Patents by Inventor Min-Hsuan Tsai

Min-Hsuan Tsai has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20210312186
    Abstract: Systems and methods of automatically extracting summaries of video content are described herein. A data processing system can access, from a video database, a first video content element including a first plurality of frame. The data processing system can select an intervallic subset of the first plurality of frames of the first video content element. The data processing system can calculate, for each of a plurality of further subsets comprising a predetermined number of frames from the intervallic subset, a score for the further subset. The data processing system can identify, from the plurality of further subsets, a further subset having a highest score. The data processing system can select a portion of the first video content element comprising the frames of the further subset having the highest score. The data processing system can generate a second video content element comprising the selected portion of the first video content element.
    Type: Application
    Filed: June 18, 2021
    Publication date: October 7, 2021
    Applicant: Google LLC
    Inventors: Yi Shen, Xiangrong Chen, Min-hsuan Tsai, Yun Shi, Tianpeng Jin, Zheng Sun, Weilong Yang, Jingbin Wang
  • Patent number: 11042754
    Abstract: Systems and methods of automatically extracting summaries of video content are described herein. A data processing system can access, from a video database, a first video content element including a first plurality of frame. The data processing system can select an intervallic subset of the first plurality of frames of the first video content element. The data processing system can calculate, for each of a plurality of further subsets comprising a predetermined number of frames from the intervallic subset, a score for the further subset. The data processing system can identify, from the plurality of further subsets, a further subset having a highest score. The data processing system can select a portion of the first video content element comprising the frames of the further subset having the highest score. The data processing system can generate a second video content element comprising the selected portion of the first video content element.
    Type: Grant
    Filed: August 3, 2017
    Date of Patent: June 22, 2021
    Assignee: Google LLC
    Inventors: Yi Shen, Xiangrong Chen, Min-hsuan Tsai, Yun Shi, Tianpeng Jin, Zheng Sun, Weilong Yang, Jingbin Wang
  • Publication number: 20210166035
    Abstract: A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.
    Type: Application
    Filed: December 14, 2020
    Publication date: June 3, 2021
    Inventors: Sanketh Shetty, Tomas Izo, Min-Hsuan Tsai, Sudheendra Vijayanarasimhan, Apostol Natsev, Sami Abu-El-Haija, George Dan Toderici, Susana Ricco, Balakrishnan Varadarajan, Nicola Muscettola, WeiHsin Gu, Weilong Yang, Nitin Khandelwal, Phuong Le
  • Publication number: 20210117691
    Abstract: Systems and methods of automatically extracting summaries of video content are described herein. A data processing system can access, from a video database, a first video content element including a first plurality of frame. The data processing system can select an intervallic subset of the first plurality of frames of the first video content element. The data processing system can calculate, for each of a plurality of further subsets comprising a predetermined number of frames from the intervallic subset, a score for the further subset. The data processing system can identify, from the plurality of further subsets, a further subset having a highest score. The data processing system can select a portion of the first video content element comprising the frames of the further subset having the highest score. The data processing system can generate a second video content element comprising the selected portion of the first video content element.
    Type: Application
    Filed: August 3, 2017
    Publication date: April 22, 2021
    Applicant: Google LLC
    Inventors: Yi Shen, Xiangrong Chen, Min-hsuan Tsai, Yun Shi, Tianpeng Jin, Zheng Sun, Weilong Yang, Jingbin Wang
  • Patent number: 10867183
    Abstract: A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.
    Type: Grant
    Filed: April 23, 2018
    Date of Patent: December 15, 2020
    Assignee: Google LLC
    Inventors: Sanketh Shetty, Tomas Izo, Min-Hsuan Tsai, Sudheendra Vijayanarasimhan, Apostol Natsev, Sami Abu-El-Haija, George Dan Toderici, Susanna Ricco, Balakrishnan Varadarajan, Nicola Muscettola, WeiHsin Gu, Weilong Yang, Nitin Khandelwal, Phuong Le
  • Patent number: 10777229
    Abstract: Frame-level quality scores for video frames of a video item is determined. A sliding window is applied to the video frames to identify a plurality of groups of the video frames for scoring on a group-level. A plurality of group-level quality scores for the plurality of groups of video frames of the video item is determined using the frame-level quality scores of the video frames. One of the plurality of groups of video frames of the video item is selected based on the plurality of group-level quality scores. A moving thumbnail is created using the selected group of video frames selected based on the respective group level quality score.
    Type: Grant
    Filed: July 8, 2019
    Date of Patent: September 15, 2020
    Assignee: Google LLC
    Inventors: Weilong Yang, Min-hsuan Tsai, Zheng Sun, Pei Cao, Tomas Izo
  • Publication number: 20190333538
    Abstract: Frame-level quality scores for video frames of a video item is determined. A sliding window is applied to the video frames to identify a plurality of groups of the video frames for scoring on a group-level. A plurality of group-level quality scores for the plurality of groups of video frames of the video item is determined using the frame-level quality scores of the video frames. One of the plurality of groups of video frames of the video item is selected based on the plurality of group-level quality scores. A moving thumbnail is created using the selected group of video frames selected based on the respective group level quality score.
