Patents by Inventor Zhisong Wang
Zhisong Wang 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: 20240135638Abstract: A method, an electronic device, and a computer program product for generating a three-dimensional scene are provided in embodiments of the present disclosure. The method may include obtaining source image features from a plurality of two-dimensional source images associated with the three-dimensional scene to be generated. The method may further include obtaining editing features from an editing instruction input by a user for the three-dimensional scene, each of the editing features respectively forming a feature pair with each of the source image features. Furthermore, the method may include updating the source image features by maximizing a correlation coefficient of each of the feature pairs, and generating the three-dimensional scene based at least on the updated source image features. Embodiments of the present disclosure can realize arbitrary editing of a three-dimensional scene, thus enhancing the experience of human-computer interaction.Type: ApplicationFiled: November 10, 2022Publication date: April 25, 2024Inventors: Zhisong Liu, Zijia Wang, Anzhou Hou, Zhen Jia
-
Publication number: 20240135482Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for processing a virtual avatar. The method includes generating an image feature of the virtual avatar based on a plurality of image blocks of the virtual avatar and corresponding positions of the plurality of image blocks in the virtual avatar. The method further includes generating, based on a watermark to be added to the virtual avatar, a text feature associated with text of the watermark. The method further includes generating a watermarked virtual avatar based on the image feature and the text feature, wherein the watermark is invisible to human beings and identifies an identity of a user of the virtual avatar in a metaverse. Through embodiments of the present disclosure, identification of a virtual avatar, illustratively for verification and/or tracking purposes can be achieved without affecting the appearance of the virtual avatar.Type: ApplicationFiled: November 11, 2022Publication date: April 25, 2024Inventors: Zijia Wang, Zhisong Liu, Zhen Jia
-
Publication number: 20240135489Abstract: A method includes generating a feature map of a second resolution for an input image of a first resolution, the first resolution being less than the second resolution. The method further includes generating a feature map of the second resolution and a feature map of the first resolution through a first residual-based dense back projection (RDBP) network. In addition, the method further includes generating a feature map of the second resolution and a feature map of the first resolution through a second RDBP network, the first RDBP network and the second RDBP network respectively including a downsampling back projection layer, an upsampling back projection layer, and an attention layer. The method further includes generating an output image of the second resolution based on the feature maps of the second resolution and the feature maps of the first resolution generated through the first RDBP network and the second RDBP network.Type: ApplicationFiled: November 15, 2022Publication date: April 25, 2024Inventors: Zhisong Liu, Zijia Wang, Zhen Jia
-
Publication number: 20240135599Abstract: Embodiments of the present disclosure relate to a method, a device, and a computer program product for processing data. The method includes determining, based on acquired text, character features for a group of characters in the text and text features for the text. The method further includes determining initial visual features for the text based on the text features. The method further includes determining target visual features for the text based on the initial visual features, the character features, and the text features. The method further includes generating a target image corresponding to the text based on the target visual features. Through the method, the accuracy of conversion between text and an image is improved, the data processing efficiency is improved, and the data compression efficiency is further improved.Type: ApplicationFiled: November 10, 2022Publication date: April 25, 2024Inventors: Zijia Wang, Zhisong Liu, Zhen Jia
-
Publication number: 20240127530Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for generating a target object. The method includes upsampling a first feature of an input point cloud. The method further includes determining a reference feature of a reference point cloud having a predetermined shape. The method further includes determining a second feature based on the upsampled first feature and the reference feature. The method further includes generating a three-dimensional target object based on the second feature and the input point cloud, wherein the target object has a fitted curved surface, and the target object has a greater number of points than the input point cloud. With embodiments of the present disclosure, a point cloud of the target object can be made denser, and the number of points can be increased, thereby achieving a more accurate three-dimensional reconstruction of the target object.Type: ApplicationFiled: November 7, 2022Publication date: April 18, 2024Inventors: Zhisong Liu, Zijia Wang, Zhen Jia
-
