公开(公告)号：WO2023076985A2

公开(公告)日：2023-05-04

申请号：PCT/US2022/078761

申请日：2022-10-27

申请人： ALIGN TECHNOLOGY, INC. ,  VYSOKANOV, Boris Aleksandrovich ,  KADRUL, Vera Vladimirovna ,  PROKOSHEV, Valery ,  BOCHENKO, Andrew ,  KARSAKOV, Aleksandr Sergeevich

发明人： CHEKH, Dmitry Yurievich ,  LOPES, David Patrick ,  MIRYAHA, Vladislav Andreevich ,  AGILINA, Elena ,  CHIKHANOVA, Anastasia ,  LISITSIN, Alexey ,  KHZMALYAN, David ,  HARRISON, Travis ,  BLANCO, Samuel ,  SUROV, Sergey Borisovich ,  SABINA, Michael ,  DESHPANDE, Akhil

IPC分类号： G16H20/40 ,  A61C7/00 ,  G16H50/50 ,  A61C13/00 ,  A61C9/00 ,  A61B5/0088 ,  A61C13/0004 ,  A61C13/34 ,  A61C5/77 ,  A61C7/002 ,  A61C9/0053 ,  G06T19/20 ,  G06T2200/24 ,  G06T2207/10016 ,  G06T2207/20084 ,  G06T2207/30036 ,  G06T2207/30201 ,  G06T2210/41 ,  G06T2219/2004 ,  G06T2219/2021 ,  G06T7/0012 ,  G06T7/0014 ,  G06V20/46 ,  G06V40/161 ,  G06V40/171 ,  G16H30/40

摘要： Systems and methods for planning a treatment for a patient's teeth are provided. In some embodiments, a method includes receiving a treatment plan including a target tooth arrangement including a change in mass of at least one tooth. The method can also include outputting a graphical user interface including a visualization of the treatment plan. The visualization can include a plurality of digital models, each digital model representing an intermediate tooth arrangement configured to adjust the patient's teeth toward the target tooth arrangement. The visualization can also include a heatmap overlaid onto at least one digital model of the plurality of digital models. The heatmap can show a difference in tooth mass between the target tooth arrangement and the corresponding at least one intermediate tooth arrangement of the at least one digital model.

公开(公告)号：WO2023273628A1

公开(公告)日：2023-01-05

申请号：PCT/CN2022/092377

申请日：2022-05-12

申请人： 腾讯科技（深圳）有限公司

发明人： 郭卉

IPC分类号： G06K9/00 ,  G06F18/22 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V20/40 ,  G06V20/46

摘要： 本申请实施例公开了一种视频循环识别方法、装置、计算机设备及存储介质，包括：获取待识别视频的目标视频片段对，确定第一目标编码特征和第二目标编码特征；获取目标网络模型；将第一目标编码特征输入至与第一模态信息相关联的第一目标序列模型，输出目标视频片段对的第一目标相似结果；将第二目标编码特征输入至与第二模态信息相关联的第二目标序列模型，输出目标视频片段对的第二目标相似结果；将第一目标相似结果和第二目标相似结果进行比对，得到目标视频片段对的循环比对结果。采用本申请实施例，可以提高视频循环识别的准确率。

公开(公告)号：WO2023273049A1

公开(公告)日：2023-01-05

申请号：PCT/CN2021/126425

申请日：2021-10-26

申请人： 杭州海康威视系统技术有限公司

发明人： 茅陈庆 ,  刘名扬 ,  杨海舟 ,  梁晨华 ,  项恒光 ,  周坚波

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06F18/253 ,  G06V20/41 ,  G06V20/46

摘要： 本申请实施例提供了一种目标对象位置关系分析方法、装置、存储介质及电子设备。其中，目标对象位置关系分析方法包括：获取分别包含目标空间区域视频图像的多段视频；在多段视频中确定多个目标对象，并对多段视频进行融合以得到包含多个目标对象的合成视频；基于合成视频中每个目标对象对应的目标图像的特征参数随时间序列的变化分析并确定目标对象之间的位置关系。采用本申请实施例能够解决与事件相关的多个目标对象无法在一段视频中同时展现，工作人员无法从一段视频中获取该多个目标对象之间的位置关系的问题。

