Patents by Inventor Junkai LIU
Junkai LIU 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: 20240133281Abstract: A calculation system for predicting a proppant embedding depth based on a shale softening effect is provided, including a sampling test terminal, a scheduling module, a monitoring module, and a calculation module, wherein the scheduling module, the monitoring module, and the calculation module are connected in communication, and the monitoring module is connected to an external operating system through a wireless network, wherein the external operating system is configured to perform a hydraulic fracturing operation and receive a first control signal and/or a second control signal from the monitoring module. The sampling test terminal is configured to test the samples and obtain test data. The scheduling module is configured to determine a target construction parameter.Type: ApplicationFiled: December 23, 2023Publication date: April 25, 2024Applicant: SOUTHWEST PETROLEUM UNIVERSITYInventors: Cong LU, Qijun ZENG, Jianchun GUO, Jiaxing LIU, Jun WU, Junkai LU, Cheng LUO, Guangqing ZHOU, Xianbo MENG, Jiandong WANG, Yanhui LIU, Xiaoshan WANG, Xin SHAN
-
Patent number: 11858536Abstract: Example aspects of the present disclosure describe determining, using a machine-learned model framework, a motion trajectory for an autonomous platform. The motion trajectory can be determined based at least in part on a plurality of costs based at least in part on a distribution of probabilities determined conditioned on the motion trajectory.Type: GrantFiled: November 1, 2021Date of Patent: January 2, 2024Assignee: UATC, LLCInventors: Jerry Junkai Liu, Wenyuan Zeng, Raquel Urtasun, Mehmet Ersin Yumer
-
Patent number: 11676310Abstract: The present disclosure is directed encoding LIDAR point cloud data. In particular, a computing system can receive point cloud data for a three-dimensional space. The computing system can generate a tree-based data structure from the point cloud data, the tree-based data structure comprising a plurality of nodes. The computing system can generate a serial representation of the tree-based data structure. The computing system can, for each respective node represented by a symbol in the serial representation: determine contextual information for the respective node, generate, using the contextual information as input to a machine-learned model, a statistical distribution associated with the respective node, and generate a compressed representation of the symbol associated with the respective node by encoding the symbol using the statistical distribution for the respective node.Type: GrantFiled: September 11, 2020Date of Patent: June 13, 2023Assignee: UATC, LLCInventors: Yushu Huang, Jerry Junkai Liu, Kelvin Ka Wing Wong, Shenlong Wang, Raquel Urtasun, Sourav Biswas
-
Patent number: 11375194Abstract: Systems and method for video compression using conditional entropy coding. An ordered sequence of image frames can be transformed to produce an entropy coding for each image frame. Each of the entropy codings provide a compressed form of image information based on a prior image frame and a current image frame (the current image frame occurring after the prior image frame). In this manner, the compression model can capture temporal relationships between image frames or encoded representations of the image frames using a conditional entropy encoder trained to approximate the joint entropy between frames in the image frame sequence.Type: GrantFiled: September 10, 2020Date of Patent: June 28, 2022Assignee: UATC, LLCInventors: Jerry Junkai Liu, Shenlong Wang, Wei-Chiu Ma, Raquel Urtasun
-
Patent number: 11245927Abstract: A machine-learned image compression model includes a first encoder configured to generate a first image code based at least in part on first image data. The first encoder includes a first series of convolutional layers configured to generate a first series of respective feature maps based at least in part on the first image. A second encoder is configured to generate a second image code based at least in part on second image data and includes a second series of convolutional layers configured to generate a second series of respective feature maps based at least in part on the second image and disparity-warped feature data. Respective parametric skip functions associated convolutional layers of the second series are configured to generate disparity-warped feature data based at least in part on disparity associated with the first series of respective feature maps and the second series of respective feature maps.Type: GrantFiled: May 4, 2021Date of Patent: February 8, 2022Assignee: UATC, LLCInventors: Jerry Junkai Liu, Shenlong Wang, Raquel Urtasun
-
Publication number: 20210258611Abstract: A machine-learned image compression model includes a first encoder configured to generate a first image code based at least in part on first image data. The first encoder includes a first series of convolutional layers configured to generate a first series of respective feature maps based at least in part on the first image. A second encoder is configured to generate a second image code based at least in part on second image data and includes a second series of convolutional layers configured to generate a second series of respective feature maps based at least in part on the second image and disparity-warped feature data. Respective parametric skip functions associated convolutional layers of the second series are configured to generate disparity-warped feature data based at least in part on disparity associated with the first series of respective feature maps and the second series of respective feature maps.Type: ApplicationFiled: May 4, 2021Publication date: August 19, 2021Inventors: Jerry Junkai Liu, Shenlong Wang, Raquel Urtasun
-
