Patents by Inventor Wenjie Luo

Wenjie Luo 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: 20210321071
    Abstract: A method for synthesizing an omni-directional parallax view includes: obtaining parallaxes between an original image data pair, wherein the parallaxes include a horizontal parallax and a vertical parallax; determining a target viewpoint based on a base line between the original image data pair; obtaining a target pixel of the target viewpoint in original image data based on the horizontal parallax and the vertical parallax; and synthesizing a target view of the target viewpoint based on the target pixel.
    Type: Application
    Filed: September 21, 2020
    Publication date: October 14, 2021
    Inventors: Chunxia XIAO, Fei LUO, Wenjie LI, Liheng ZHOU
  • Publication number: 20210302584
    Abstract: A method, an apparatus and an electronic device for real-time object detection are provided according to the present disclosure. In the method, target point cloud data in a range of a preset angle is acquired, where the target point cloud data includes one or more data points, and the preset angle is less than the round angle. A one-dimensional LiDAR point feature of each of the data points in the target point cloud data is determined. A previous frame of LiDAR feature vector is updated based on the one-dimensional LiDAR point feature of each of the data points in the target point cloud data to generate a current frame of LiDAR feature vector. Object information is determined in a real-time manner based on the current frame of LiDAR feature vector.
    Type: Application
    Filed: September 28, 2020
    Publication date: September 30, 2021
    Inventor: Wenjie LUO
  • Publication number: 20210278732
    Abstract: An embodiment of the present disclosure provides an array substrate, a display panel, and a display device, including a substrate, a data line located above the substrate, and a shielding member located on a side, away from the substrate, of the data line, the shielding member includes a conductive screening portion, an orthographic projection of the conductive screening portion on the substrate partially covering an orthographic projection of the data line on the substrate, or the shielding member includes a filling body, an orthographic projection of the filling body on the substrate covering an orthographic projection of the data line on the substrate, and the filling body protruding outward from a surface of the substrate in a direction away from the substrate.
    Type: Application
    Filed: July 23, 2018
    Publication date: September 9, 2021
    Applicants: HEFE1 XINSHENG OPTOELECTRONICS TECHNOLOGY CO., LTD., BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Xingxing SONG, Kun YU, Zhongzhen LI, Dayong YU, Biao LUO, Wenjie WANG
  • Publication number: 20210209370
    Abstract: Systems and methods for performing semantic segmentation of three-dimensional data are provided. In one example embodiment, a computing system can be configured to obtain sensor data including three-dimensional data associated with an environment. The three-dimensional data can include a plurality of points and can be associated with one or more times. The computing system can be configured to determine data indicative of a two-dimensional voxel representation associated with the environment based at least in part on the three-dimensional data. The computing system can be configured to determine a classification for each point of the plurality of points within the three-dimensional data based at least in part on the two-dimensional voxel representation associated with the environment and a machine-learned semantic segmentation model. The computing system can be configured to initiate one or more actions based at least in part on the per-point classifications.
    Type: Application
    Filed: March 22, 2021
    Publication date: July 8, 2021
    Inventors: Chris Jia-Han Zhang, Wenjie Luo, Raquel Urtasun
  • Publication number: 20210150244
    Abstract: Systems and methods for answering region specific questions are provided. A method includes obtaining a regional scene question including an attribute query and a spatial region of interest for a training scene depicting a surrounding environment of a vehicle. The method includes obtaining a universal embedding for the training scene and an attribute embedding for the attribute query of the scene question. The universal embedding can identify sensory data corresponding to the training scene that can be used to answer questions concerning a number of different attributes in the training scene. The attribute embedding can identify aspects of an attribute that can be used to answer questions specific to the attribute. The method includes determining an answer embedding based on the universal embedding and the attribute embedding and determining a regional scene answer to the regional scene question based on the spatial region of interest and the answer embedding.