公开(公告)号：WO2022271266A1

公开(公告)日：2022-12-29

申请号：PCT/US2022/026349

申请日：2022-04-26

申请人： X DEVELOPMENT LLC

发明人： RADKOFF, Rebecca ,  ANDRE, David

IPC分类号： G06V10/82 ,  G06F40/00 ,  G06V20/40 ,  G06V30/19 ,  G06V10/778 ,  G06F40/30 ,  G06V10/7788 ,  G06V20/41 ,  G06V20/44 ,  G06V20/46

摘要： Implementations are described herein for formulating natural language descriptions based on temporal sequences of digital images. In various implementations, a natural language input may be analyzed. Based on the analysis, a semantic scope to be imposed on a natural language description that is to be formulated based on a temporal sequence of digital images may be determined. The temporal sequence of digital images may be processed based on one or more machine learning models to identify one or more candidate features that fall within the semantic scope. One or more other features that fall outside of the semantic scope may be disregarded. The natural language description may be formulated to describe one or more of the candidate features.

公开(公告)号：WO2021248712A1

公开(公告)日：2021-12-16

申请号：PCT/CN2020/113534

申请日：2020-09-04

申请人： 哈尔滨工业大学（深圳）（哈尔滨工业大学深圳科技创新研究院）

发明人： 袁丁

IPC分类号： G06K9/00 ,  G06T7/20 ,  G06V20/42 ,  G06V20/46

摘要： 一种微运动监测方法，该方法包括：接收到微运动监测指令，获取所述微运动监测指令对应的目标视频（S10）；根据所述目标视频的各帧图，确定所述目标视频中的动力学特征点，和所述动力学特征点所属的目标运动区域（S10）；计算所述目标运动区域内所述动力学特征点的偏移量，对所述动力学特征点的偏移量进行放大，得到微运动振幅放大图（S10）。还公开了一种微运动监测装置、设备及计算机可读存储介质。

公开(公告)号：WO2023058293A1

公开(公告)日：2023-04-13

申请号：PCT/JP2022/027782

申请日：2022-07-08

申请人： MITSUBISHI ELECTRIC CORPORATION

发明人： JONES, Michael

IPC分类号： G06V10/50 ,  G06T7/20 ,  G06V10/75 ,  G06V20/40 ,  G06V20/52 ,  G05B23/0286 ,  G06F18/2148 ,  G06F18/22 ,  G06F18/285 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/30164 ,  G06T7/0008 ,  G06T7/001 ,  G06T7/11 ,  G06T7/248 ,  G06T7/254 ,  G06V10/758 ,  G06V20/41 ,  G06V20/46 ,  G06V20/49 ,  G06V2201/06

摘要： A system for detecting an anomaly in a video of a factory automation scene is disclosed. The system may accept the video; accept a set of training feature vectors derived from spatio-temporal regions of a training video, where a spatio-temporal region is associated with one or multiple training feature vectors; partition the video into multiple sequences of video volumes; produce a sequence of binary difference images for each of the video volumes; count occurrences of each of predetermined patterns of pixels in each binary difference image for each of the video volumes to produce an input feature vector including an input motion feature vector defining a temporal variation of counts of the predetermined patterns for each of the video volumes; produce a set of distances based on the produced input feature vectors and the set of training feature vectors; and detect the anomaly based on the produced set of distances.

公开(公告)号：WO2022240525A1

公开(公告)日：2022-11-17

申请号：PCT/US2022/024179

申请日：2022-04-11

申请人： MICROSOFT TECHNOLOGY LICENSING, LLC

发明人： WILLIAMS, Todd Matthew

IPC分类号： G10H1/00 ,  G10H1/36 ,  G06F40/279 ,  G06K9/6256 ,  G06N20/00 ,  G06V10/40 ,  G06V20/41 ,  G06V20/44 ,  G06V20/46 ,  G06V40/172 ,  G06V40/174 ,  G10H1/0025 ,  G10H1/368 ,  G10H2210/005 ,  G10H2210/036 ,  G10H2210/111 ,  G10H2220/441 ,  G10H2240/085 ,  G10H2250/311 ,  G10L25/57 ,  G11B27/036

摘要： A method for training one or more AI models for generating audio scores accompanying visual datasets includes obtaining training data comprising a plurality of audiovisual datasets and analyzing each of the plurality of audiovisual datasets to extract multiple visual features, textual features, and audio features. The method also includes correlating the multiple visual features and textual features with the multiple audio features via a machine learning network. Based on the correlations between the visual features, textual features, and audio features, one or more AI models are trained for composing one or more audio scores for accompanying a given dataset.

