Patents by Inventor Dongqing Zhang

Dongqing Zhang 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).

  • Patent number: 11030750
    Abstract: Approaches for the automatic segmentation of magnetic resonance (MR) images. Machine learning models segment images to identify image features in consecutive frames at different levels of resolution. A neural network block is applied to groups of MR images to produce primary feature maps at two or more levels of resolution. The images in a given group of MR images may correspond to a cycle and have a temporal order. A second RNN block is applied to the primary feature maps to produce two or more output tensors at corresponding levels of resolution. A segmentation block is applied to the two or more output tensors to produce a probability map for the MR images. The first neural network block may be a convolutional neural network (CNN) block. The second neural network block may be a convolutional long short-term (LSTM) block.
    Type: Grant
    Filed: May 30, 2019
    Date of Patent: June 8, 2021
    Assignees: Merck Sharp & Dohme Corp., MSD International GmbH
    Inventors: Antong Chen, Dongqing Zhang, Ilknur Icke, Belma Dogdas, Sarayu Parimal
  • Publication number: 20210139826
    Abstract: The invention discloses a device for producing biogas with high methane content by utilizing livestock and poultry feces, wherein the interior of a tank body of a biogas fermentation tank is divided by a baffle, so as to form a main reaction chamber and an auxiliary reaction chamber which are communicated in upper portions, so that a reactant flows into the auxiliary reaction chamber only after entering the main reaction chamber via a relatively low feeding hole and then reaching a high position of a liquid level, and extension of fermentation time is realized, meanwhile, scales formed at the top of fermentation broth flow into the auxiliary reaction chamber along with liquid, so that the interior of the main reaction chamber keeps a liquid state all the time, and sealing and reduction of quantity of anaerobic bacteria are avoided.
    Type: Application
    Filed: January 17, 2020
    Publication date: May 13, 2021
    Inventors: XiaoJun NIU, MengYu LV, Xia LI, Li ZHANG, NingYu TU, XingYao YE, DongQing ZHANG, LiHua CHENG, HuaFang GUO
  • Patent number: 10986400
    Abstract: Comprehensive, compact, and discriminative representations of videos can be obtained using a counting grid representation of the video and aggregating features associated with active locations of the counting grid to obtain a feature representation of the video. The feature representation can be used for video retrieval and/or recognition. In some examples, the techniques may include conducting normalization and dimension reduction on the aggregated features to obtain a further compact and discriminative feature representation. In some examples, the counting grid representation of the video is generated using a pre-trained counting grid model in order to provide spatially consistent feature representations of the videos.
    Type: Grant
    Filed: August 4, 2016
    Date of Patent: April 20, 2021
    Assignee: Microsoft Technology Licensing. LLC
    Inventors: Gang Hua, Dongqing Zhang, Zhanning Gao
  • Publication number: 20200111214
    Abstract: Approaches for the automatic segmentation of magnetic resonance (MR) images. Machine learning models segment images to identify image features in consecutive frames at different levels of resolution. A neural network block is applied to groups of MR images to produce primary feature maps at two or more levels of resolution. The images in a given group of MR images may correspond to a cycle and have a temporal order. A second RNN block is applied to the primary feature maps to produce two or more output tensors at corresponding levels of resolution. A segmentation block is applied to the two or more output tensors to produce a probability map for the MR images. The first neural network block may be a convolutional neural network (CNN) block. The second neural network block may be a convolutional long short-term (LSTM) block.
    Type: Application
    Filed: May 30, 2019
    Publication date: April 9, 2020
    Inventors: Antong Chen, Dongqing Zhang, Ilknur Icke, Belma Dogdas, Sarayu Parimal
  • Patent number: 10130004
    Abstract: A network device includes a shelf in which a first accommodation area, a second accommodation area, a first channel, and a second channel are disposed. A third channel is formed between adjacent rear board modules or between the rear board module and the shelf. A first fan and a second fan are both disposed at a rear end of the shelf, the first fan faces the third channel, and the second fan faces the second channel. A first airflow sequentially passes, from a front end of the shelf, through the front board module in the first accommodation area, the third channel, and the first fan to form a first heat dissipation channel. A second airflow sequentially passes through the inside of the rear board module, the second channel, and the second fan after entering the first channel from the outside of the shelf to form a second heat dissipation channel.