    Type: Application
    Filed: September 8, 2020
    Publication date: May 20, 2021
    Inventors: Sean Segal, Wenjie Luo, Eric Randall Kee, Ersin Yumer, Raquel Urtasun, Abbas Sadat
  • Patent number: 10970553
    Abstract: Systems and methods for performing semantic segmentation of three-dimensional data are provided. In one example embodiment, a computing system can be configured to obtain sensor data including three-dimensional data associated with an environment. The three-dimensional data can include a plurality of points and can be associated with one or more times. The computing system can be configured to determine data indicative of a two-dimensional voxel representation associated with the environment based at least in part on the three-dimensional data. The computing system can be configured to determine a classification for each point of the plurality of points within the three-dimensional data based at least in part on the two-dimensional voxel representation associated with the environment and a machine-learned semantic segmentation model. The computing system can be configured to initiate one or more actions based at least in part on the per-point classifications.
    Type: Grant
    Filed: September 6, 2018
    Date of Patent: April 6, 2021
    Assignee: UATC, LLC
    Inventors: Chris Jia-Han Zhang, Wenjie Luo, Raquel Urtasun
  • Patent number: 10762650
    Abstract: A system for estimating depth using a monocular camera may include one or more processors, a monocular camera, and a memory device. The monocular camera and the memory device may be operably connected to the one or more processors. The memory device may include an image capture, an encoder-decoder module, a semantic information generating module, and a depth map generating module. The modules may configure the one or more processors to executed by one or more processors cause the one or more processors to obtain a captured image from the monocular camera, generate a synthesized image based on the captured image wherein the style transfer module was trained using a generative adversarial network, generate, a feature map based on the synthesized image, generate semantic information based on the feature map, and generate a depth map based on the feature map and the semantic information.
    Type: Grant
    Filed: September 13, 2019
    Date of Patent: September 1, 2020
    Assignee: Toyota Motor Engineering & Manufacturing North America, Inc.
    Inventors: Rui Guo, Wenjie Luo, Shalini Keshavamurthy, Haritha Muralidharan, Fangying Zhai, Kentaro Oguchi
  • Publication number: 20200159225
    Abstract: Systems and methods for generating motion plans including target trajectories for autonomous vehicles are provided. An autonomous vehicle may include or access a machine-learned motion planning model including a backbone network configured to generate a cost volume including data indicative of a cost associated with future locations of the autonomous vehicle. The cost volume can be generated from raw sensor data as part of motion planning for the autonomous vehicle. The backbone network can generate intermediate representations associated with object detections and objection predictions. The motion planning model can include a trajectory generator configured to evaluate one or more potential trajectories for the autonomous vehicle and to select a target trajectory based at least in part on the cost volume generate by the backbone network.
    Type: Application
    Filed: August 15, 2019
    Publication date: May 21, 2020
    Inventors: Wenyuan Zeng, Wenjie Luo, Abbas Sadat, Bin Yang, Raquel Urtasun
  • Publication number: 20190382007
    Abstract: Generally, the disclosed systems and methods utilize multi-task machine-learned models for object intention determination in autonomous driving applications. For example, a computing system can receive sensor data obtained relative to an autonomous vehicle and map data associated with a surrounding geographic environment of the autonomous vehicle. The sensor data and map data can be provided as input to a machine-learned intent model. The computing system can receive a jointly determined prediction from the machine-learned intent model for multiple outputs including at least one detection output indicative of one or more objects detected within the surrounding environment of the autonomous vehicle, a first corresponding forecasting output descriptive of a trajectory indicative of an expected path of the one or more objects towards a goal location, and/or a second corresponding forecasting output descriptive of a discrete behavior intention determined from a predefined group of possible behavior intentions.
    Type: Application
    Filed: May 23, 2019
    Publication date: December 19, 2019
    Inventors: Sergio Casas, Wenjie Luo, Raquel Urtasun
  • Patent number: 10336757
    Abstract: Treatment of neurodegenerative diseases is achieved using small molecule purine scaffold compounds that inhibit Hsp90 and that possess the ability to cross the blood-brain barrier or are other wise delivered to the brain.
    Type: Grant
    Filed: July 2, 2007
    Date of Patent: July 2, 2019
    Assignees: Sloan-Kettering Institute for Cancer Research, The Rockefeller University
    Inventors: Gabriela Chiosis, Paul Greengard, Fei Dou, Wenjie Luo, Huazhong He, Danuta Zatorska
  • Publication number: 20190147250
    Abstract: Systems and methods for performing semantic segmentation of three-dimensional data are provided. In one example embodiment, a computing system can be configured to obtain sensor data including three-dimensional data associated with an environment. The three-dimensional data can include a plurality of points and can be associated with one or more times. The computing system can be configured to determine data indicative of a two-dimensional voxel representation associated with the environment based at least in part on the three-dimensional data. The computing system can be configured to determine a classification for each point of the plurality of points within the three-dimensional data based at least in part on the two-dimensional voxel representation associated with the environment and a machine-learned semantic segmentation model. The computing system can be configured to initiate one or more actions based at least in part on the per-point classifications.
