-
公开(公告)号：US20210125519A1
公开(公告)日：2021-04-29
申请号：US16662072
申请日：2019-10-24
Applicant: International Business Machines Corporation
Inventor： Wu Song Fang , Su Liu , Ting Chen , Zhi Kong
IPC: G09B19/00 , G06F16/735 , G06K9/00 , G06F3/0354 , G09B5/02
Abstract: Embodiments describe an approach for concurrently managing a video display and an application user interface. Embodiments describe generating a translucent mask video display over a computer-implemented application and displaying a video in the translucent mask video display over the computer-implemented application. Additionally, embodiments describe detecting user activity associated with the computer-implemented application and pausing the video in the translucent mask video display when the user activity is detected. Responsive to an end to the user activity, embodiments describe translating the detected user activity as a set of computer operations, outputting the set of computer operations for performance on the computer-implemented application, and resuming the video in the translucent mask video display.
-
公开(公告)号：US20200073628A1
公开(公告)日：2020-03-05
申请号：US16116200
申请日：2018-08-29
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Wu Song Fang , Si Bin Fan , Ting Chen , Xing Xing Jing , Xiao Ying Zhou , Bin Xiong
Abstract: A method, a device and a computer program product for content collaboration are proposed. One or more computer processors determine voice identification information of a first user based on a voice input from the first user. The one or more computer processors determine a focus for the first user based on the voice identification information, the focus for the first user associated with first content appearing on a screen of the first user. The one or more computer processors set a focus for a second user to be same as the focus for the first user, the focus for the second user associated with second content displayed on a screen of the second user.
-
公开(公告)号：US09349105B2
公开(公告)日：2016-05-24
申请号：US14133193
申请日：2013-12-18
Applicant: International Business Machines Corporation
Inventor： David J. Beymer , Karen W. Brannon , Ting Chen , Moritz A. W. Hardt , Ritwik K. Kumar , Tanveer F. Syeda-Mahmood
CPC classification number: G06N99/005
Abstract: Machine learning solutions compensate for data missing from input (training) data and thereby arrive at a predictive model that is based upon, and consistent with, the training data. The predictive model can be generated within a learning algorithm framework by transforming the training data to generate modality or similarity kernels. Similarity values can be generated for these missing similarity values.
Abstract translation: 机器学习解决方案可以补偿输入（训练）数据丢失的数据，从而达到基于并与训练数据一致的预测模型。 可以通过将训练数据转换为生成模态或相似性内核，在学习算法框架内生成预测模型。 可以为这些缺失的相似度值生成相似度值。
-
公开(公告)号：US20150170055A1
公开(公告)日：2015-06-18
申请号：US14133193
申请日：2013-12-18
Applicant: International Business Machines Corporation
Inventor： David J. Beymer , Karen W. Brannon , Ting Chen , Moritz A. W. Hardt , Ritwik K. Kumar , Tanveer F. Syeda-Mahmood
IPC: G06N99/00
CPC classification number: G06N99/005
Abstract: Machine learning solutions compensate for data missing from input (training) data and thereby arrive at a predictive model that is based upon, and consistent with, the training data. The predictive model can be generated within a learning algorithm framework by transforming the training data to generate modality or similarity kernels. Similarity values can be generated for these missing similarity values.
Abstract translation: 机器学习解决方案可以补偿输入（训练）数据丢失的数据，从而达到基于并与训练数据一致的预测模型。 可以通过将训练数据转换为生成模态或相似性内核，在学习算法框架内生成预测模型。 可以为这些缺失的相似度值生成相似度值。
-
Patent Agency Ranking
公开(公告)号：US11722576B2
公开(公告)日：2023-08-08
申请号：US16188708
申请日：2018-11-13
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Si Bin Fan , Wu Song Fang , Xing Xing Jing , Xiao Ying Zhou , Bin Xiong , Ting Chen
IPC: H04L67/306 , G06Q50/00
CPC classification number: H04L67/306 , G06Q50/01
Abstract: A first content and a second content of a first user are obtained. The second content is configured by the first user to be displayed to a second user instead of the first content. A familiarity degree between the first user and the second user are determined. A third content is generated based on the first content, the second content, and the familiarity degree. The third content is displayed to the second user.