    Type: Grant
    Filed: October 23, 2015
    Date of Patent: November 13, 2018
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Lei Shi, Dongqing Zhang
  • Publication number: 20180041765
    Abstract: Comprehensive, compact, and discriminative representations of videos can be obtained using a counting grid representation of the video and aggregating features associated with active locations of the counting grid to obtain a feature representation of the video. The feature representation can be used for video retrieval and/or recognition. In some examples, the techniques may include conducting normalization and dimension reduction on the aggregated features to obtain a further compact and discriminative feature representation. In some examples, the counting grid representation of the video is generated using a pre-trained counting grid model in order to provide spatially consistent feature representations of the videos.
    Type: Application
    Filed: August 4, 2016
    Publication date: February 8, 2018
    Inventors: Gang Hua, Dongqing Zhang, Zhanning Gao
  • Patent number: 9824486
    Abstract: A method and system is proposed to create a generative model to interpolate any view of a planar scene given a sequence of reference views and a synthesis view that is optimized by the marginalization of photometric regulation, and geometric registration parameters. According to one aspect of the claimed subject matter, a technique is proposed to combine information from varying input camera poses. Planar homography based image super resolution in free view interpolation for planar structure is applied to the combined information. Non-redundant information is combined in such a manner that the high resolution and free view problems in traditional 2D based image-based rendering techniques are overcome.
    Type: Grant
    Filed: December 16, 2014
    Date of Patent: November 21, 2017
    Assignee: Futurewei Technologies, Inc.
    Inventors: Jie Hu, Chang Wen Chen, Dongqing Zhang, Hong Heather Yu
  • Patent number: 9679380
    Abstract: Apparatus and method for modification of emotion conveyed by an image. In one aspect, a metric corresponding to the emotion conveyed by an image is generated, and a command for modifying the emotion of the image causes the emotion conveyed by the image to be changed according to the specified change to emotion. The command to modify the image emotion can be made via an emotion keyword, and can include an indicated magnitude of emotion change. Emotion conveyed by an image can be specified via an emotion vector, where elements of the vector correspond with emotions arranged along orthogonal dimensions in an emotion space. In one aspect, an emotion predictor is trained to predict the emotion conveyed by an image via determining characteristic values for a set of image feature categories, based on a set of images associated with emotion keywords of the emotion space.
    Type: Grant
    Filed: January 27, 2015
    Date of Patent: June 13, 2017
    Assignee: Futurewei Technologies, Inc.
    Inventors: Kuan-chuan Peng, Hong Heather Yu, Dongqing Zhang, Tsuhan Chen
  • Publication number: 20160125062
    Abstract: Described embodiments utilize a multi-scale timeline approach in which photographs in a photograph album are organized into photograph clusters associated with multiple timeline scales. Each photograph cluster can be represented on a display screen as a thumbnail indicator in a photograph album window for efficient browsing. The thumbnail indicator can comprise one or more images automatically selected to represent a large number of photographs from the photograph cluster. Activation of one of the thumbnail indicators can trigger a change to another timeline scale. A multi-scale timeline one-step incremental spectral photograph clustering algorithm can also be utilized to quickly add or delete photographs from the cluster photographs at multiple timeline scales with a complexity approaching O(n).
    Type: Application
    Filed: October 30, 2014
    Publication date: May 5, 2016
    Inventors: Kolbeinn KARLSSON, Wei JIANG, Dongqing ZHANG
  • Publication number: 20160120062
    Abstract: A network device includes a shelf in which a first accommodation area, a second accommodation area, a first channel, and a second channel are disposed. A third channel is formed between adjacent rear board modules or between the rear board module and the shelf. A first fan and a second fan are both disposed at a rear end of the shelf, the first fan faces the third channel, and the second fan faces the second channel. A first airflow sequentially passes, from a front end of the shelf, through the front board module in the first accommodation area, the third channel, and the first fan to form a first heat dissipation channel. A second airflow sequentially passes through the inside of the rear board module, the second channel, and the second fan after entering the first channel from the outside of the shelf to form a second heat dissipation channel.
