Fujifilm Business Innovation Corp.

Fuji Xerox Co., Ltd.

Yanxia Zhang

Qiong Liu

Hao Hu

Francine R Chen

Andreas Girgensohn

Yanjun Zhu

Patrick Chiu

Daniel Avrahami

Chelhwon Kim

Lynn D Wilcox

Laurent Denoue

Donald G Kimber

Maribeth Joy Back

Hideto Oda

Yin-Ying Chen

Yulius Tjahjadi

Chidansh Amitkumar Bhatt

Ray Yuan

Yu-Ding Lu

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 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, 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.

A computer-implemented method is provided for coordinating sensed poses associated with real-time movement of a first object in a live video feed, and pre-recorded poses associated with movement of a second object in a video. The computer-implemented method comprises applying a matching function to determine a match between a point of one of the sensed poses and a corresponding point of the pre-recorded poses, and based on the match, determining a playtime and outputting at least one frame of the video associated with the second object for the playtime.

Growing community of inventors

Cupertino, CA, United States of America

Yanxia Zhang