Sony Computer Entertainment Inc.

Sony Interactive Entertainment Inc.

Other

Sony Corporation

Tsinghua University

Sony Electronics Inc

Ruxin Chen

Xavier Menendez-Pidal

Steven Osman

Duanpei Wu

Jaekwon Yoo

Miyuki Tanaka

Lex S Olorenshaw

Gustavo Hernandez-Abrego

Richard Lee Marks

Javier Fernandez Rico

Naveen Kumar

Michael G Taylor

Xiaodong Mao

Eric James Larsen

Erik Beran

Ozlem Kalinli

Rishi Deshpande

Care Michaud-Wideman

Haoqi Li

Glenn T Black

Dennis Dale Castleman

Hrishikesh R Deshpande

Xiaoyu Liu

Ozlem Kalinli-Akbacak

Frank Zhao

Gustavo Hernandez Abrego

Jian Zheng

Min-Hung Chen

Dominic Saul Mallinson

Xiadong Mao

Anton Mikhailov

Makoto Akabane

Yoshikazu Takahashi

Sergey Bashkirov

Michael Taylor

Arindam Jati

Javier Fernandez-Rico

Fang Zheng

Masanori Omote

Xi Xiao

Linquan Liu

Zhan You

Wenxiao Cao

Seth C H Luisi

Xavier Men&eacute;ndez-Pidal

Chenhao Zhang

Thomas Fang Zheng

Methods and systems are provided for providing real world assistance by a robot utility and interface device (RUID) are provided. A method provides for identifying a position of a user in a physical environment and a surface within the physical environment for projecting an interactive interface. The method also provides for moving to a location within the physical environment based on the position of the user and the surface for projecting the interactive interface. Moreover, the method provides for capturing a plurality of images of the interactive interface while the interactive interface is being interacted with by the use and for determining a selection of an input option made by the user.

Robot utility and interface device

A system, method, and computer program product for hierarchical categorization of sound comprising one or more neural networks implemented on one or more processors. The one or more neural networks are configured to categorize a sound into a two or more tiered hierarchical coarse categorization and a finest level categorization in the hierarchy. The categorization sound may be used to search a database for similar or contextually related sounds.

Sound categorization system

In sequence level prediction of a sequence of frames of high dimensional data one or more affective labels are provided at the end of the sequence. Each label pertains to the entire sequence of frames. An action is taken with an agent controlled by a machine learning algorithm for a current frame of the sequence at a current time step. An output of the action represents affective label prediction for the frame at the current time step. A pool of actions taken up until the current time step including the action taken with the agent is transformed into a predicted affective history for a subsequent time step. A reward is generated on predicted actions up to the current time step by comparing the predicted actions against corresponding annotated affective labels.

Deep reinforcement learning framework for sequence level prediction of high dimensional data

A domain adaptation module is used to optimize a first domain derived from a second domain using respective outputs from respective parallel hidden layers of the domains.

Systems and methods for domain adaptation in neural networks using cross-domain batch normalization

An autonomous personal companion executing a method including capturing data related to user behavior. Patterns of user behavior are identified in the data and classified using predefined patterns associated with corresponding predefined tags to generate a collected set of one or more tags. The collected set is compared to sets of predefined tags of a plurality of scenarios, each to one or more predefined patterns of user behavior and a corresponding set of predefined tags. A weight is assigned to each of the sets of predefined tags, wherein each weight defines a corresponding match quality between the collected set of tags and a corresponding set of predefined tags. The sets of predefined tags are sorted by weight in descending order. A matched scenario is selected for the collected set of tags that is associated with a matched set of predefined tags having a corresponding weight having the highest match quality.

Continual selection of scenarios based on identified tags describing contextual environment of a user for execution by an artificial intelligence model of the user by an autonomous personal companion

Systems and methods for domain adaptation in neural networks using domain classifier

Methods and systems for performing sequence level prediction of a video scene are described. Video information in a video scene is represented as a sequence of features depicted each frame. One or more scene affective labels are provided at the end of the sequence. Each label pertains to the entire sequence of frames of data. An action is taken with an agent controlled by a machine learning algorithm for a current frame of the sequence at a current time step. An output of the action represents affective label prediction for the frame at the current time step. A pool of actions taken up until the current time step including the action taken with the agent is transformed into a predicted affective history for a subsequent time step. A reward is generated on predicted actions up to the current time step by comparing the predicted actions against corresponding annotated scene affective labels.

Deep reinforcement learning framework for characterizing video content

For image captioning such as for computer game images or other images, bottom-up attention is combined with top-down attention to provide a multi-level residual attention-based image captioning model. A residual attention mechanism is first applied in the Faster R-CNN network to learn better feature representations for each region by taking spatial information into consideration. In the image captioning network, taking the extracted regional features as input, a second residual attention network is implemented to fuse the regional features attentionally for subsequent caption generation.

System and method for converting image data into a natural language description

Method for providing image of HMD user to a non-HMD user includes, receiving a first image of a user including the user's facial features captured by an external camera when the user is not wearing a head mounted display (HMD). A second image capturing a portion of the facial features of the user when the user is wearing the HMD is received. An image overlay data is generated by mapping contours of facial features captured in the second image with contours of corresponding facial features captured in the first image. The image overlay data is forwarded to the HMD for rendering on a second display screen that is mounted on a front face of the HMD.

Display screen front panel of HMD for viewing by users viewing the HMD player

Methods and systems for performing sequence level prediction of a video scene are described. Video information in a video scene is represented as a sequence of features depicted each frame. An environment state for each time step t corresponding to each frame is represented by the video information for time step t and predicted affective information from a previous time step t&#x2212;1. An action A(t) as taken with an agent controlled by a machine learning algorithm for the frame at step t, wherein an output of the action A(t) represents affective label prediction for the frame at the time step t. A pool of predicted actions is transformed to a predicted affective history at a next time step t+1. The predictive affective history is included as part of the environment state for the next time step t+1. A reward R is generated on predicted actions up to the current time step t, by comparing them against corresponding annotated movie scene affective labels.

The present disclosure is related to unmanned aerial vehicles or drones that have a capability of quickly swapping batteries. This may be accomplished even as the drone continues to fly. A drone consistent with the present disclosure may drop one battery and pickup another using an attachment mechanism. Attachment mechanisms of the present disclosure may include electro-magnets, mechanical actuators, pins, or hooks. Systems consistent with the present disclosure may also include locations where replacement batteries may be provided to aircraft via actuation devices coupled to a physical location.

UAV battery form factor and insertion/ejection methodologies

A method for improved initialization of speech recognition system comprises mapping a trained hidden markov model based recognition node network (HMM) to a Connectionist Temporal Classification (CTC) based node label scheme. The central state of each frame in the HMM are mapped to CTC-labeled output nodes and the non-central states of each frame are mapped to CTC-blank nodes to generate a CTC-labeled HMM and each central state represents a phoneme from human speech detected and extracted by a computing device. Next the CTC-labeled HMM is trained using a cost function, wherein the cost function is not part of a CTC cost function. Finally the CTC-labeled HMM is trained using a CTC cost function to produce a CTC node network. The CTC node network may be iteratively trained by repeating the initialization steps.

Initialization of CTC speech recognition with standard HMM

Growing community of inventors

Redwood City, CA, United States of America

Ruxin Chen