    Type: Application
    Filed: October 23, 2015
    Publication date: April 28, 2016
    Inventors: Lei Shi, Dongqing Zhang
  • Patent number: 9275438
    Abstract: An apparatus comprising one or more processors configured to receive a digital image comprising a current pixel and a plurality of nearby pixels, determine a pixel intensity of the current pixel, wherein the pixel intensity comprises a noise component, and reduce the noise component by applying a bilateral filter as a combination of a domain filter and a range filter on the current pixel, wherein the domain filter is dependent on the pixel intensity and geometric closeness between the current pixel and the nearby pixels, and wherein the range filter is dependent on the pixel intensity and photometric similarity between the current pixel and the nearby pixels.
    Type: Grant
    Filed: March 26, 2014
    Date of Patent: March 1, 2016
    Assignee: Futurewei Technologies, Inc.
    Inventors: Bo Wang, Zixiang Xiong, Dongqing Zhang, Hong Heather Yu
  • Patent number: 9124765
    Abstract: A method for performing a video conference in a mobile phone is provided. The video conference involves a plurality of conferencing devices that display presentation content and a video image of one or more participants in the video conference. The mobile phone receives a first and second real-time transport protocol (RTP) packets including a video image of a participant and presentation content in the video conference, respectively. The video image of the participant includes a face portion of the participant and a background portion. The mobile phone decodes the video image of the participant and the presentation content, extracts the face portion of the participant from the video image of the participant, overlays the face portion of the participant over a portion of the presentation content to form a composite image, and displays the composite image on a display device of the mobile phone.
    Type: Grant
    Filed: December 27, 2013
    Date of Patent: September 1, 2015
    Assignee: Futurewei Technologies, Inc.
    Inventors: DongQing Zhang, Zhenyu Wu, Hong Heather Yu
  • Publication number: 20150213331
    Abstract: Apparatus and method for modification of emotion conveyed by an image. In one aspect, a metric corresponding to the emotion conveyed by an image is generated, and a command for modifying the emotion of the image causes the emotion conveyed by the image to be changed according to the specified change to emotion. The command to modify the image emotion can be made via an emotion keyword, and can include an indicated magnitude of emotion change. Emotion conveyed by an image can be specified via an emotion vector, where elements of the vector correspond with emotions arranged along orthogonal dimensions in an emotion space. In one aspect, an emotion predictor is trained to predict the emotion conveyed by an image via determining characteristic values for a set of image feature categories, based on a set of images associated with emotion keywords of the emotion space.
    Type: Application
    Filed: January 27, 2015
    Publication date: July 30, 2015
    Inventors: Kuan-chuan PENG, Hong Heather YU, Dongqing ZHANG, Tsuhan CHEN
  • Publication number: 20150170405
    Abstract: A method and system is proposed to create a generative model to interpolate any view of a planar scene given a sequence of reference views and a synthesis view that is optimized by the marginalization of photometric regulation, and geometric registration parameters. According to one aspect of the claimed subject matter, a technique is proposed to combine information from varying input camera poses. Planar homography based image super resolution in free view interpolation for planar structure is applied to the combined information. Non-redundant information is combined in such a manner that the high resolution and free view problems in traditional 2D based image-based rendering techniques are overcome.
    Type: Application
    Filed: December 16, 2014
    Publication date: June 18, 2015
    Inventors: Jie HU, Chang Wen CHEN, Dongqing ZHANG, Hong Heather YU
  • Publication number: 20140293096
    Abstract: An apparatus comprising one or more processors configured to receive a digital image comprising a current pixel and a plurality of nearby pixels, determine a pixel intensity of the current pixel, wherein the pixel intensity comprises a noise component, and reduce the noise component by applying a bilateral filter as a combination of a domain filter and a range filter on the current pixel, wherein the domain filter is dependent on the pixel intensity and geometric closeness between the current pixel and the nearby pixels, and wherein the range filter is dependent on the pixel intensity and photometric similarity between the current pixel and the nearby pixels.
