中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

89 records (took 0.052 seconds)

    Frame removal and replacement for stop-action animation
    51.
    发明授权
    Frame removal and replacement for stop-action animation 有权

    公开(公告)号：US09870637B2

    公开(公告)日：2018-01-16

    申请号：US14575742

    申请日：2014-12-18

    Applicant: Intel Corporation

    Inventor： Glen J. Anderson ,  Kathy Yuen ,  Omesh Tickoo ,  Jamie Sherman ,  Jeffrey Ota ,  Ravishankar R. Iyer

    IPC: G06T13/80 ,  G11B27/00

    CPC classification number: G06T13/80 ,  G11B27/00

    Abstract: Various systems and methods for frame removal and replacement for stop-action animation are described herein. A system for creating a stop-motion video includes an access module to access a series of frames of an input video, and a processing module to determine whether each frame of the series of frames includes a portion of a hand and composite frames from the series of frames that do not include the portion of the hand to render an output video. A system for creating a video includes an access module to access an input video, and a video processing module to identify a physical object in the input video, track movement of the physical object in the input video to identify a path, identify a three-dimensional model of the physical object, and create an output video with the three-dimensional model in place of the physical object, the three-dimensional model following the path.

    DEVICE-BASED PERSONAL SPEECH RECOGNITION TRAINING
    53.
    发明申请
    DEVICE-BASED PERSONAL SPEECH RECOGNITION TRAINING 审中-公开
    基于设备的个人语音识别培训

    公开(公告)号：US20150161986A1

    公开(公告)日：2015-06-11

    申请号：US14365603

    申请日：2013-12-09

    Applicant: INTEL CORPORATION

    Inventor： Omesh Tickoo ,  Rameshkumar G. Illikkal ,  Anthony L. Chun ,  Hector A. Cordourier Maruri

    IPC: G10L15/06

    CPC classification number: G10L15/07

    Abstract: In embodiments, apparatuses, methods and storage media for personalized speech recognition are described. In various embodiments, a personalized speech recognition system (“PSRS”) may receive personal speech recognition training data (“PTD”) that is associated with a user to facilitate recognition of speech from the user. The PSRS may train a speech recognition module using the received PTD. The user may provide the PTD using a mobile device under control of the user. The PTD may be generated and stored on the mobile device through actions of the user, such as by using the mobile device to record a corpus of speech examples by the user. The user may subsequently facilitate provisioning of the PTD to the PSRS using the mobile device, such as through a wired or wireless network. Other embodiments may be described and claimed.

    Abstract translation: 在实施例中，描述用于个性化语音识别的装置，方法和存储介质。 在各种实施例中，个性化语音识别系统（“PSRS”）可以接收与用户相关联的个人语音识别训练数据（“PTD”），以便于从用户识别语音。 PSRS可以使用接收到的PTD训练语音识别模块。 用户可以在用户的​​控制下使用移动设备来提供PTD。 PTD可以通过用户的动作来生成和存储在移动设备上，例如通过使用移动设备来记录用户语音语料库。 用户随后可以使用移动设备（例如通过有线或无线网络）方便地向PSRS提供PTD。 可以描述和要求保护其他实施例。

    Probabilistic in-memory computing
    55.
    发明授权
    Probabilistic in-memory computing 有权

    公开(公告)号：US11900979B2

    公开(公告)日：2024-02-13

    申请号：US17508818

    申请日：2021-10-22

    Applicant: INTEL CORPORATION

    Inventor： Hai Li ,  Dmitri E. Nikonov ,  Punyashloka Debashis ,  Ian A. Young ,  Mahesh Subedar ,  Omesh Tickoo

    IPC: G11C11/16 ,  G06F7/544 ,  G11C11/54 ,  G06N3/045 ,  G06N3/047

    CPC classification number: G11C11/1673 ,  G06F7/5443 ,  G06N3/045 ,  G06N3/047 ,  G11C11/1675 ,  G11C11/1697 ,  G11C11/54

    Abstract: Embodiments of the present disclosure are directed toward probabilistic in-memory computing configurations and arrangements, and configurations of probabilistic bit devices (p-bits) for probabilistic in-memory computing. concept with emerging. A probabilistic in-memory computing device includes an array of p-bits, where each p-bit is disposed at or near horizontal and vertical wires. Each p-bit is a time-varying resistor that has a time-varying resistance, which follows a desired probability distribution. The time-varying resistance of each p-bit represents a weight in a weight matrix of a stochastic neural network. During operation, an input voltage is applied to the horizontal wires to control the current through each p-bit. The currents are accumulated in the vertical wires thereby performing respective multiply-and-accumulative (MAC) operations. Other embodiments may be described and/or claimed.

