专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11322183B2 Automated video generation from financial market analysis 有权
公开(公告)号：US11322183B2
公开(公告)日：2022-05-03
申请号：US16926406
申请日：2020-07-10
申请人： AUTOCHARTIST LIMITED
发明人： Ilan Azbel , Kobus Steenekamp , Jan Van Der Westhuizen
IPC分类号： H04N5/93 , G11B27/00 , G11B27/06 , G06Q40/04 , G06F40/58 , G10L13/00 , H04N9/80
摘要： Production of a financial market trading data video streams in a plurality of languages by receiving a financial market analysis result having an analysis type. Producing a sentence text-string corresponding to each of several languages by inserting characteristic information values from the financial market analysis result into a sentence template and translations of the sentence-template. The each said text string is converted into an audio segment and an image segment such that the audio segment and corresponding image segment have equal duration. A video segment is created by combining said audio segment and image segment. For each language of said plurality of languages, the video segments are stitched together thereby producing a financial market trading data video stream for said financial market analysis result.

2. 发明授权

US11314970B1 Reinforcement learning techniques for automated video summarization 有权
公开(公告)号：US11314970B1
公开(公告)日：2022-04-26
申请号：US16953049
申请日：2020-11-19
申请人： Adobe Inc.
发明人： Viswanathan Swaminathan , Stefano Petrangeli , Hongxiang Gu
IPC分类号： G06K9/00 , G06N3/08 , G11B27/031 , G06K9/62 , G11B27/06
摘要： A video summarization system generates a concatenated feature set by combining a feature set of a candidate video shot and a summarization feature set. Based on the concatenated feature set, the video summarization system calculates multiple action options of a reward function included in a trained reinforcement learning module. The video summarization system determines a reward outcome included in the multiple action options. The video summarization system modifies the summarization feature set to include the feature set of the candidate video shot by applying a particular modification indicated by the reward outcome. The video summarization system identifies video frames associated with the modified summarization feature set, and generates a summary video based on the identified video frames.

3. 发明授权

US11302360B1 Enhancing review videos 有权
公开(公告)号：US11302360B1
公开(公告)日：2022-04-12
申请号：US17066207
申请日：2020-10-08
申请人： ADOBE INC.
发明人： Sourabh Gupta , Mrinal Sharma , Gourav Singhal
IPC分类号： G11B27/10 , G06F3/0482 , G11B27/06 , G11B27/031 , G06N20/00 , G06F40/30 , G06Q30/02 , G06Q30/06 , G06F40/279 , G06F17/00
摘要： Review videos on product pages are enhanced with user interface elements that cause playback of the review videos at points at which particular topics are discussed. A review video is processed by converting speech to text and timestamping the text. Topics are identified in the text, and a time in the review video corresponding to each topic is identified from the timestamps for the text. In some configurations, sentiment is also determined for each topic. User interface elements corresponding to each identified topic are presented with the review video on the product page. When a user viewing the product page selects a user interface element, the review video is played at a time corresponding to the topic of the selected user interface element.

4. 发明授权

US11275950B2 Method and apparatus for segmenting video 有权
公开(公告)号：US11275950B2
公开(公告)日：2022-03-15
申请号：US17223664
申请日：2021-04-06
申请人： Beijing Wodong Tianjun information Technology Co., Ltd.
发明人： Jianping Zeng , Jingjing Lyu , Yongjun Bao
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62 , G11B27/031 , G11B27/06 , G11B27/34
摘要： Embodiments of the present disclosure provide a method and apparatus for segmenting a video. The method may include: performing video shot segmentation on a to-be-segmented video to obtain an initial video clip set; selecting at least one video clip from the video clip set; determining, for a video clip in the at least one video clip, a semantic similarity between two video clips adjacent to the video clip; and combining two video clips corresponding to a semantic similarity greater than a preset first similarity threshold value in the determined semantic similarity and a video clip between the two video clips to obtain a final video clip set.

5. 发明申请

US20220028425A1 System and Method to Customizing Video 有权
公开(公告)号：US20220028425A1
公开(公告)日：2022-01-27
申请号：US17382765
申请日：2021-07-22
申请人： Idomoo LTD
发明人： Danny KALISH
IPC分类号： G11B27/034 , G06F16/78 , G06F16/783 , G11B27/06
摘要： The present invention provides method for customizing video, said method comprising the steps of: determine original video, metadata which includes at least partial information to generate the new video file and parameter which effect/customize video content—in association to creating a new basic standard video file, wherein the partial information include at least an ID or link of the basic video original; upon opening the video the by a client player reading the metadata; checking metadata predefined conditions for playing the video as is; playing video as is in case the video initial condition are met; in case initial condition require user intervention prompting user to update the video rabbling user to input change in customization parameters data; in case user selected option of update providing the user option of update/edit the video Enabling user to input change in customization parameters data.

6. 发明授权

US11227638B2 Method, system, medium, and smart device for cutting video using video content 有权
公开(公告)号：US11227638B2
公开(公告)日：2022-01-18
申请号：US16935222
申请日：2020-07-22
申请人： Sunday Morning Technology (Guangzhou) Co., Ltd.
发明人： Qianya Lin , Tian Xia , RemyYiYang Ho , Zhenli Xie , Pinlin Chen , Rongchan Liu
IPC分类号： G11B27/06 , G11B27/036 , G10L15/26 , G06K9/00 , G11B27/10 , G10L21/0208 , G10L25/57
摘要： The present invention discloses a method and system for cutting video using video content. The method comprises: acquiring recorded video produced by user's recording operation; extracting features of recorded audio in the recorded video and judging whether the recorded audio is damaged; and if not, extracting human voice data from the recorded audio which has been filtered out background sound, intercepting video segment corresponding to effective human voice, and displaying the video segment as clip video; and if yes, extracting image feature data of person's mouth shape and human movements in the recorded video after image processing, fitting the image feature data and the human voice data which has been filtered out background sound, and displaying the video segment with the highest fitting degree as clip video.