公开(公告)号：WO2022237065A1

公开(公告)日：2022-11-17

申请号：PCT/CN2021/123284

申请日：2021-10-12

申请人： 中移智行网络科技有限公司 ,  中移（上海）信息通信科技有限公司 ,  中国移动通信集团有限公司

发明人： 张宁 ,  刘林

IPC分类号： G06K9/62 ,  G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G06K9/6256 ,  G06K9/6269 ,  G06V20/46

摘要： 本申请提供了一种分类模型的训练方法、视频分类方法及相关设备，所述视频分类方法包括以下步骤：获取待分类视频；提取第三视频帧中的第二特征信息，并根据第二特征信息确定第三视频帧对应的权重值；对多个第三视频帧进行筛选，得到第二目标视频帧；将第二目标视频帧输入至目标分类模型中进行分类，得到分类结果。本申请实施例预先对待分类视频中的视频帧进行了筛选，输入至分类模型中的目标视频帧均为权重值大于等于第一预设阈值的视频帧，这样，剔除了待分类视频中的空白视频帧，确保上述目标视频帧不包括空白视频帧。分类模型无需对待分类视频中的空白视频帧进行相关计算，以此减少了分类模型的计算量，进而提高了视频分类的效率。

公开(公告)号：WO2021247372A1

公开(公告)日：2021-12-09

申请号：PCT/US2021/034573

申请日：2021-05-27

申请人： STATS LLC

发明人： WEI, Xinyu ,  HOBBS, Jennifer ,  SHA, Long ,  LUCEY, Patrick, Joseph ,  GANGULY, Sujoy

IPC分类号： G06E1/00 ,  G06K9/6256 ,  G06K9/6262 ,  G06N3/0454 ,  G06N3/08 ,  G06V10/82 ,  G06V20/42 ,  G06V20/46 ,  G06V20/52 ,  G06V40/20

摘要： A method and system of generating agent and actions prediction based on multi-agent tracking data are disclosed herein. A computing system retrieves tracking data from a data store. The computing system generates a trained neural network by generating a plurality of training data sets based on the tracking data by converting each frame of data into a matrix representation of the data contained in the frame and learning, by the neural network, a start frame and end frame of each action contained in the frame and its associated actor. The computing system receives target tracking data associated with an event. The target tracking data includes a plurality of actors and a plurality of actions. The computing system generates, via the trained neural network, a target start frame and a target end frame of each action identified in the tracking data and a corresponding actor.

公开(公告)号：WO2021077141A2

公开(公告)日：2021-04-22

申请号：PCT/US2021/016776

申请日：2021-02-05

申请人： INNOPEAK TECHNOLOGY, INC.

发明人： CHEN, Ming ,  HO, Chiu, Man

IPC分类号： H04N21/4402 ,  H04N21/472 ,  H04N21/4728 ,  H04N21/8549 ,  G06K9/00 ,  G06V10/25 ,  G06V20/41 ,  G06V20/44 ,  G06V20/46 ,  G06V20/49 ,  H04N5/23245 ,  H04N5/232945 ,  H04N5/247 ,  H04N5/772 ,  H04N5/783

摘要： This application is directed to detecting a highlight moment that occurs in a field of view of an electronic device. The electronic device identifies a region of interest (ROI) for each image in a sequence of images, and determines a gray centroid of the ROI of an initial image. The electronic device determines that an object appears in the ROI of the sequence of images from the initial image based on at least the gray centroid of the ROI of the initial image. In accordance with such a determination, the electronic device further determines that the highlight moment is initiated at the initial image in the sequence of images and stores a plurality of highlight images in association with the highlight moment in memory of the electronic device. The stored highlight images include the initial image and corresponds to a frame rate at which the sequence of images are captured.