Fuji Xerox Co., Ltd.

Fujifilm Business Innovation Corp.

Fujifilm Corporation

Qiong Liu

Patrick Chiu

Donald G Kimber

Lynn D Wilcox

Andreas Girgensohn

Chunyuan Liao

Yanxia Zhang

Shang Ma

Sven Kratz

Jonathan T Foote

Laurent Denoue

Hao Hu

Matthew L Cooper

Yulius Tjahjadi

Hao Tang

Francine R Chen

John E Adcock

Chelhwon Kim

John Steven Boreczky

Hanning Zhou

Yanjun Zhu

Scott Carter

Daniel Avrahami

Frank M Shipman, Iii

Anthony Dunnigan

Kazumasa Murai

Xin Yang

Tohru Fuse

Maribeth Joy Back

Shingo Uchihashi

Hideto Oda

Yin-Ying Chen

Hai Tao

Miteshkumar Patel

Wolfgang Polak

Koichi Fujii

Volker Roth

John J Doherty

Bee Yian Liew

Chidansh Amitkumar Bhatt

Althea Turner

Hironori Yano

Surapong Lertsithichai

Don Kimber

Ming Yang

Xuemin Liu

Jochen Huber

Andrew Allan Port

Doga Buse Cavdir

Chang Hu

Paul P McEvoy

Jack Yang

Hangjin Zhang

Timothy E Black

Yu-Ding Lu

Ray Yuan

Mingming Fan

A computer-implemented method, comprising receiving an order associated with a user, and capturing information associated with a physical attribute of the user; for the order being completed, performing a matching operation on the physical attribute of the user and information associated with a region of the user that includes the physical attribute of the user and respective physical attributes of other users, to determine a closest match; and generating an output that identifies the user associated with the closest match in the information associated with the region of the user, and providing the output to a server to deliver the order to the user.

Systems and methods for reducing service errors for restaurants

A computer-implemented method comprises receiving an input associated with the arrival of an entity, performing a classification on the input to determine a purpose of the arrival of the entity, and based on a determined classification of the purpose of the arrival of the entity, invoking an action.

Building entry management system

A computer-implemented method of learning sensory media association includes receiving a first type of nontext input and a second type of nontext input; encoding and decoding the first type of nontext input using a first autoencoder having a first convolutional neural network, and the second type of nontext input using a second autoencoder having a second convolutional neural network; bridging first autoencoder representations and second autoencoder representations by a deep neural network that learns mappings between the first autoencoder representations associated with a first modality and the second autoencoder representations associated with a second modality; and based on the encoding, decoding, and the bridging, generating a first type of nontext output and a second type of nontext output based on the first type of nontext input or the second type of nontext input in either the first modality or the second modality.

System and method for learning sensory media association without using text labels

A computer-implemented method includes receiving first inputs associated with a first modality and second inputs associated with a second modality; processing the received first and second inputs with convolutional neural networks (CNN), wherein a set of first weights are used to handle the first inputs and a second set of weights are used to handle the second inputs; determining a loss for each of the first and the second inputs based on a loss function that applies the first set of weights, the second set of weights, and a presence of a co-occurrence; generating a shared feature space as an output of the CNNs, wherein a distance between cells associated with the first inputs and the second inputs in the shared feature space is determined based on the loss associated with each of the first inputs and the second inputs; and based on the shared feature space, providing an output.

System and method for automated learning from sensors

A computer-implemented method is provided, comprising, based on information of a subject positioned on an object in an environment, generating a data stream; for the data stream, extracting features associated with a movement of the subject with respect to the object or the environment, wherein the movement is represented by spatio-temporal features extracted from sensors; generating a prediction associated with a likelihood of the movement based on the extracted features, and a risk profile of the movement based on a plurality of fall risk factors; and applying the prediction and the risk profile to a rule base to perform an action.

System and method for event prevention and prediction

A computer-implemented method, comprising, extracting a video sequence, the video sequence including a series of video frames, estimating current poses of one or more subjects within each video frame and determining joint locations for a joint associated with the one or more subjects within each video frame, computing optical flows from the video sequence, extracting motion features from the video sequence based on the optical flows, and predicting at least one future pose.

System and method for vision-based joint action and pose motion forecasting

Example implementations described herein are directed to the transmission of hand information from a user hand or other object to a remote device via browser-to-browser connections, such that the hand or other object is oriented correctly on the remote device based on orientation measurements received from the remote device. Such example implementations can facilitate remote assistance in which the user of the remote device needs to view the hand or object movement as provided by an expert for guidance.

