04N21/242 ,  H04N21/4307 ,  H04N21/4341 ,  H04N21/435

    Abstract: A device, method and system of video and audio sharing among communication devices, may comprise a communication device for generating and sending a packet containing information related to the video and audio, and another communication device for receiving the packet and rendering the information related to the audio and video. In some embodiments, the communication device may comprise: an audio encoding module to encode a piece of audio into an audio bit stream; an avatar data extraction module to extract avatar data from a piece of video and generate an avatar data bit stream; and a synchronization module to generate synchronization information for synchronizing the audio bit stream with the avatar parameter stream. In some embodiments, the another communication device may comprise: an audio decoding module to decode an audio bit stream into decoded audio data; an Avatar animation module to animate an Avatar model based on an Avatar data bit stream to generate an animated Avatar model; and a synchronizing and rendering module to synchronize and render the decoded audio data and the animated Avatar model by utilizing the synchronization information.

    Abstract translation: 在通信设备之间的视频和音频共享的设备，方法和系统可以包括用于生成和发送包含与视频和音频相关的信息的分组的通信设备，以及用于接收分组并呈现与 音频和视频。 在一些实施例中，通信设备可以包括：音频编码模块，用于将音频片段编码成音频比特流; 一个头像数据提取模块，用于从一条视频中提取头像数据，并生成化身数据比特流; 以及同步模块，用于生成用于使音频比特流与化身参数流同步的同步信息。 在一些实施例中，另一通信设备可以包括：音频解码模块，用于将音频比特流解码为解码的音频数据; Avatar动画模块，用于基于Avatar数据位流为Avatar模型生成动画Avatar模型; 以及同步和渲染模块，通过利用同步信息来同步和渲染解码的音频数据和动画化身模型。

    GPU OPTIMIZED AND ONLINE SINGLE GAUSSIAN BASED SKIN LIKELIHOOD ESTIMATION
    16.
    发明申请
    GPU OPTIMIZED AND ONLINE SINGLE GAUSSIAN BASED SKIN LIKELIHOOD ESTIMATION 审中-公开

    公开(公告)号：US20190065892A1

    公开(公告)日：2019-02-28

    申请号：US16080003

    申请日：2016-03-25

    Applicant: INTEL CORPORATION

    Inventor： Lin Xu ,  Liu Yang ,  Anbang Yao ,  Yurong Chen

    IPC: G06K9/62 ,  G06T7/90 ,  G06K9/00 ,  G06N7/00

    Abstract: A system for performing single Gaussian skin detection is described herein. The system includes a memory and a processor. The memory is configured to receive image data. The processor is coupled to the memory. The processor is to generate a single Gaussian skin model based on a skin dominant region associated with the image data and a single Gaussian non-skin model based on a second region associated with the image data and to classify individual pixels associated with the image data via a discriminative skin likelihood function based on the single Gaussian skin model and the single Gaussian non-skin model to generate skin label data associated with the image data.

    Methods and systems for boosting deep neural networks for deep learning
    18.
    发明授权
    Methods and systems for boosting deep neural networks for deep learning 有权

    公开(公告)号：US11790223B2

    公开(公告)日：2023-10-17

    申请号：US16475076

    申请日：2017-04-07

    Applicant: INTEL CORPORATION

    Inventor： Libin Wang ,  Yiwen Guo ,  Anbang Yao ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shandong Wang ,  Wenhua Cheng ,  Yurong Chen

    IPC: G06N3/08 ,  G06N3/063 ,  G06T1/20 ,  G06F18/21 ,  G06F18/214 ,  G06N3/045

    CPC classification number: G06N3/08 ,  G06F18/217 ,  G06F18/2148 ,  G06N3/045 ,  G06N3/063 ,  G06T1/20

    Abstract: Methods and systems are disclosed for boosting deep neural networks for deep learning. In one example, in a deep neural network including a first shallow network and a second shallow network, a first training sample is processed by the first shallow network using equal weights. A loss for the first shallow network is determined based on the processed training sample using equal weights. Weights for the second shallow network are adjusted based on the determined loss for the first shallow network. A second training sample is processed by the second shallow network using the adjusted weights. In another example, in a deep neural network including a first weak network and a second weak network, a first subset of training samples is processed by the first weak network using initialized weights. A classification error for the first weak network on the first subset of training samples is determined. The second weak network is boosted using the determined classification error of the first weak network with adjusted weights. A second subset of training samples is processed by the second weak network using the adjusted weights.

Patent Agency Ranking