-
公开(公告)号:US20220121924A1
公开(公告)日:2022-04-21
申请号:US17075963
申请日:2020-10-21
Applicant: International Business Machines Corporation
Inventor: Ulrich Alfons Finkler , Michele Merler , Mayoore Selvarasa Jaiswal , Hui Wu , Rameswar Panda , Wei Zhang
Abstract: An embodiment includes identifying an initial plurality of sets of hyperparameter values at which to evaluate an objective function that relates hyperparameter values to performance values of a neural network. The embodiment also executes training processes on the neural network with the hyperparameters set to the each of the initial sets of hyperparameter values such that the training process provides an initial set of the performance values for the objective function. The embodiment also generates an approximation of the objective function using splines at selected performance values. The embodiment approximates a point at which the approximation of the objective function reaches a maximum value, then determines an updated set of hyperparameter values associated with the maximum value. The embodiment then executes a runtime process using the neural network with the hyperparameters set to the updated set of hyperparameter values.
-
公开(公告)号:US11010176B2
公开(公告)日:2021-05-18
申请号:US16157310
申请日:2018-10-11
Applicant: International Business Machines Corporation
Inventor: Marco Cavallo , Jenna Reinen , Ravi Tejwani , Aldis Sipolins , Hui Wu
Abstract: A data presentation method through augmented reality, system, and computer program product include creating a file container for a presentation that supports raw data embedding and definition of available interactions and levels of confidentiality of information for the presentation, streaming presentation content from the file container to a plurality of augmented reality devices, and generating a personalized individual interactive experience of the presentation content for at least one person wearing an augmented reality device in the plurality of augmented reality devices.
-
公开(公告)号:US10922821B2
公开(公告)日:2021-02-16
申请号:US16840885
申请日:2020-04-06
Applicant: International Business Machines Corporation
Inventor: Marco Cavallo , Ravi Tejwani , Patrick Watson , Aldis Sipolins , Jenna Reinen , Hui Wu
Abstract: Systems, computer-implemented methods, and computer program products to generate virtual motion sensor data from computer animations are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a tracker component that can track virtual location data corresponding to a feature of a computer animated character in a virtual environment. The computer executable components can further comprise a virtual motion sensor component that, based on the virtual location data, can generate virtual motion sensor data.
-
公开(公告)号:US10725540B2
公开(公告)日:2020-07-28
申请号:US16023427
申请日:2018-06-29
Applicant: International Business Machines Corporation
Inventor: Aldis Sipolins , Jenna Reinen , Ravi Tejwani , Marco Cavallo , Hui Wu
Abstract: Augmented reality speed reading is provided by detecting a reader's changing gaze direction; detecting movements of the reader's eye; and between movements of the reader's eye, displaying text at the reader's gaze direction. An exemplary apparatus includes an eye illuminator that delivers light to a reader's eye; an eyeward camera that generates digital images of the reader's eye including reflected light from the eye illuminator; a display; and a processor that is connected in communication with the eyeward camera and the display. The processor implements an eye tracking module that receives the digital images from the eyeward camera and detects the reader's gaze direction, and the processor implements a text display module that controls the display to present text at the reader's gaze direction.
-
公开(公告)号:US10102454B2
公开(公告)日:2018-10-16
申请号:US15813401
申请日:2017-11-15
Applicant: International Business Machines Corporation
Inventor: Michele Merler , John R. Smith , Rosario A. Uceda-Sosa , Hui Wu
Abstract: A method includes utilizing two or more classifiers to calculate, for an input image, probability scores for a plurality of classes based on visual information extracted from the input image and semantic relationships in a classification hierarchy, wherein each of the two or more classifiers is associated with a given one of two or more levels in the classification hierarchy with each level in the classification hierarchy comprising a subset of the plurality of classes, and classifying the input image based on the calculated probability scores.