7. 发明授权

US11183220B2 Methods and apparatus for temporal track derivations 有权
公开(公告)号：US11183220B2
公开(公告)日：2021-11-23
申请号：US16589906
申请日：2019-10-01
申请人： MEDIATEK Singapore Pte. Ltd.
发明人： Xin Wang , Lulin Chen
IPC分类号： G11B27/036 , H04N19/31 , H04N21/81 , G11B27/06 , H04N21/218 , G11B27/00
摘要： The techniques described herein relate to methods, apparatus, and computer readable media configured to access multimedia data that has a hierarchical track structure that includes at least a first track at a first level of the hierarchical track structure comprising first media data, wherein the first media data comprises a first sequence of temporally-related media units, and a second track at a second level in the hierarchical track structure that is different than the first level of the first track, the second track comprising metadata specifying a temporal track derivation operation. The temporal track derivation operation is performed on a set of media units comprising at least the first sequence of temporally-related media units to temporally modify the set of media units to generate second media data for the second track, wherein the second media data comprises a second sequence of temporally-related media units from the set of media units.

8. 发明授权

US11164604B2 Video editing method and apparatus, computer device and readable storage medium 有权
公开(公告)号：US11164604B2
公开(公告)日：2021-11-02
申请号：US17018350
申请日：2020-09-11
申请人： BEIJING MICROLIVE VISION TECHNOLOGY CO., LTD
发明人： Hao Cui
IPC分类号： G11B27/06 , G11B27/036 , G11B27/10
摘要： Disclosed are a video editing method and apparatus, a device and a readable-storage medium. The method includes: acquiring a first video, separating a first video signal of the first video and an audio signal of the first video, collecting a second video signal, and synthesizing the collected second video signal with the audio signal to obtain a second video, clipping the first video and the second video to obtain a plurality of first short videos and a plurality of second short videos respectively; and selecting, according to the audio signal, a first target short video and a second target short video from the multiple first short videos and the multiple second short videos, and stitching the first target short video and the second target short video.

9. 发明授权

US09852767B2 Method for generating a cyclic video sequence 有权
公开(公告)号：US09852767B2
公开(公告)日：2017-12-26
申请号：US15074645
申请日：2016-03-18
申请人： Thomas Niel Vassort
发明人： Thomas Niel Vassort
IPC分类号： H04N5/93 , G11B27/034 , G06T13/80 , G11B27/038 , G11B27/06 , G11B27/34
CPC分类号： G11B27/034 , G06T13/80 , G06T2210/44 , G11B27/038 , G11B27/06 , G11B27/34
摘要： A method for generating a cyclic video sequence (SC), implemented by a data-processor (11). The method includes receiving a video sequence (S); determining a first singular point (P1) of the video sequence (S) in a first interval (11) of the sequence (S) and a second singular point (P2) of the video sequence (S) in a second interval (12) of the sequence (S). The first and second singular points (P1, P2) have a maximum similarity according to a given similarity criterion; then generating a connecting sequence (SR) between the image of the video sequence (S) corresponding to the second singular point (P2) and the image of the video sequence (S) corresponding to the first singular point (P1) by morphing then constructing the cyclic video sequence (SC) by concatenation of a fragment (S′) of the video sequence (S) extending from the first singular point (P1) to the second singular point (P2), and of the connecting sequence (SR).

10. 发明授权

US09146455B2 Spatio-temporal video compositing 有权
标题翻译：时空视频合成
公开(公告)号：US09146455B2
公开(公告)日：2015-09-29
申请号：US14022048
申请日：2013-09-09
申请人： Disney Enterprises, Inc.
发明人： Jan Ruegg , Oliver Wang , Aljosa Smolic , Markus Gross
IPC分类号： G03B27/06 , G11B27/06 , H04N5/262 , H04N5/265
CPC分类号： G03B27/06 , G11B27/031 , G11B27/06 , H04N5/262 , H04N5/265
摘要： Embodiments provide techniques for creating a composite video stream. Additionally, a first selection of pixels from the first video stream and a second selection of pixels from the second video stream are received. Here, both the first selection of pixels and the second selection of pixels indicate pixels that are to be included in the composite video stream. Embodiments identify a plurality of spatiotemporal seams across the first video stream and the second video stream, based at least in part on the first selection of pixels and the second selection of pixels. The first video stream and the second video stream are then composited into the composite video stream, by joining frames from the first video stream and the second video stream at the identified plurality of spatiotemporal seams.
摘要翻译：实施例提供了用于创建复合视频流的技术。此外，接收来自第一视频流的第一选择像素和来自第二视频流的像素的第二选择。这里，第一像素选择和第二像素选择都指示要包括在复合视频流中的像素。至少部分地基于像素的第一选择和第二像素选择，实施例在第一视频流和第二视频流之间识别多个时空接缝。然后，通过在所识别的多个时空接合处连接来自第一视频流和第二视频流的帧，将第一视频流和第二视频流合成到复合视频流中。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式