Publication number: 20240116962Abstract: Disclosed in the present invention are a pyridine-2-amine derivative and a pharmaceutical composition and use thereof. The pyridine-2-amine derivative can be used as a TLR8 selective agonist, has the characteristics of high selectivity, strong activity and high safety, can be used for preventing and/or treating diseases related to TLR activity, for example, diseases caused by or related to pathogen infection, immunological diseases, inflammation, and tumors, can also be used for preparing a vaccine adjuvant to enhance immune response, and has better application prospects and research and development value.Type: ApplicationFiled: December 31, 2021Publication date: April 11, 2024Inventors: Xuebin LIAO, Zhisong WANG, Yan ZHANG
-
Publication number: 20240106766Abstract: Methods, apparatus, and processor-readable storage media for automatically processing user request data using artificial intelligence techniques are provided herein. An example computer-implemented method includes generating, using a chatbot during a communication session with a user, answers to user requests by processing the user requests using a first set of artificial intelligence techniques associated with the chatbot; generating knowledge base-related predictions associated with the user requests by processing the user requests using a second set of artificial intelligence techniques associated with a knowledge base; calculating at least one score associated with at least a portion of the answers and the user requests based on qualifying values computed in connection with at least one of generating the answers and generating the knowledge base-related predictions; and performing one or more automated actions based on the at least one calculated score.Type: ApplicationFiled: September 19, 2022Publication date: March 28, 2024Inventors: Zijia Wang, Zhisong Liu, Zhen Jia, Kenneth Durazzo
-
Publication number: 20240096000Abstract: Embodiments of the present disclosure relate to a method, a device, and a computer program product for rendering an image. The method includes determining, based on a coordinate value of a target point in a target scenario and a viewing direction for the target point, a rendering parameter for the target point. The method further includes adjusting the rendering parameter based on the viewing direction and by performing an upsampling operation on the rendering parameter. The method further includes rendering an image for the target scenario based on the adjusted rendering parameter. By means of the method, resources required by processing of image data are reduced; the image data processing speed is increased; and fast rendering of a high-resolution image can be achieved.Type: ApplicationFiled: October 14, 2022Publication date: March 21, 2024Inventors: Zhisong Liu, Zijia Wang, Zhen Jia
-
Publication number: 20240095970Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for processing a target object. The method includes acquiring an initial non-video feature vector on the basis of at least one input of a received speech input and text input. The method further includes taking, in response to not receiving a video input, a default feature vector as an initial video feature vector corresponding to the video input. The method further includes generating a video feature, a speech feature, and a text feature on the basis of the initial non-video feature vector and the initial video feature vector. The method further includes generating a processing parameter for a target object on the basis of the video feature, the speech feature, and the text feature, wherein the processing parameter includes at least one of an emotion parameter, an attribute parameter, and a pose parameter.Type: ApplicationFiled: October 20, 2022Publication date: March 21, 2024Inventors: Zijia Wang, Zhisong Liu, Zhen Jia
-
Publication number: 20240070956Abstract: A method, an electronic device, and a computer program product for video processing are provided in embodiments of the present disclosure. The method generates an avatar image using a reference image and image data for a first frame in a video stream, and generates an avatar video using the avatar image and image data, audio data, and text data in the video stream. Through this solution, a user-defined avatar video adapted to a user of a real video and actions thereof can be generated more accurately and with high quality.Type: ApplicationFiled: June 22, 2023Publication date: February 29, 2024Inventors: Zhisong Liu, Zijia Wang, Zhen Jia
-
Patent number: 11913085Abstract: A method for preparing a press-hardened steel component is provided. The method includes forming a heated blank by heating a steel alloy blank to a first temperature in a first zone of a furnace having two or more zones, and after the heating of the steel alloy blank to the first temperature, heating the steel alloy blank to a second temperature in a second zone of the furnace. The second temperature is greater than the first temperature. The first zone has a first flow rate for a protective gas, and the second zone has a second flow rate for the protective gas that is greater than the first flow rate. The method further includes stamping and quenching the heated blank at a constant rate to a temperature between a martensite finish temperature of the steel alloy defining the steel alloy blank and room temperature to form the press-hardened steel component.Type: GrantFiled: October 13, 2022Date of Patent: February 27, 2024Assignees: GM Global Technology Operations LLC, Northeastern UniversityInventors: Zhisong Chai, Tingdong Ren, Jinlong Zhu, Wei Xu, Jianfeng Wang
-