-
公开(公告)号:US11455335B2
公开(公告)日:2022-09-27
申请号:US17129176
申请日:2020-12-21
Applicant: International Business Machines Corporation
Inventor: Hui Wu , Rogerio S. Feris , Yu Cheng , Xiaoxiao Guo
IPC: G06F7/02 , G06F16/00 , G06F16/583 , G06F16/242 , G06F16/951 , G06F40/253
Abstract: A search engine is modified to perform increasingly precise image searching using iterative Natural Language (NL) interactions. From an NL search input, the modification extracts a set of input features, which includes a set of response features corresponding to an NL statement in the NL search input and a set of image features from a seed image in the NL search input. The modification performs image analysis on an image result in a result set of a query including at least some of the input features. In a next iteration of NL interactions, at least some of the result set is provided. An NL response in the iteration is added to a cumulative NL basis, and a revised result set is provided, which includes a new image result corresponding to a new response feature extracted from the cumulative NL basis.
-
公开(公告)号:US11100145B2
公开(公告)日:2021-08-24
申请号:US16656468
申请日:2019-10-17
Applicant: International Business Machines Corporation
Inventor: Xiaoxiao Guo , Hui Wu , Rogerio Feris
IPC: G06F16/00 , G06F16/332 , G06F16/383 , G06K9/62 , G06N3/04 , G06F16/535 , G06F16/53
Abstract: A method includes: receiving initial input from a client at least partially specifying one or more characteristics sought by the client; selecting a set of images from an image database for output to the client; and determining after each set of images whether an end condition has occurred. The method also includes, until the end condition has occurred: responsive to each set of images output to the client, receiving additional input from the client further specifying the one or more characteristics sought by the client; and responsive to each input received from the client, selecting another set of images for presentation to the client, said set of images being determined to at least partially satisfy the one or more characteristics specified by all input received from the client, said determination being based at least in part on side information for respective images for at least the set of images.
-
公开(公告)号:US10775879B1
公开(公告)日:2020-09-15
申请号:US16297644
申请日:2019-03-09
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor: Marco Cavallo , Aldis Sipolins , Jenna Reinen , Ravi Tejwani , Hui Wu
IPC: G06F3/01
Abstract: A virtual reality (VR) system for VR desk application that allows a user to move in a VR environment while sitting in front of a working desk is provided. The VR system receives sensor data from a mobile device. The VR system generates a set of sitting motion data by interpreting the received sensor data as a motion of a limb of a person in a sitting posture. The VR system maps the set of sitting motion data into a set of movements in the VR environment. The VR system renders the VR environment and presents the rendered VR environment.
-
公开(公告)号:US20200234454A1
公开(公告)日:2020-07-23
申请号:US16840885
申请日:2020-04-06
Applicant: International Business Machines Corporation
Inventor: Marco Cavallo , Ravi Tejwani , Patrick Watson , Aldis Sipolins , Jenna Reinen , Hui Wu
Abstract: Systems, computer-implemented methods, and computer program products to generate virtual motion sensor data from computer animations are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a tracker component that can track virtual location data corresponding to a feature of a computer animated character in a virtual environment. The computer executable components can further comprise a virtual motion sensor component that, based on the virtual location data, can generate virtual motion sensor data.
-
公开(公告)号:US20180089543A1
公开(公告)日:2018-03-29
申请号:US15813401
申请日:2017-11-15
Applicant: International Business Machines Corporation
Inventor: Michele Merler , John R. Smith , Rosario A. Uceda-Sosa , Hui Wu
CPC classification number: G06K9/66 , G06K9/627 , G06K9/6277 , G06K9/628 , G06K9/6285 , H05K999/99
Abstract: A method includes utilizing two or more classifiers to calculate, for an input image, probability scores for a plurality of classes based on visual information extracted from the input image and semantic relationships in a classification hierarchy, wherein each of the two or more classifiers is associated with a given one of two or more levels in the classification hierarchy with each level in the classification hierarchy comprising a subset of the plurality of classes, and classifying the input image based on the calculated probability scores.
-
-
-
-
-
-
-
-
-