Xerox Corporation

Palo Alto Research Center Inc.

Conduent Business Services, LLC

The Procter Gamble Company

Matthew Adam Shreve

Robert P Loce

Raja Bala

Robert Roy Price

Edgar A Bernal

Michael C Mongeon

Sricharan Kallur Palli Kumar

Jeyasri Subramanian

Francisco Eduardo Torres

Anne Plochowietz

Kent J Evans

John Turner Maxwell, Iii

Qun Li

Richard Leighton Howe

Pei Li

Paul Jonathan Matts

Gaurang R Gavai

Matthew Klenk

Shiwali Mohan

Jin Sun

Aaron Ang

Wencheng Wu

Eugene Michael Chow

Jengping Lu

Lester D Nelson

Sourobh Raychaudhuri

Julie A Bert

Lara S Crawford

Ankur Purwar

Bradley Rupp

Hoda M A Eldardiry

Sergey Butylkov

Valerie J Raburn

Mark Jeffrey Stefik

Peter Paul

Palghat Srinivas Ramesh

Vladimir Kozitsky

Robert Thomas Krivacic

Stephen C Morgana

Jayant Kumar

Eric Cocker

Christoforos Somarakis

Svyatoslav Korneev

Adrian Lew

Pramod Sankar Kompalli

Jacob Le

Luisa Fernanda Polania Cabrera

Sreenivas Venkobarao

Beilei Xu

Yao Rong Wang

Aaron Michael Burry

Martin Sidney Maltz

Orhan Bulan

Michael Robert Furst

Phillip J Emmett

Yunda Wang

Hoda Eldardiry

James D Glasnapp

Gregory Michael Youngblood

Evgeniy Bart

Megan Clar

Eric Harte

Hui Ding

Chad Ramos

Qun Liu

Sumeet Menon

Ankur N M N Purwar

Wencheng N M N Wu

Lisa S E Rythen Larsson

Shagan Sah

A system captures, by a recording device, a scene with physical objects, the scene displayed as a three-dimensional (3D) mesh. The system marks 3D annotations for a physical object and identifies a mask. The mask indicates background pixels corresponding to a region behind the physical object. Each background pixel is associated with a value. The system captures a plurality of images of the scene with varying features, wherein a respective image includes: two-dimensional (2D) projections corresponding to the marked 3D annotations for the physical object; and the mask based on the associated value for each background pixel. The system updates the value of each background pixel with a new value. The system trains a machine model using the respective image as generated labeled data, thereby obtaining the generated labeled data in an automated manner based on a minimal amount of marked annotations.

Method and system for facilitating generation of background replacement masks for improved labeled image dataset collection

A method of labeling training data includes inputting a plurality of unlabeled input data samples into each of a plurality of pre-trained neural networks and extracting a set of feature embeddings from multiple layer depths of each of the plurality of pre-trained neural networks. The method also includes generating a plurality of clusterings from the set of feature embeddings. The method also includes analyzing, by a processing device, the plurality of clusterings to identify a subset of the plurality of unlabeled input data samples that belong to a same unknown class. The method also includes assigning pseudo-labels to the subset of the plurality of unlabeled input data samples.

Using multiple trained models to reduce data labeling efforts

A method is provided. The method includes obtaining a state graph that represents a set of objects within an environment and a set of positions of the set of objects within the environment. The state graph includes a set of object nodes and a set of property nodes. The method also includes obtaining user input data. The user input data is generated based on a natural language input. The method further includes updating the state graph based on the user input data to generate an enhanced state graph. The enhanced state graph includes additional nodes generated based on the user input data. The method further includes providing the enhanced state graph to a planning module. The planning modules generates instructions for operating a mechanical system based on the enhanced state graph.

Interacting with machines using natural language input and an enhanced state graph

A system determines an input video and a first annotated image from the input video which identifies an object of interest. The system initiates a tracker based on the first annotated image and the input video. The tracker generates, based on the first annotated image and the input video, information including: a sliding window for false positives; a first set of unlabeled images from the input video; and at least two images with corresponding labeled states. A semi-supervised classifier classifies, based on the information, the first set of unlabeled images from the input video. If a first unlabeled image is classified as a false positive, the system reinitiates the tracker based on a second annotated image occurring in a frame prior to a frame with the false positive. The system generates an output video comprising the input video displayed with tracking on the object of interest.

Method and system for semi-supervised state transition detection for object tracking

A method of labeling data and training a model is provided. The method includes obtaining a set of images. The set of images includes a first subset and a second subset. The first subset is associated with a first set of labels. The method also includes generating a set of pseudo labels for the set of images and a second set of labels for the second subset based on the first subset, the second subset, a first machine learning model, and a domain adaption model. The method further includes generating second machine learning model. The second machine learning model is generated based on the set of images, the set of pseudo labels, the first set of labels, and the second set of labels. The second set of labels is updated based on one or more inferences generated by the second machine learning model.

