公开(公告)号：US11636677B2

公开(公告)日：2023-04-25

申请号：US17145219

申请日：2021-01-08

申请人： Varshanth Ravindra Rao ,  Peng Dai ,  Hanwen Liang ,  Md Ibrahim Khalil ,  Juwei Lu

发明人： Varshanth Ravindra Rao ,  Peng Dai ,  Hanwen Liang ,  Md Ibrahim Khalil ,  Juwei Lu

IPC分类号： G06K9/68 ,  G06K9/70 ,  G06V20/40 ,  G06K9/62 ,  G06V10/764 ,  G06V30/19

摘要： System and method of analyzing a video, comprising dividing the video into a set of successive basic units; generating semantic tags for the basic units using a set of hierarchical classifier nodes that comprise a parent classifier node and a plurality of child classifier nodes, wherein the basic units are each routed through selected child classifier nodes based on classification of the basic units by the parent classifier node; and generating a semantic topic for the video based on the semantic tags generated for the basic units.

公开(公告)号：US11195046B2

公开(公告)日：2021-12-07

申请号：US16441918

申请日：2019-06-14

申请人： Varshanth Ravindra Rao ,  Uzair Ahmad ,  Peng Dai ,  Juwei Lu ,  Wei Li ,  Jianpeng Xu

发明人： Varshanth Ravindra Rao ,  Uzair Ahmad ,  Peng Dai ,  Juwei Lu ,  Wei Li ,  Jianpeng Xu

IPC分类号： G06K9/46 ,  G06K9/40 ,  G06F16/538 ,  G06N20/00 ,  G06T3/40

摘要： Methods and systems for processing an image are described. A saliency map is generated from the image. The saliency map indicates one or more salient portions of the image that have saliency values satisfying a saliency criterion. A scene graph is generated for at least the one or more salient portions. The scene graph represents a plurality of objects detected in the image. The scene graph further represents one or more relationships between each respective object pairs. One or more dataset entries associated with the image are generated. Each of the one or more relationships for each of the one or more object pairs is indicated by a respective dataset entry. The one or more dataset entries are stored in a first dataset.

公开(公告)号：US10963702B1

公开(公告)日：2021-03-30

申请号：US16566179

申请日：2019-09-10

申请人： Ruiwen Li ,  Peng Dai ,  Varshanth Ravindra Rao ,  Juwei Lu ,  Wei Li ,  Jianpeng Xu

发明人： Ruiwen Li ,  Peng Dai ,  Varshanth Ravindra Rao ,  Juwei Lu ,  Wei Li ,  Jianpeng Xu

IPC分类号： G06K9/00 ,  G11B27/031 ,  G11B27/30 ,  G06F40/205

摘要： Methods and systems for video segmentation and scene recognition are described. A video having a plurality of frames and a subtitle file associated with the video are received. Segmentation is performed on the video to generate a first set video frames comprising one or more video frames based on a frame-by-frame comparison of features in the frames of the video. Each video frame in the first includes a frame indicator which indicates at least a first start frame of the video frame. The subtitle file associated with the video is parsed to generate one or more subtitle segments based on a start and an end time of each dialogue in the subtitle file. A second set of video frames comprising one or more second video frames are generated based on the video frames of the first set of video frames and the e or more subtitle segments.