公开(公告)号：US20240022759A1

公开(公告)日：2024-01-18

申请号：US18361887

申请日：2023-07-30

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Umar Asif ,  Lenin Mehedy ,  Jianbin Tang

IPC: H04N19/54 ,  H04N21/234 ,  G06N20/00 ,  H04N19/23 ,  G06V10/46

CPC classification number: H04N19/54 ,  H04N21/23418 ,  G06N20/00 ,  H04N19/23 ,  G06V10/462

Abstract: A computer-implemented method of decoding video data in multiple resolution formats includes receiving an encoded video stream including a salient data and a non-salient data, the salient data having a higher resolution format than the non-salient data. The video stream is decoded into the non-salient data in a lower-resolution format and the salient data in the higher-resolution format. The non-salient data is reconstructed to a higher resolution format. The salient data and the reconstructed non-salient data are combined to form a video stream in the higher-resolution format of the salient data.

公开(公告)号：US20220101185A1

公开(公告)日：2022-03-31

申请号：US17036248

申请日：2020-09-29

Applicant: International Business Machines Corporation

Inventor： Umar Asif ,  Stefan von Cavallar ,  Jianbin Tang ,  Stefan Harrer

IPC: G06N20/00 ,  G06K9/62

Abstract: A machine learning model can be updated based on collected data (i.e., initially unlabeled data). The unlabeled data can be labeled based on comparisons to labeled data. The newly labeled data, referred to as “weak labeled data” (as it was labeled without direct input of a professional) can then be used as training data in order to retrain the machine learning model.

公开(公告)号：US20220101184A1

公开(公告)日：2022-03-31

申请号：US17036218

申请日：2020-09-29

Applicant: International Business Machines Corporation

Inventor： Umar Asif ,  Stefan von Cavallar ,  Jianbin Tang ,  Stefan Harrer

IPC: G06N20/00 ,  G06N3/08

Abstract: A machine learning model can be optimized for deployment on a device based on hardware specifications of the device. An existing model is acquired and pruned to reduce hardware resource consumption of the model. The pruned model is then trained based on training data. The pruned model is also trained based on a collection of “teacher” models. Performance of the trained model is then evaluated and compared to performance requirements, which can be based on the hardware specifications of a device.

公开(公告)号：US10448002B2

公开(公告)日：2019-10-15

申请号：US15906487

申请日：2018-02-27

Applicant: International Business Machines Corporation

Inventor： Feng Cao ,  Jianbin Tang ,  Yini Wang ,  Ziyuan Wang

IPC: G02F1/07 ,  H04N13/337 ,  G02F1/01 ,  G09G5/00 ,  H04N13/398 ,  G02B27/28 ,  G02F1/09 ,  G02C7/10 ,  H04N13/30

Abstract: There is provided a system and method for providing privacy viewing of an output from a electronic display, including a first polarizer configured to polarize a display signal at a first polarization angle; a second polarizer configured to polarize a noise signal at a second polarization angle orthogonal to the first polarization angle; a combiner configured to combine the polarized display signal and the polarized noise signal, and a third polarizer configured to receive the output of the electronic display and polarize the combined polarized display and noise signal at the first polarization angle. The system includes first and second polarization rotators configured to rotate the first and second polarization angles of the combined polarized display and noise signals prior to being output by the electronic display and prior to being received by the third polarizer.

公开(公告)号：US20180114117A1

公开(公告)日：2018-04-26

申请号：US15299626

申请日：2016-10-21

Applicant: International Business Machines Corporation

Inventor： Yonghua Lin ,  Jianbin Tang ,  Junsong Wang

IPC: G06N3/10 ,  G06N3/08 ,  G06N3/04

CPC classification number: G06F9/46 ,  G06N3/063 ,  G06N3/105

Abstract: A method, system and computer program product for accelerating a deep neural network (DNN) in a field-programmable gate array (FPGA) are disclosed. The method includes receiving a DNN net file and weights, converting the received DNN net file to one or more source files, generating an executable FPGA bit file using the one or more source files, and downloading the executable FPGA bit file from the DNN conversion platform to the FPGA. Converting of the received DNN net file and the weights to the one or more source files can further include analyzing the DNN net file to identify a plurality of neural layers, decomposing one or more neural layers of the plurality of neural layers to one or more operation blocks, instantiating the one or more source files, based on the one or more operation blocks.