    Type: Application
    Filed: March 26, 2014
    Publication date: October 2, 2014
    Applicant: Futurewei Technologies, Inc.
    Inventors: Bo Wang, Zixiang Xiong, Dongqing Zhang, Hong Heather Yu
  • Publication number: 20140184721
    Abstract: A method for performing a video conference in a mobile phone is provided. The video conference involves a plurality of conferencing devices that display presentation content and a video image of one or more participants in the video conference. The mobile phone receives a first and second real-time transport protocol (RTP) packets including a video image of a participant and presentation content in the video conference, respectively. The video image of the participant includes a face portion of the participant and a background portion. The mobile phone decodes the video image of the participant and the presentation content, extracts the face portion of the participant from the video image of the participant, overlays the face portion of the participant over a portion of the presentation content to form a composite image, and displays the composite image on a display device of the mobile phone.
    Type: Application
    Filed: December 27, 2013
    Publication date: July 3, 2014
    Applicant: Huawei Technologies Co., Ltd.
    Inventors: DongQing Zhang, Zhenyu Wu, Hong Heather Yu
  • Publication number: 20130293776
    Abstract: Caption boxes which are embedded in video content can be located and the text within the caption boxes decoded. Real time processing is enhanced by locating caption box regions in the compressed video domain and performing pixel based processing operations within the region of the video frame in which a caption box is located. The captions boxes are further refined by identifying word regions within the caption boxes and then applying character and word recognition processing to the identified word regions. Domain based models are used to improve text recognition results. The extracted caption box text can be used to detect events of interest in the video content and a semantic model applied to extract a segment of video of the event of interest.
    Type: Application
    Filed: July 3, 2013
    Publication date: November 7, 2013
    Inventors: Chang Shih-Fu, Dongqing Zhang
  • Patent number: 8488682
    Abstract: Caption boxes which are embedded in video content can be located and the text within the caption boxes decoded. Real time processing is enhanced by locating caption box regions in the compressed video domain and performing pixel based processing operations within the region of the video frame in which a caption box is located. The captions boxes are further refined by identifying word regions within the caption boxes and then applying character and word recognition processing to the identified word regions. Domain based models are used to improve text recognition results. The extracted caption box text can be used to detect events of interest in the video content and a semantic model applied to extract a segment of video of the event of interest.
    Type: Grant
    Filed: December 19, 2007
    Date of Patent: July 16, 2013
    Assignee: The Trustees of Columbia University in the City of New York
    Inventors: Shih-Fu Chang, Dongqing Zhang
  • Publication number: 20080303942
    Abstract: Caption boxes which are embedded in video content can be located and the text within the caption boxes decoded. Real time processing is enhanced by locating caption box regions in the compressed video domain and performing pixel based processing operations within the region of the video frame in which a caption box is located. The captions boxes are further refined by identifying word regions within the caption boxes and then applying character and word recognition processing to the identified word regions. Domain based models are used to improve text recognition results. The extracted caption box text can be used to detect events of interest in the video content and a semantic model applied to extract a segment of video of the event of interest.
    Type: Application
    Filed: December 19, 2007
    Publication date: December 11, 2008
    Inventors: Shih-Fu Chang, Dongqing Zhang
  • Patent number: 7339992
    Abstract: Caption boxes which are embedded in video content can be located and the text within the caption boxes decoded. Real time processing is enhanced by locating caption box regions in the compressed video domain (210) and performing pixel based processing operations within the region of the video frame in which a caption box is located. The captions boxes are further refined by identifying word regions (240) within the caption boxes and then applying character and word recognition processing (250) to the identified word regions. Domain based models are used to improve text recognition results. The extracted caption box text can be used to detect events of interest in the video content and a semantic model applied to extract a segment of video of the event of interest.
    Type: Grant
    Filed: December 6, 2002
    Date of Patent: March 4, 2008
    Assignee: The Trustees of Columbia University in the city of New York
    Inventors: Shih-Fu Chang, Dongqing Zhang