Patent number: 10341291Abstract: A method, a device and a storage medium for processing a communication service in a circuit switch domain are provided. The method may include: judging, when a communication service being currently processed by a communication terminal is a voice call service or a short message service in a circuit switch domain, whether a switching condition for switching the communication service onto a real-time communication tool in a packet switch domain of the communication terminal is met; if it is met, switching the communication service onto the real-time communication tool in the packet switch domain of the communication terminal.Type: GrantFiled: October 17, 2014Date of Patent: July 2, 2019Assignee: ZTE CORPORATIONInventors: Zhigang Dai, Zhisong Wang
-
Publication number: 20170180310Abstract: A method, a device and a storage medium for processing a communication service in a circuit switch domain are provided. The method may include: judging, when a communication service being currently processed by a communication terminal is a voice call service or a short message service in a circuit switch domain, whether a switching condition for switching the communication service onto a real-time communication tool in a packet switch domain of the communication terminal is met; if it is met, switching the communication service onto the real-time communication tool in the packet switch domain of the communication terminal.Type: ApplicationFiled: October 17, 2014Publication date: June 22, 2017Applicant: ZTE CORPORATIONInventors: Zhigang DAI, Zhisong WANG
-
Publication number: 20100046733Abstract: This invention provides method and device for blind transfer service. The method comprises the following steps: first, user A establishes a call with user B, then, user B originates a call transfer request to request to transfer the call with user A to user C; application server of user B heads off the request and returns an accept response to user B; the application server of user B firstly originates a call invitation to user C and acquires media parameter information of user C; the application server of user B originates a call re-invitation to user A, provides the media parameter information of user C, instructs user A to carry out media switch, and acquires media parameter information of user A; the application server of user B provides the media parameter information of user A to user C, and instructs user C to establish a media stream connection with user A.Type: ApplicationFiled: December 11, 2007Publication date: February 25, 2010Applicant: ZTE CORPORATIONInventors: Min Shen, Zhisong Wang, Chengnian Shen, Wenjie Ling, Lu Zhang
-
Publication number: 20100040218Abstract: This invention provides consultative transfer service method and apparatus.Type: ApplicationFiled: December 11, 2007Publication date: February 18, 2010Applicant: ZTE CORPORATIONInventors: Min Shen, Zhisong Wang, Wenjie Ling, Chengnian Shen, Lu Zhang
-
Patent number: 6894642Abstract: A method for enhanced Capon beamforming includes the steps of providing a sensor array including a plurality of sensor elements where an array steering vector corresponding to a signal of interest (SOI) is unknown. A covariance matrix fitting relation is bounded for the unknown array steering vector by constraining the array steering vector using a constant norm and a spherical uncertainty set. The matrix fitting relation is then solved to provide an estimate of said array steering vector.Type: GrantFiled: October 1, 2003Date of Patent: May 17, 2005Assignee: University of Florida Research Foundation, Inc.Inventors: Jian Li, Petre Stoica, Zhisong Wang
-
Publication number: 20050073457Abstract: A method for enhanced Capon beamforming includes the steps of providing a sensor array including a plurality of sensor elements where an array steering vector corresponding to a signal of interest (SOI) is unknown. A covariance matrix fitting relation is bounded for the unknown array steering vector by constraining the array steering vector using a constant norm and a spherical uncertainty set. The matrix fitting relation is then solved to provide an estimate of said array steering vector.Type: ApplicationFiled: October 1, 2003Publication date: April 7, 2005Inventors: Jian Li, Petre Stoica, Zhisong Wang
-
Patent number: 6798380Abstract: A method for enhanced Capon beamforming, referred to herein as an advanced robust Capon beamformer (advanced RCB), includes the steps of providing a sensor array including a plurality of sensor elements, wherein an array steering vector corresponding to a signal of interest (SOI) is unknown. The array steering vector is represented by an ellipsoidal uncertainty set. A covariance fitting relation for the array steering vector is bounded with the uncertainty ellipsoid. The matrix fitting relation is solved to provide an estimate of the array steering vector.Type: GrantFiled: February 5, 2003Date of Patent: September 28, 2004Assignee: University of Florida Research Foundation, Inc.Inventors: Jian Li, Petre Stoica, Zhisong Wang
-
Publication number: 20040150558Abstract: A method for enhanced Capon beamforming, referred to herein as an advanced robust Capon beamformer (advanced RCB), includes the steps of providing a sensor array including a plurality of sensor elements, wherein an array steering vector corresponding to a signal of interest (SOI) is unknown. The array steering vector is represented by an ellipsoidal uncertainty set. A covariance fitting relation for the array steering vector is bounded with the uncertainty ellipsoid. The matrix fitting relation is solved to provide an estimate of the array steering vector.Type: ApplicationFiled: February 5, 2003Publication date: August 5, 2004Applicant: University of FloridaInventors: Jian Li, Petre Stoica, Zhisong Wang