公开(公告)号：US20180107451A1

公开(公告)日：2018-04-19

申请号：US15293954

申请日：2016-10-14

Applicant: International Business Machines Corporation

Inventor： Stefan Harrer ,  Antonio Jose Jimeno Yepes ,  Filiz Isabel Kiral-Kornek ,  Benjamin Scott Mashford ,  Jianbin Tang

IPC: G06F7/483 ,  G06N3/08

CPC classification number: G06F7/483 ,  G06F2207/4824 ,  G06N3/0454 ,  G06N3/063

Abstract: Automatic scaling is performed on a floating point implementation of a DNN to perform scaling to a fixed point implementation. The DNN includes multiple layers in an order from a starting to an ending layer. The automatic scaling includes determining a scaling factor for each of multiple ones of the layers during training of the DNN. The scaling factor converts floating point numbers used for calculations in a layer into integer numbers to be used in the calculations. A scaling factor is determined for a selected layer, which is at a position in the order, based on scaling factors used in layers in the order prior to the position of the selected layer. The automatic scaling includes outputting the scaling factors for the multiple layers to be used for implementing the fixed point implementation of the DNN that uses integer calculations instead of floating point calculations.

公开(公告)号：US09575336B1

公开(公告)日：2017-02-21

申请号：US14876002

申请日：2015-10-06

Applicant: International Business Machines Corporation

Inventor： Feng Cao ,  Jianbin Tang ,  Yini Wang ,  Ziyuan Wang

IPC: G02F1/07 ,  G02F1/01

CPC classification number: H04N13/337 ,  G02B27/281 ,  G02C7/101 ,  G02F1/0136 ,  G02F1/09 ,  G02F2001/0139 ,  G09G5/003 ,  G09G2320/068 ,  G09G2358/00 ,  G09G2370/18 ,  H04N13/398 ,  H04N2013/405 ,  H04N2213/008

Abstract: There is provided a system and method for providing privacy viewing of an output from a electronic display, including a first polarizer configured to polarize a display signal at a first polarization angle; a second polarizer configured to polarize a noise signal at a second polarization angle orthogonal to the first polarization angle; a combiner configured to combine the polarized display signal and the polarized noise signal, and a third polarizer configured to receive the output of the electronic display and polarize the combined polarized display and noise signal at the first polarization angle. The system includes first and second polarization rotators configured to rotate the first and second polarization angles of the combined polarized display and noise signals prior to being output by the electronic display and prior to being received by the third polarizer.

Abstract translation: 提供了一种用于提供来自电子显示器的输出的隐私观看的系统和方法，包括：第一偏振器，被配置为以第一偏振角偏振显示信号; 第二偏振器，被配置为以与第一偏振角正交的第二偏振角偏振噪声信号; 配置为组合所述偏振显示信号和所述偏振噪声信号的组合器，以及配置为接收所述电子显示器的输出并且以所述第一偏振角极化所述组合偏振显示和噪声信号的第三偏振器。 该系统包括第一和第二偏振旋转器，其被配置为在由电子显示器输出之前并且在被第三偏振器接收之前旋转组合偏振显示和噪声信号的第一和第二偏振角。

公开(公告)号：US09525497B2

公开(公告)日：2016-12-20

申请号：US14717291

申请日：2015-05-20

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Yu Bo Li ,  Yong Hua Lin ,  Jianbin Tang ,  Jun Song Wang ,  Qi Jun Wang ,  Qing Wang

IPC: H04B15/00 ,  H04W72/08 ,  H04W24/10 ,  H04B1/00

CPC classification number: H04B15/00 ,  H04B1/0082 ,  H04W24/10 ,  H04W72/082

Abstract: A method for processing interference in wireless communication at a base station, wherein at least some of a plurality of (Radio Frequency) RF channels in the base station operates at a current operating frequency point assigned to the base station includes detecting interference of one or more candidate frequency points by using at least one RF channel, wherein the one or more candidate frequency points are different from the current operating frequency point; reporting result of detecting interference of the one or more candidate frequency points to a resource manager; and in response to the resource manager assigning one of the one or more candidate frequency points to the base station, notifying a user to switch from the current operating frequency point to the assigned candidate frequency point.