    SOURCE-FREE ACTIVE ADAPTATION TO DISTRIBUTIONAL SHIFTS FOR MACHINE LEARNING
    56.
    发明申请
    SOURCE-FREE ACTIVE ADAPTATION TO DISTRIBUTIONAL SHIFTS FOR MACHINE LEARNING 有权

    公开(公告)号：US20230137905A1

    公开(公告)日：2023-05-04

    申请号：US18089513

    申请日：2022-12-27

    Applicant: Intel Corporation

    Inventor： Amrutha Machireddy ,  Ranganath Krishnan ,  Nilesh Ahuja ,  Omesh Tickoo

    IPC: G06N3/091

    Abstract: Disclosed is an example solution to perform source-free active adaptation to distributional shifts for machine learning. The example solution includes: interface circuitry; programmable circuitry; and instructions to cause the programmable circuitry to: perform a first training of a neural network on a baseline data set associated with a first data distribution; compare data of a shifted data set to a threshold uncertainty value, wherein the threshold uncertainty value is associated with a distributional shift between the baseline data set and the shifted data set; generate a shifted data subset including items of the shifted dataset that satisfy the threshold uncertainty value; and perform a second training of the neural network based on the shifted data subset.

    Hybrid pixel-domain and compressed-domain video analytics framework
    57.
    发明授权
    Hybrid pixel-domain and compressed-domain video analytics framework 有权

    公开(公告)号：US11570466B2

    公开(公告)日：2023-01-31

    申请号：US17509246

    申请日：2021-10-25

    Applicant: Intel Corporation

    Inventor： Yiting Liao ,  Yen-Kuang Chen ,  Shao-Wen Yang ,  Vallabhajosyula S. Somayazulu ,  Srenivas Varadarajan ,  Omesh Tickoo ,  Ibrahima J. Ndiour

    IPC: H04N19/52 ,  H04N19/523 ,  H04N19/172 ,  G06V10/20 ,  G06N3/04 ,  G06K9/62

    Abstract: In one embodiment, an apparatus comprises processing circuitry to: receive, via a communication interface, a compressed video stream captured by a camera, wherein the compressed video stream comprises: a first compressed frame; and a second compressed frame, wherein the second compressed frame is compressed based at least in part on the first compressed frame, and wherein the second compressed frame comprises a plurality of motion vectors; decompress the first compressed frame into a first decompressed frame; perform pixel-domain object detection to detect an object at a first position in the first decompressed frame; and perform compressed-domain object detection to detect the object at a second position in the second compressed frame, wherein the object is detected at the second position in the second compressed frame based on: the first position of the object in the first decompressed frame; and the plurality of motion vectors from the second compressed frame.

    POTENTIAL COLLISION WARNING SYSTEM BASED ON ROAD USER INTENT PREDICTION
    58.
    发明申请
    POTENTIAL COLLISION WARNING SYSTEM BASED ON ROAD USER INTENT PREDICTION 有权

    公开(公告)号：US20220324441A1

    公开(公告)日：2022-10-13

    申请号：US17741124

    申请日：2022-05-10

    Applicant: Intel Corporation

    Inventor： David Gomez Gutierrez ,  Javier Felip Leon ,  Kshitij A. Doshi ,  Leobardo E. Campos Macias ,  Nilesh Amar Ahuja ,  Omesh Tickoo

    IPC: B60W30/095 ,  B60W50/14 ,  G06V20/58 ,  G06V40/10

    Abstract: An apparatus comprising a memory to store an observed trajectory of a pedestrian, the observed trajectory comprising a plurality of observed locations of the pedestrian over a first plurality of timesteps; and a processor to generate a predicted trajectory of the pedestrian, the predicted trajectory comprising a plurality of predicted locations of the pedestrian over the first plurality of timesteps and over a second plurality of timesteps occurring after the first plurality of timesteps; determine a likelihood of the predicted trajectory based on a comparison of the plurality of predicted locations of the pedestrian over the first plurality of timesteps and the plurality of observed locations of the pedestrian over the first plurality of timesteps; and responsive to the determined likelihood of the predicted trajectory, provide information associated with the predicted trajectory to a vehicle to warn the vehicle of a potential collision with the pedestrian.

    VIDEO SUMMARIZATION USING SEMANTIC INFORMATION
    59.
    发明申请
    VIDEO SUMMARIZATION USING SEMANTIC INFORMATION 有权

    公开(公告)号：US20210201047A1

    公开(公告)日：2021-07-01

    申请号：US17201969

    申请日：2021-03-15

    Applicant: Intel Corporation

    Inventor： Myung Hwangbo ,  Krishna Kumar Singh ,  Teahyung Lee ,  Omesh Tickoo

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04

    Abstract: Example apparatus disclosed herein are to process a first image of a first video segment from the image capture sensor with a machine learning algorithm to determine a first score for the first image, the machine learning algorithm to detect actions associated with images, the actions associated with labels. Disclosed example apparatus are also to determine a second score for the first video segment based on respective first scores for corresponding images in the first video segment. Disclosed example apparatus are further to determine, based on the second score, whether to retain the first video segment in the memory.

Patent Agency Ranking