Patent number: 11056062Abstract: Provided are an organic light emitting display device and a driving method thereof. The display device includes data lines, first detection lines, first compensation detection circuits, a display driving chip, a compensation chip and a control chip. Each data line is electrically connected to a corresponding first detection line through at least one first compensation detection circuit. The display driving chip sends a reference data signal to the data lines in a detection stage. The compensation chip acquires signals collected by the first detection lines and sends the signals to the control chip in the detection stage. The control chip determines a data signal compensation parameter according to the received signals, and controls the display driving chip to provide a display data signal to the data lines in a display stage according to the data signal compensation parameter.Type: GrantFiled: April 3, 2020Date of Patent: July 6, 2021Assignee: XIAMEN TIANMA MICRO-ELECTRONICS CO., LTD.Inventors: Junkai Liu, Yang Yang, Xiangzi Kong, Shuai Yang
-
Patent number: 11019364Abstract: A machine-learned image compression model includes a first encoder configured to generate a first image code based at least in part on first image data. The first encoder includes a first series of convolutional layers configured to generate a first series of respective feature maps based at least in part on the first image. A second encoder is configured to generate a second image code based at least in part on second image data and includes a second series of convolutional layers configured to generate a second series of respective feature maps based at least in part on the second image and disparity-warped feature data. Respective parametric skip functions associated convolutional layers of the second series are configured to generate disparity-warped feature data based at least in part on disparity associated with the first series of respective feature maps and the second series of respective feature maps.Type: GrantFiled: March 20, 2020Date of Patent: May 25, 2021Assignee: UATC, LLCInventors: Jerry Junkai Liu, Shenlong Wang, Raquel Urtasun
-
Publication number: 20210150771Abstract: The present disclosure is directed encoding LIDAR point cloud data. In particular, a computing system can receive point cloud data for a three-dimensional space. The computing system can generate a tree-based data structure from the point cloud data, the tree-based data structure comprising a plurality of nodes. The computing system can generate a serial representation of the tree-based data structure. The computing system can, for each respective node represented by a symbol in the serial representation: determine contextual information for the respective node, generate, using the contextual information as input to a machine-learned model, a statistical distribution associated with the respective node, and generate a compressed representation of the symbol associated with the respective node by encoding the symbol using the statistical distribution for the respective node.Type: ApplicationFiled: September 11, 2020Publication date: May 20, 2021Inventors: Lila Huang, Jerry Junkai Liu, Kelvin Ka Wing Wong, Shenglong Wang, Raquel Urtasun, Souray Biswas
-
Publication number: 20210152831Abstract: The present disclosure is directed to video compression using conditional entropy coding. An ordered sequence of image frames can be transformed to produce an entropy coding for each image frame. Each of the entropy codings provide a compressed form of image information based on a prior image frame and a current image frame (the current image frame occurring after the prior image frame). In this manner, the compression model can capture temporal relationships between image frames or encoded representations of the image frames using a conditional entropy encoder trained to approximate the joint entropy between frames in the image frame sequence.Type: ApplicationFiled: September 10, 2020Publication date: May 20, 2021Inventors: Jerry Junkai Liu, Shenlong Wang, Wei-Chiu Ma, Raquel Urtasun
-
Publication number: 20200304835Abstract: A machine-learned image compression model includes a first encoder configured to generate a first image code based at least in part on first image data. The first encoder includes a first series of convolutional layers configured to generate a first series of respective feature maps based at least in part on the first image. A second encoder is configured to generate a second image code based at least in part on second image data and includes a second series of convolutional layers configured to generate a second series of respective feature maps based at least in part on the second image and disparity-warped feature data. Respective parametric skip functions associated convolutional layers of the second series are configured to generate disparity-warped feature data based at least in part on disparity associated with the first series of respective feature maps and the second series of respective feature maps.Type: ApplicationFiled: March 20, 2020Publication date: September 24, 2020Inventors: Jerry Junkai Liu, Shenlong Wang, Raquel Urtasun
-
Publication number: 20200234651Abstract: Provided are an organic light emitting display device and a driving method thereof. The display device includes data lines, first detection lines, first compensation detection circuits, a display driving chip, a compensation chip and a control chip. Each data line is electrically connected to a corresponding first detection line through at least one first compensation detection circuit. The display driving chip sends a reference data signal to the data lines in a detection stage. The compensation chip acquires signals collected by the first detection lines and sends the signals to the control chip in the detection stage. The control chip determines a data signal compensation parameter according to the received signals, and controls the display driving chip to provide a display data signal to the data lines in a display stage according to the data signal compensation parameter.Type: ApplicationFiled: April 3, 2020Publication date: July 23, 2020Inventors: Junkai LIU, Yang YANG, Xiangzi KONG, Shuai YANG