Abstract translation: 一种用于在基站处理无线通信中的干扰的方法，其中所述基站中的多个（射频）RF信道中的至少一些在分配给所述基站的当前操作频率点处操作包括检测一个或多个 使用至少一个RF信道的候选频率点，其中所述一个或多个候选频率点与当前操作频率点不同; 将所述一个或多个候选频点的干扰检测到资源管理器的报告结果; 并且响应于资源管理器将一个或多个候选频率点中的一个分配给基站，通知用户从当前操作频点切换到所分配的候选频点。

公开(公告)号：US09247538B2

公开(公告)日：2016-01-26

申请号：US14800154

申请日：2015-07-15

Applicant: International Business Machines Corporation

Inventor： Yong Hua Lin ,  Jianbin Tang ,  Qing Wang ,  Jun Song Wang ,  Rong Yan ,  Hai Zhan ,  Chao Zhu ,  Zhen Bo Zhu

IPC: H04W72/04 ,  H04W72/00 ,  H04W16/14 ,  H04W28/04

CPC classification number: H04W16/14 ,  H04L1/0026 ,  H04L27/2691 ,  H04W24/08 ,  H04W24/10 ,  H04W28/04 ,  H04W72/005 ,  H04W72/042 ,  H04W72/0453 ,  H04W72/082 ,  H04W74/085

Abstract: An apparatus for sharing frequencies in an orthogonal frequency-division multiplexing OFDM-based wireless communication system, wherein the OFDM-based wireless communication system comprises a base station and a mobile device that work within a radio frequency band, the method comprising: detecting an interference signal in the radio frequency band; setting by the base station, based upon the interference signal, interference indication information in a control header of a downlink frame to be sent to the mobile device, the interference indication information indicating a frequency range that is occupied by the interference signal in the radio frequency band; and sending by the base station the downlink frame to the mobile device, such that the mobile device may, based upon the interference indication information, avoid the frequency range where the interference signal is located.

Abstract translation: 一种用于在正交频分复用基于OFDM的无线通信系统中共享频率的装置，其中所述基于OFDM的无线通信系统包括在无线电频带内工作的基站和移动设备，所述方法包括：检测干扰 无线电频段信号; 由基站根据干扰信号设置要发送给移动设备的下行链路帧的控制报头中的干扰指示信息，指示由射频中的干扰信号占用的频率范围的干扰指示信息 带; 以及由所述基站向所述移动设备发送下行链路帧，使得所述移动设备可以基于所述干扰指示信息来避免所述干扰信号所在的频率范围。

公开(公告)号：US20140293895A1

公开(公告)日：2014-10-02

申请号：US14224306

申请日：2014-03-25

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Yonghua Lin ,  Jianbin Tang ,  Jun Song Wang ,  Qing Wang

IPC: H04L5/00

CPC classification number: H04L5/0062 ,  H04L5/0007 ,  H04L5/0037 ,  H04L5/0053

Abstract: A method and system for processing interference received by a wireless communication terminal. The method including: receiving interference information from the wireless communication terminal, wherein the interference information is used to identify an interfered sub-channel(s) of the wireless communication terminal; and adjusting a downlink resource allocated to the wireless communication terminal based on the interference information. The system including: a memory; a processor communicatively coupled to the memory; and a feature selection module communicatively coupled to the memory and the processor, wherein the feature selection module is configured to perform the steps of a method including: detecting interference received by a wireless communication terminal; identifying interfered sub-channel(s) of the terminal to obtain interference information of the terminal; and reporting interference information to a base station for the base station to adjust a downlink resource allocated to the terminal based on interference information.

Abstract translation: 一种用于处理由无线通信终端接收的干扰的方法和系统。 所述方法包括：从所述无线通信终端接收干扰信息，其中所述干扰信息用于识别所述无线通信终端的受干扰子信道; 以及基于所述干扰信息来调整分配给所述无线通信终端的下行链路资源。 系统包括：存储器; 通信地耦合到所述存储器的处理器; 以及通信地耦合到所述存储器和所述处理器的特征选择模块，其中所述特征选择模块被配置为执行以下方法的步骤：包括：检测由无线通信终端接收的干扰; 识别终端的受干扰子信道以获得终端的干扰信息; 并向基站报告干扰信息，以便基站根据干扰信息来调整分配给终端的下行链路资源。