Training machine learning models based on unlabeled data

In one embodiment, a method is provided. The method includes obtaining sensor data indicative of a set of objects detected within an environment. The method also includes determining a set of positions of the set of objects and a set of properties of the set of objects based on the sensor data. The method further includes generating a state graph based on the sensor data. The state graph represents the set of objects and the set of positions of the set of objects. The state graph includes a set of object nodes to represent the set of objects and a set of property nodes to represent the set of properties of the set of objects. The state graph is provided to a graph enhancement module that updates the state graph with additional data to generate an enhanced state graph.

Interacting with machines using natural language input and a state graph

A system is provided which mixes static scene and live annotations for labeled dataset collection. A first recording device obtains a 3D mesh of a scene with physical objects. The first recording device marks, while in a first mode, first annotations for a physical object displayed in the 3D mesh. The system switches to a second mode. The system displays, on the first recording device while in the second mode, the 3D mesh including a first projection indicating a 2D bounding area corresponding to the marked first annotations. The first recording device marks, while in the second mode, second annotations for the physical object or another physical object displayed in the 3D mesh. The system switches to the first mode. The first recording device displays, while in the first mode, the 3D mesh including a second projection indicating a 2D bounding area corresponding to the marked second annotations.

Method and system for mixing static scene and live annotations for efficient labeled image dataset collection

A system and method for translating a 2D image to a 3D image is provided. A 2D image having pixels grouped into tiles is obtained. Contour lines associated with an altitude value are located on the 2D image. The altitude values are determined. Each tile in the 2D image is represented using at least one voxel. A height map of the voxels is generated based on the contour lines and altitude values as a base layer for a 3D image. A terrain type of each of the voxels of the 3D image is determined and objects are placed in the 3D image. The 3D image is output.

System and method for translating a 2D image to a 3D image

A system and method provide a combination of a modular message structure, a priority-based message packing scheme, and a data packet queue management system to optimize the information content of a transmitted message in, for example, the Ocean of Things (OoT) environment. The modular message structure starts with a header that provides critical information and reference points for time and location. The rest of the message is composed of modular data packets, each of which has a data ID section that the message decoder uses for reference when reconstructing the message contents, an optional size section that specifies the length of the following data section if it can contain data of variable length, and a data section that can be compressed in a manner unique to that data type. The message packing scheme uses a combination of priority level and minimum reporting interval, both of which are dynamically configurable for each data packet type, to maximize the value of the information contained in the modular data packets included in each message. Finally, the data packet queues manage temporary storage of data packets that have been generated but not yet included in an outgoing message.

System and method using improved message queue and packing scheme for electronic device

A method utilizes a target substrate has an array of chips on a carrier with a plurality of vacancies and a plurality of donor coupons are incompletely filled with functional chips. A bounding box is defined that encompasses the vacancies on the target substrate. Outcomes are simulated by overlapping a representation of the bounding box over a representation of each of a plurality of donor coupons at a plurality of translational offsets on a substrate plane to determine matches. An optimal one of the outcomes is found at a selected one or more of the donor coupons corresponding one or more offsets. A parallel transfer of the matching functional chips fills the vacancies on the target substrate using the one or more selected donor coupons and corresponding one or more offsets.

System and method for repairing vacancies resulting from mass transfer of devices

A method is provided. The method includes obtaining sensor data indicative of a set of objects detected within an environment. The method also includes generating a state graph based on the sensor data. The state graph includes a set of object nodes and a set of property nodes. The method further includes obtaining user input data generated based on a natural language input. The method further includes updating the state graph based on the user input data to generate an enhanced state graph. The enhanced state graph includes additional nodes generated based on the user input data. The method further includes generating a set of instructions for a set of mechanical systems based on the enhanced state graph. The method further includes operating the set of mechanical systems to achieve a set of objectives based on the set of instructions.

System for interacting with machines using natural language input

A method includes defining a model for a liquid while the liquid is positioned at least partially within a nozzle of a printer. The method also includes synthesizing video frames of the liquid using the model to produce synthetic video frames. The method also includes generating a labeled dataset that includes the synthetic video frames and corresponding model values. The method also includes receiving real video frames of the liquid while the liquid is positioned at least partially within the nozzle of the printer. The method also includes generating an inverse mapping from the real video frames to predicted model values using the labeled dataset. The method also includes reconstructing the liquid in the real video frames based at least partially upon the predicted model values.

Characterizing liquid reflective surfaces in 3D liquid metal printing

Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.

System and method for generating photorealistic synthetic images based on semantic information

A method of labeling a dataset includes inputting a testing set comprising a plurality of input data samples into a plurality of pre-trained machine learning models to generate a set of embeddings output by the plurality of pre-trained machine learning models. The method further includes performing an iterative cluster labeling algorithm that includes generating a plurality of clusterings from the set of embeddings, analyzing the plurality of clusterings to identify a target embedding with a highest duster quality, analyzing the target embedding to determine a compactness for each of the plurality of clusterings of the target embedding, and identifying a target cluster among the plurality of clusterings of the target embedding based on the compactness. The method further includes assigning pseudo-labels to the subset of the plurality of input data samples that are members of the target duster.

One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object.

System and method using augmented reality for efficient collection of training data for machine learning

Growing community of inventors

Webster, NY, United States of America

Matthew Adam Shreve