Web-based remote assistance system with context and content-aware 3D hand gesture visualization

Systems and methods for automatic detection and insetting of digital streams into a video. Various examples of such regions of interest to the user include, without limitation, content displayed on various electronic displays or written on electronic paper (electronic ink), content projected on various surfaces using electronic projectors, content of paper documents appearing in the video and/or content written on white (black) boards inside the video. For some content, such as whiteboards, paper documents or paintings in a museum, a participant (or curator) could have taken pictures of the regions, again stored digitally somewhere and available for download. These digital streams with content of interest to the user are obtained and then inset onto the view generated from the raw video feed, giving users the ability to view them at their native high resolution.

Systems and methods for automatic detection and insetting of digital streams into a video

Example implementations described herein are directed to systems and methods for skill assessment, such as hand washing compliance in hospitals, or assembling products in factories. Example implementations involve body part tracking (e.g., hands), skeleton tracking and deep neural networks to detect and recognize sub-tasks and to assess the skill on each sub-task. Furthermore, the order of the sub-tasks is checked for correctness. Beyond monitoring individual users, example implementations can be used for analyzing and improving workflow designs with multiple sub-tasks.

Methods for real-time skill assessment of multi-step tasks performed by hand movements using a video camera

A computer implemented method is provided that includes embedding a received signal in a first modality, re-embedding the embedded received signal of the first modality into a signal of a second modality, and generating an output in the second modality, and based on the output, rendering a signal in the second modality that is configured to be sensed, wherein the embedding, re-embedding and generating applies a model that is trained by performing an adversarial learning operation associated with discriminating actual examples of the target distribution from the generated output, and performing a metric learning operation associated with generating the output having perceptual distances.

Transmodal translation of feature vectors to audio for assistive devices

A computer-implemented method, comprising extracting each frame of a video sequence, estimating current poses of a subject within each frame and determining joint locations for a joint associated with the subject within each frame, computing optical flows between each pair of consecutive video frames, extracting motion features from each video frame of the video sequence based on the optical flows, encoding state information based on the current poses and the motion features, determining a current action label for each motion feature in the state information for a first frame; predicting future action labels for each motion feature in a second frame subsequent to the first frame, based on the current pose, action label and state information, predicting future poses for each motion feature in the second frame based on the current poses and the state information; and refining the current action label, the future action labels, and the future poses.

Systems and methods for automatic detection and insetting of digital streams into a 360 video. Various examples of such regions of interest to the user include, without limitation, content displayed on various electronic displays or written on electronic paper (electronic ink), content projected on various surfaces using electronic projectors, content of paper documents appearing in the 360-degree video and/or content written on white (black) boards inside the 360-degree video. For some content, such as whiteboards, paper documents or paintings in a museum, a participant (or curator) could have taken pictures of the regions, again stored digitally somewhere and available for download. These digital streams with content of interest to the user are obtained and then inset onto the 360-degree view generated from the raw 360-degree video feed, giving users the ability to view them at their native high resolution.

Systems and methods for automatic detection and insetting of digital streams into a 360-degree video

Systems and methods for automated vehicle guidance based on coded lighting to enable automated vehicle following and/or regrouping. Systems use projectors to project temporal identifiers for space partitioned by pixel projections. Different space partition is associated with a different identifier. By using simple light sensors mounted on the vehicles, and decoding the sensed light signal, the vehicle can determine its precise location in the space relative to the coded light projector. This information may be used for precise vehicle guidance to enable vehicle following and/or regrouping. For vehicle following, the coded light projector is placed on a moving vehicle. For vehicle regrouping, the coded light projector may be placed on a ground or on a pole. Depending on the guidance precision requirements, the coded light precision may be adjusted by using light projectors with different resolutions.

Systems and methods for automated vehicle following and regrouping

A computer-implemented system and method for using certain simulated sensors constructed with an accurate localization sensor and a mobile phone to replace/enhance many existing real-life sensors. By using 'simulated sensor' to convert localization sensor measurement to real signal outputs that are similar to real distance-sensor outputs, real direction sensor outputs, or real line following sensor outputs, one or more embodiments of the invention may be used to upgrade traditional robots by plugging these simulated outputs to robots' corresponding sensor inputs without the need to rewire or add customized hardware.

Systems and methods for using an external sensor and a mobile device to simulate real sensors for a robot

Described is a way to steer speaker array or microphone array based on direction outputs of tiny light sensors attached to TV viewers, noisy-environment workers, or AR/VR system users. More specifically, a light projector is disposed on a ceiling, which sends out different sequential on/off signals for each pixel. Two light sensors are attached to each speaker array or microphone array, and one or more light sensors are attached to each user. Because each projector pixel corresponds to a specific direction, when a light sensor receives sequential signal from the projector, the light sensor can determine its direction corresponding to the projector and report that to the central station. With the speaker/microphone array direction and user direction known, the system can generate proper phase shifts for different speaker signals and generate directional sound for each individual. Similarly, the central station can determine phase shifts for combining audios from different microphones.

Systems and methods for steering speaker array and microphone array with encoded light rays

Growing community of inventors

Milpitas, CA, United States of America

Qiong Liu