    Type: Application
    Filed: July 8, 2019
    Publication date: October 31, 2019
    Inventors: Weilong Yang, Min-hsuan Tsai, Zheng Sun, Pei Cao, Tomas Izo
  • Patent number: 10431655
    Abstract: A transistor structure including a substrate, a transistor device, a split buried layer, and a second buried layer is provided. The substrate has a device region. The transistor device is located in the device region. The split buried layer is located under the transistor device in the substrate and includes first buried layers separated from each other. The second buried layer is located under the split buried layer in the substrate and connects the first buried layers. The second buried layer and the split buried layer have a first conductive type. The transistor structure may have a higher breakdown voltage.
    Type: Grant
    Filed: March 16, 2018
    Date of Patent: October 1, 2019
    Assignee: United Microelectronics Corp.
    Inventors: Yen-Ming Chen, Chiu-Ling Lee, Min-Hsuan Tsai, Chiu-Te Lee, Chih-Chung Wang
  • Publication number: 20190245041
    Abstract: A transistor structure including a substrate, a transistor device, a split buried layer, and a second buried layer is provided. The substrate has a device region. The transistor device is located in the device region. The split buried layer is located under the transistor device in the substrate and includes first buried layers separated from each other. The second buried layer is located under the split buried layer in the substrate and connects the first buried layers. The second buried layer and the split buried layer have a first conductive type. The transistor structure may have a higher breakdown voltage.
    Type: Application
    Filed: March 16, 2018
    Publication date: August 8, 2019
    Applicant: United Microelectronics Corp.
    Inventors: Yen-Ming Chen, Chiu-Ling Lee, Min-Hsuan Tsai, Chiu-Te Lee, Chih-Chung Wang
  • Patent number: 10347294
    Abstract: A method of generating a moving thumbnail is disclosed. The method includes sampling video frames of a video item. The method further includes determining frame-level quality scores for the sampled video frames. The method also includes determining multiple group-level quality scores for multiple groups of the sampled video frames using the frame-level quality scores of the sampled video frames. The method further includes selecting one of the groups of the sampled video frames based on the multiple group-level quality scores. The method includes creating a moving thumbnail using a subset of the video frames that have timestamps within a range from the start timestamp to the end timestamp.
    Type: Grant
    Filed: June 30, 2016
    Date of Patent: July 9, 2019
    Assignee: GOOGLE LLC
    Inventors: Weilong Yang, Min-Hsuan Tsai, Zheng Sun, Pei Cao, Tomas Izo
  • Patent number: 10257546
    Abstract: Systems and methods are disclosed for identifying transitions within media content items. In one implementation, a processing device process a first media content item, the first media content item being associated with a transition, to identify one or more characteristics associated with the transition. The processing device processes a second media content item to identify at least one of the one or more characteristics at a chronological interval of the second media content item. The processing device receives a sponsored content item. The processing device provides, during a presentation of the second media content item, the sponsored content item at the chronological interval.
    Type: Grant
    Filed: March 8, 2018
    Date of Patent: April 9, 2019
    Assignee: Google LLC
    Inventors: Jun Hong, Yun Shi, Ramesh Sarukkai, Min-hsuan Tsai
  • Publication number: 20180239964
    Abstract: A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.
    Type: Application
    Filed: April 23, 2018
    Publication date: August 23, 2018
    Inventors: Sanketh Shetty, Tomas Izo, Min-Hsuan Tsai, Sudheendra Vijayanarasimhan, Apostol Natsev, Sami Abu-El-Haija, George Dan Toderici, Susanna Ricco, Balakrishnan Varadarajan, Nicola Muscettola, WeiHsin Gu, Weilong Yang, Nitin Khandelwal, Phuong Le
  • Patent number: 9953222
    Abstract: A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.
    Type: Grant
    Filed: September 8, 2015
    Date of Patent: April 24, 2018
    Assignee: Google LLC
    Inventors: Sanketh Shetty, Tomas Izo, Min-Hsuan Tsai, Sudheendra Vijayanarasimhan, Apostol Natsev, Sami Abu-El-Haija, George Dan Toderici, Susanna Ricco, Balakrishnan Varadarajan, Nicola Muscettola, WeiHsin Gu, Weilong Yang, Nitin Khandelwal, Phuong Le
  • Patent number: 9955193
    Abstract: Systems and methods are disclosed for identifying transitions within media content items. In one implementation, a processing device process a first media content item, the first media content item being associated with a transition, to identify one or more characteristics associated with the transition. The processing device processes a second media content item to identify at least one of the one or more characteristics at a chronological interval of the second media content item. The processing device receives a sponsored content item. The processing device provides, during a presentation of the second media content item, the sponsored content item at the chronological interval.