    Type: Application
    Filed: September 6, 2018
    Publication date: May 16, 2019
    Inventors: Chris Jia-Han Zhang, Wenjie Luo, Raquel Urtasun
  • Publication number: 20190147372
    Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices for object detection, tracking, and motion prediction are provided. For example, the disclosed technology can include receiving sensor data including information based on sensor outputs associated with detection of objects in an environment over one or more time intervals by one or more sensors. The operations can include generating, based on the sensor data, an input representation of the objects. The input representation can include a temporal dimension and spatial dimensions. The operations can include determining, based on the input representation and a machine-learned model, detected object classes of the objects, locations of the objects over the one or more time intervals, or predicted paths of the objects. Furthermore, the operations can include generating, based on the input representation and the machine-learned model, an output including bounding shapes corresponding to the objects.
    Type: Application
    Filed: September 7, 2018
    Publication date: May 16, 2019
    Inventors: Wenjie Luo, Bin Yang, Raquel Urtasun
  • Publication number: 20190145765
    Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices for object detection are provided. For example, sensor data associated with objects can be received. Segments encompassing areas associated with the objects can be generated based on the sensor data and a machine-learned model. A position, a shape, and an orientation of each of the objects in each of the one or more segments can be determined over a plurality of time intervals. Further, a predicted position, a predicted shape, and a predicted orientation of each of the objects at a last one of the plurality of time intervals can be determined. Furthermore, an output based at least in part on the predicted position, the predicted shape, or the predicted orientation of each of the one or more objects at the last one of the plurality of time intervals can be generated.
    Type: Application
    Filed: September 17, 2018
    Publication date: May 16, 2019
    Inventors: Wenjie Luo, Bin Yang, Raquel Urtasun
  • Patent number: 9605041
    Abstract: The invention provides a previously uncharacterized protein (gamma secretase activating protein or gSAP) that activates ?-secretase to produce ?-amyloid protein (A?). Deposition of A? has been associated with Alzheimer's disease and other pathologies. The invention thus additionally provides, e.g., screening methods and novel research tools, inhibitors of this novel protein, and methods of diagnosis, treatment and control of Alzheimer's disease and other neurodegenerative conditions associated with deposition of A?.
    Type: Grant
    Filed: February 6, 2012
    Date of Patent: March 28, 2017
    Assignees: INTRA-CELLULAR THERAPIES, INC., THE ROCKEFELLER UNIVERSITY
    Inventors: Paul Greengard, Wenjie Luo, Gen He, Peng Li, Lawrence Wennogle
  • Publication number: 20130149309
    Abstract: The invention provides a previously uncharacterized protein (gamma secretase activating protein or gSAP) that activates ?-secretase to produce ?-amyloid protein (A?). Deposition of A? has been associated with Alzheimer's disease and other pathologies. The invention thus additionally provides, e.g., screening methods and novel research tools, inhibitors of this novel protein, and methods of diagnosis, treatment and control of Alzheimer's disease and other neurodegenerative conditions associated with deposition of A?.
    Type: Application
    Filed: February 6, 2012
    Publication date: June 13, 2013
    Inventors: Paul Greengard, Gen He, Peng Li, Wenjie Luo, Lawrence P. Wennogle
  • Publication number: 20090298857
    Abstract: Treatment of neurodegenerative diseases is achieved using small molecule purine scaffold compounds that inhibit Hsp90 and that possess the ability to cross the blood-brain barrier or are other wise delivered to the brain.
    Type: Application
    Filed: July 2, 2007
    Publication date: December 3, 2009
    Applicants: SLOAN-KETTERING INSTITUTE FOR CANCER RESEARCH, THE ROCKEFELLER UNIVERSITY
    Inventors: Gabriela Chiosis, Paul Greengard, Fei Dou, Wenjie Luo