Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

Other

Antonio Criminisi

Jamie Daniel Joseph Shotton

Andrew Blake

Andrew William Fitzgibbon

Toby Leonard Sharp

Pushmeet Kohli

Carsten Rother

Shahram Izadi

John Michael Winn

Geoffrey Cross

Jamie Shotton

Vladimir Kolmogorov

Stephen Edward Hodges

Steven J White

Lyndsay Williams

Kenneth Robert Wood

Duncan Paul Robertson

Khan Mohammad Siddiqui

James Srinivasan

Aditya Vithal Nori

Peter Kontschieder

Matthew Darius Cook

Ankur Agarwal

Kentaro Toyama

Otmar Hilliges

David G Molyneaux

Carsten Curt Eckard Rother

Prakash Ramu

Reinhard Sebastian Bernhard Nowozin

Sharon Alpert

Sayan Dev Pathak

Christopher Zach

Philip H S Torr

Michel Gangnet

Brandon Michael Smith

Patrick Perez

Ryutaro Tanno

Benjamin Michael Glocker

Durga Venkata Kiran Yakkala

Ender Konukoglu

Ross Brook Girshick

Richard S Szeliski

Sing Bing Kang

Adriana Dumitras

Amit Kumar Agrawal

Denis Demandolx

Matthew Uyttendaele

Apoorv Chaudhri

Noam Sorek

David Kim

William A S Buxton

Cem Keskin

John Herbert Chiloyan

Eric Paul Bennett

Henrik Valdemar Turbell

Visesh Uday Kumar Chari

Siddharth Choudhary

Siddhartha Chandra

Dimitrios Vytiniotis

Jinjin Li

Sean Ryan Francesco Fanello

Gavin Smyth

Ridge Carpenter

Jonas Dorn

Darko Zikic

Mat Cook

Osbert Bastani

Srikumar Ramalingam

Leonidas Lampropoulos

Ganesh Subramanian Iyer

F Noam Sorek

Indeera Munasinghe

Mitch Goldberg

Varun Gulshan

Amit Shesh

Vladimir Farbman

Evgeny Salnikov

Bill Buxton

Thomas Deselaers

A predictor has a memory which stores at least one example for which an associated outcome is not known. The memory stores at least one decision tree comprising a plurality of nodes connected by edges, the nodes comprising a root node, internal nodes and leaf nodes. Individual ones of the nodes and individual ones of the edges each have an assigned module, comprising parameterized, differentiable operations, such that for each of the internal nodes the module computes a binary outcome for selecting a child node of the internal node. The predictor has a processor configured to compute the prediction by processing the example using a plurality of the differentiable operations selected according to a path through the tree from the root node to a leaf node.

Neural trees

Described are systems and methods directed to a body change journey that utilizes one or more current body measurement values, one or more goal body measurement values, and a cohort to determine a body change journey that a user can follow to progress from the current body measurement value to the goal body measurement value. The cohort may include a plurality of data of other bodies who have progressed from a starting body measurement value that is similar to the current body measurement value.

Cohort based body change journeys

Systems for preparing a medical report, and related methods, generate and output feedback indicative or potential errors in the medical report. A system for preparing a medical report is configured to receive image data for a medical image of a patient, display the medical image, monitor content of the medical report during preparation of the medical report, process the image data to detect one or more organs of the patient imaged in the medical image, compare the content of the medical report with the one or more organs imaged in the medical image to detect one or more potential errors in the medical report, and output feedback indicative of the one or more potential errors in the medical report.

Methods and systems for detection of errors in medical reports

Systems and techniques for producing image-based radiology reports including contextual cropping of image data and radiologist supplied notes and annotations are provided herein. Computer vision and natural language processing algorithms may enable processing of image data and language inputs to identify objects associated with annotations, aid in cropping the image data according to the annotations and object identification and in producing a final text and image laden report.

Contextual image cropping and report generation

Described are systems and methods directed to generation and subsequent update of a dimensionally accurate body model of a body, such as a human body, based on two-dimensional ('2D') images of at least a portion of that body and/or face images of a face of the body. A user may use a 2D camera, such as a digital camera typically included in many of today's portable devices (e.g., cell phones, tablets, laptops, etc.) to produce body images that are used to generate a body model of the body of the user. Subsequently, the body model may be updated based on a face image of the face of the user, without requiring the user to provide another body image.