    Type: Grant
    Filed: February 27, 2015
    Date of Patent: April 24, 2018
    Assignee: Google LLC
    Inventors: Jun Hong, Yun Shi, Ramesh Sarukkai, Min-hsuan Tsai
  • Publication number: 20180005666
    Abstract: A method of generating a moving thumbnail is disclosed. The method includes sampling video frames of a video item. The method further includes determining frame-level quality scores for the sampled video frames. The method also includes determining multiple group-level quality scores for multiple groups of the sampled video frames using the frame-level quality scores of the sampled video frames. The method further includes selecting one of the groups of the sampled video frames based on the multiple group-level quality scores. The method includes creating a moving thumbnail using a subset of the video frames that have timestamps within a range from the start timestamp to the end timestamp.
    Type: Application
    Filed: June 30, 2016
    Publication date: January 4, 2018
    Inventors: Weilong Yang, Min-Hsuan Tsai, Zheng Sun, Pei Cao, Tomas Izo
  • Patent number: 9607224
    Abstract: A solution is provided for temporally segmenting a video based on analysis of entities identified in the video frames of the video. The video is decoded into multiple video frames and multiple video frames are selected for annotation. The annotation process identifies entities present in a sample video frame and each identified entity has a timestamp and confidence score indicating the likelihood that the entity is accurately identified. For each identified entity, a time series comprising of timestamps and corresponding confidence scores is generated and smoothed to reduce annotation noise. One or more segments containing an entity over the length of the video are obtained by detecting boundaries of the segments in the time series of the entity. From the individual temporal segmentation for each identified entity in the video, an overall temporal segmentation for the video is generated, where the overall temporal segmentation reflects the semantics of the video.
    Type: Grant
    Filed: May 14, 2015
    Date of Patent: March 28, 2017
    Assignee: Google Inc.
    Inventors: Min-hsuan Tsai, Sudheendra Vijayanarasimhan, Tomas Izo, Sanketh Shetty, Balakrishnan Varadarajan
  • Patent number: 9508813
    Abstract: The present invention provides a transistor comprising a substrate having a surface; a first deep well region in the substrate; a second deep well region in the substrate, isolated from and encircling the first deep well region; a first well region in the substrate and on the first deep well region; two second well regions in the second deep well region and respectively at two opposite sides of the first well region; a source region in the first well region and adjacent to the surface; two drain regions in the two second well regions respectively and adjacent to the surface; two gate structures on the surface, wherein each of the two gate structures is between the source region and one of the drain regions respectively; and a guard ring in the substrate encircling the second deep well region, and on the periphery of the transistor.
    Type: Grant
    Filed: May 7, 2015
    Date of Patent: November 29, 2016
    Assignee: UNITED MICROELECTRONICS CORPORATION
    Inventors: Yen-Ming Chen, Chiuling Lee, Min-Hsuan Tsai, Zheng Hong Chen, Wei Hsuan Chang, Tseng-Hsun Liu
  • Publication number: 20160335499
    Abstract: A solution is provided for temporally segmenting a video based on analysis of entities identified in the video frames of the video. The video is decoded into multiple video frames and multiple video frames are selected for annotation. The annotation process identifies entities present in a sample video frame and each identified entity has a timestamp and confidence score indicating the likelihood that the entity is accurately identified. For each identified entity, a time series comprising of timestamps and corresponding confidence scores is generated and smoothed to reduce annotation noise. One or more segments containing an entity over the length of the video are obtained by detecting boundaries of the segments in the time series of the entity. From the individual temporal segmentation for each identified entity in the video, an overall temporal segmentation for the video is generated, where the overall temporal segmentation reflects the semantics of the video.
    Type: Application
    Filed: May 14, 2015
    Publication date: November 17, 2016
    Inventors: Min-hsuan Tsai, Sudheendra Vijayanarasimhan, Tomas Izo, Sanketh Shetty, Balakrishnan Varadarajan
  • Publication number: 20160329408
    Abstract: The present invention provides a transistor comprising a substrate having a surface; a first deep well region in the substrate; a second deep well region in the substrate, isolated from and encircling the first deep well region; a first well region in the substrate and on the first deep well region; two second well regions in the second deep well region and respectively at two opposite sides of the first well region; a source region in the first well region and adjacent to the surface; two drain regions in the two second well regions respectively and adjacent to the surface; two gate structures on the surface, wherein each of the two gate structures is between the source region and one of the drain regions respectively; and a guard ring in the substrate encircling the second deep well region, and on the periphery of the transistor.
    Type: Application
    Filed: May 7, 2015
    Publication date: November 10, 2016
    Inventors: YEN-MING CHEN, CHIULING LEE, MIN-HSUAN TSAI, ZHENG HONG CHEN, WEI HSUAN CHANG, TSENG-HSUN LIU
  • Publication number: 20160125034
    Abstract: A system and method of annotating an application, including obtaining input signals associated with a target application, wherein the input signals are obtained from a plurality of sources, obtaining first annotation data from the obtained input signals, generating second annotation data in a machine-understandable form based on the first annotation data, and associating the second annotation data with the target application.
    Type: Application
    Filed: February 5, 2015
    Publication date: May 5, 2016
    Inventors: Huazhong Ning, Weilong Yang, Tianhong Fang, Min-hsuan Tsai, Hrishikesh Balkrishna Aradhye