-
公开(公告)号：US11645803B2
公开(公告)日：2023-05-09
申请号：US16987464
申请日：2020-08-07
Applicant: International Business Machines Corporation
Inventor： Jian Jun Wang , Ting Chen , Shi Hui Gui , Li Yi Zhou , Jing Xia , Yidan Lei
IPC: G06T13/80 , G06K9/00 , G11B27/031 , G06V20/40 , G06F3/0482
CPC classification number: G06T13/80 , G06V20/46 , G11B27/031 , G06F3/0482 , G06T2200/24
Abstract: According to an embodiment, a source object presented in a source video is identified. Attribute information of the source object in respective frames of a sequence of source frames in the source video is identified. The attribute information represents an animation effect associated with the source object across the sequence of source frames. The attribute information is provided for use in reproducing the animation effect in a target video.
-
公开(公告)号：US11094222B2
公开(公告)日：2021-08-17
申请号：US16662072
申请日：2019-10-24
Applicant: International Business Machines Corporation
Inventor： Wu Song Fang , Su Liu , Ting Chen , Zhi Kong
IPC: G06F3/048 , G09B19/00 , G06F16/735 , G09B5/02 , G06F3/0354 , G06K9/00
Abstract: Embodiments describe an approach for concurrently managing a video display and an application user interface. Embodiments describe generating a translucent mask video display over a computer-implemented application and displaying a video in the translucent mask video display over the computer-implemented application. Additionally, embodiments describe detecting user activity associated with the computer-implemented application and pausing the video in the translucent mask video display when the user activity is detected. Responsive to an end to the user activity, embodiments describe translating the detected user activity as a set of computer operations, outputting the set of computer operations for performance on the computer-implemented application, and resuming the video in the translucent mask video display.
-
公开(公告)号：US20240404559A1
公开(公告)日：2024-12-05
申请号：US18325091
申请日：2023-05-29
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Wei Jun Zheng , Jian Jun Wang , Yue Gao , Ting Chen , Chun Hong Zheng , Yin Hu
IPC: G11B27/031
Abstract: A method for accelerated video editing that includes providing a video, segmenting, using a segmentation module, the video into a number of clips, and automatically computing, for each clip of the number of clips, corresponding metadata representing at least one attribute of the clip based on an analysis of contents of each clip of the plurality of clips. A profile script is generated based on the corresponding metadata, the profile script is generated to include one or more editing actions to be performed on a section of the video that corresponds to at least one identified clip from the number of clips. An editing tool is used to automatically edit the video based on the profile script to generate an edited video.
-
公开(公告)号：US20150278707A1
公开(公告)日：2015-10-01
申请号：US14230400
申请日：2014-03-31
Applicant: International Business Machines Corporation
Inventor： David J. Beymer , Karen W. Brannon , Ting Chen , Ritwik K. Kumar , Tanveer Syeda-Mahmood
CPC classification number: G06N20/00
Abstract: Embodiments relate to creating a classification rule by combining classifiers. Aspects include receiving N training samples d, wherein each of the N training samples d includes a label l, receiving T classifiers C, and initializing a first random weight vector α for the N training samples d. Aspects also include initializing a second random weight vector β for the T classifiers C and creating, by a processor, the classification rule by identifying a combination of one or more of the T classifiers C that best approximates the label l for each of the N training samples d based on the first random weight vector and the second random weight vector β.
Abstract translation: 实施例涉及通过组合分类器来创建分类规则。 方面包括接收N个训练样本d，其中N个训练样本d中的每一个包括标签l，接收T分类器C，以及初始化N个训练样本d的第一随机加权矢量α。 方面还包括初始化第二随机权重向量＆bgr; 对于T分类器C，并且由处理器通过基于第一随机权重向量识别对N个训练样本d中的每一个最接近标签l的一个或多个T分类器C的组合来创建分类规则;以及 第二随机权重向量＆bgr。
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.022 seconds)