Body model composition update from two-dimensional face images

Described are systems and methods to determine one or more body dimensions of a body based on a processing of one or more two-dimensional images that include a representation of the body. Body dimensions include any length, circumference, etc., of any part of a body, such as shoulder circumference, chest circumference, waist circumference, hip circumference, inseam length, bicep circumference, leg circumference, etc.

Body dimensions from two-dimensional body images

Camera or object pose calculation is described, for example, to relocalize a mobile camera (such as on a smart phone) in a known environment or to compute the pose of an object moving relative to a fixed camera. The pose information is useful for robotics, augmented reality, navigation and other applications. In various embodiments where camera pose is calculated, a trained machine learning system associates image elements from an image of a scene, with points in the scene's 3D world coordinate frame. In examples where the camera is fixed and the pose of an object is to be calculated, the trained machine learning system associates image elements from an image of the object with points in an object coordinate frame. In examples, the image elements may be noisy and incomplete and a pose inference engine calculates an accurate estimate of the pose.

Camera/object pose from predicted coordinates

Memory facilitation using directed acyclic graphs is described, for example, where a plurality of directed acyclic graphs are trained for gesture recognition from human skeletal data, or to estimate human body joint positions from depth images for gesture detection. In various examples directed acyclic graphs are grown during training using a training objective which takes into account both connection patterns between nodes and split function parameter values. For example, a layer of child nodes is grown and connected to a parent layer of nodes using an initialization strategy. In examples, various local search processes are used to find good combinations of connection patterns and split function parameters.

Memory facilitation using directed acyclic graphs

Image labeling is described, for example, to recognize body organs in a medical image, to label body parts in a depth image of a game player, to label objects in a video of a scene. In various embodiments an automated classifier uses geodesic features of an image, and optionally other types of features, to semantically segment an image. For example, the geodesic features relate to a distance between image elements, the distance taking into account information about image content between the image elements. In some examples the automated classifier is an entangled random decision forest in which data accumulated at earlier tree levels is used to make decisions at later tree levels. In some examples the automated classifier has auto-context by comprising two or more random decision forests. In various examples parallel processing and look up procedures are used.

Image labeling using geodesic features

Video processing for motor task analysis is described. In various examples, a video of at least part of a person or animal carrying out a motor task, such as placing the forefinger on the nose, is input to a trained machine learning system to classify the motor task into one of a plurality of classes. In an example, motion descriptors such as optical flow are computed from pairs of frames of the video and the motion descriptors are input to the machine learning system. For example, during training the machine learning system identifies time-dependent and/or location-dependent acceleration or velocity features which discriminate between the classes of the motor task. In examples, the trained machine learning system computes, from the motion descriptors, the location dependent acceleration or velocity features which it has learned as being good discriminators. In various examples, a feature is computed using sub-volumes of the video.

Video processing for motor task analysis

A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine has an adversarial example generator which computes a plurality of adversarial images by, for each adversarial image, searching a region in the input space around one of the training images, the region being one in which the neural network is linear, to find an image which is incorrectly classified into the plurality of classes by the neural network. The training engine has a processor which further trains the neural network image classifier using at least the adversarial images.

Neural network image classifier

Filtering sensor data is described, for example, where filters conditioned on a local appearance of the signal are predicted by a machine learning system, and used to filter the sensor data. In various examples the sensor data is a stream of noisy video image data and the filtering process denoises the video stream. In various examples the sensor data is a depth image and the filtering process refines the depth image which may then be used for gesture recognition or other purposes. In various examples the sensor data is one dimensional measurement data from an electric motor and the filtering process denoises the measurements. In examples the machine learning system comprises a random decision forest where trees of the forest store filters at their leaves. In examples, the random decision forest is trained using a training objective with a data dependent regularization term.

Sensor data filtering

Image registration is described. In an embodiment an image registration system executes automatic registration of images, for example medical images. In an example, semantic information is computed for each of the images to be registered comprising information about the types of objects in the images and the certainty of that information. In an example a mapping is found to register the images which takes into account the intensities of the image elements as well as the semantic information in a manner which is weighted by the certainty of that semantic information. For example, the semantic information is computed by estimating posterior distributions for the locations of anatomical structures by using a regression forest and transforming the posterior distributions into a probability map. In an example the mapping is found as a global point of inflection of an energy function, the energy function having a term related to the semantic information.

Image registration

Growing community of inventors

Cambridge, United Kingdom

Antonio Criminisi