Mftb Holdco, Inc.

University of Central Florida Research Foundation Inc

Zillow, Inc.

Netflix Inc.

Naji Khosravan

Sing Bing Kang

Ivaylo Boyadzhiev

Yuguang Li

Pierre Moulon

Ulas Bagci

Will Adrian Hutchcroft

Lambert E Wixson

Yujie Li

Viktoriya Stoeva

Rohit Puri

Manjunath Narayana

Sarfaraz Hussein

Shervin Ardeshir Behrostaghi

Rodney LaLonde

Lichen Wang

Will Hutchcroft

A valuation system to identify interior features of a property, identify exterior features related to interior features using aerial images, and to generate property valuations based on the identified features is provided. The valuation system identifies, using a computer vision module, interior features based on interior image data (e.g., photos) of a property, and further identifies exterior features associated with any of the interior features based on an aerial photo of the property. For example, trees and buildings (e.g., exterior features) adjacent to a window (e.g., an interior feature) can be identified by a computer vision module through the combination of interior and exterior image data. In other words, the identification of property features by the computer vision module can be enriched by correlating interior image data (e.g., photos, video walkthroughs) to exterior image data (e.g., satellite photos, aerial photos).

Home valuation using identified exterior and interior features systems and methods

A neural network system that is trained to identify one or more portions of a media title where synchronization errors are likely to be present. The neural network system is trained based on a first set of media titles where synchronization errors are present and a second set of media titles where synchronization errors are absent. The second set of media titles can be generated by introducing synchronization errors into a set of media titles that otherwise lack synchronization errors. Via training, the neural network system learns to identify specific visual features included in one or more video frames and corresponding audio features that should be played back in synchrony with the associated visual features. Accordingly, when presented with a media title that includes synchronization errors, the neural network can indicate the specific frames where synchronization errors are likely to be present.

Techniques for identifying synchronization errors in media titles

Techniques are described for automated operations related to analyzing visual data from images captured in rooms of a building and optionally additional captured data about the rooms to assess room layout and other usability information for the building's rooms and optionally for the overall building, and to subsequently using the assessed usability information in one or more further automated manners, such as to improve navigation of the building. The automated operations may include identifying one or more objects in each of the rooms to assess, evaluating one or more target attributes of each object, assessing usability of each object using its target attributes' evaluations and each room using its objects' assessment and other room information with respect to an indicated purpose, and combining the assessments of multiple rooms in a building and other building information to assess usability of the building with respect to its indicated purpose.

Automated usability assessment of buildings using visual data of captured in-room images

Techniques are described for using computing devices to perform automated operations to generate mapping information of a defined area via analysis of visual data of images, including by using attribute information exchanged between paired or otherwise grouped images of multiple types to generate enhanced images, and for using the generated mapping information in further automated manners, including to use the generated mapping information for automated navigation and/or to display or otherwise present the generated mapping information. In some situations, the defined area includes an interior of a multi-room building, and the generated information includes at least one or more enhanced images and/or a partial floor plan and/or other modeled representation of the building, with the generating performed in some cases without having measured depth information about distances from the images' acquisition locations to walls or other objects in the surrounding building.

Automated exchange and use of attribute information between building images of multiple types

Techniques are described for using computing devices to perform automated operations for determining matching buildings and using corresponding information in further automated manners, such as by determining buildings having similarities to other indicated buildings based at least in part on building floor plans and/or other attributes, and by automatically generating descriptions of the similarities. In some situations, such matching building determinations are based on generating and using adjacency graphs for floor plans that represent inter-connections between rooms and other attributes of the buildings, and further generating and comparing vector-based embeddings that concisely represent the information of the adjacency graphs for use in performing inter-building comparisons and generating the descriptions. Information about such determined buildings may be used in various automated manners, including for controlling device navigation (e.g., autonomous vehicles), for display on client devices in corresponding graphical user interfaces, for further analysis to identify shared and/or aggregate characteristics, etc.

Automated building identification using floor plans and acquired building images

A method of detecting and diagnosing cancers characterized by the presence of at least one nodule/neoplasm from an imaging scan is presented. To detect nodules in an imaging scan, a 3D CNN using a single feed forward pass of a single network is used. After detection, risk stratification is performed using a supervised or an unsupervised deep learning method to assist in characterizing the detected nodule/neoplasm as benign or malignant. The supervised learning method relies on a 3D CNN used with transfer learning and a graph regularized sparse MTL to determine malignancy. The unsupervised learning method uses clustering to generate labels after which label proportions are used with a novel algorithm to classify malignancy. The method assists radiologists in improving detection rates of lung nodules to facilitate early detection and minimizing errors in diagnosis.

Method for detection and diagnosis of lung and pancreatic cancers from imaging scans

Techniques are described for computing devices to perform automated operations to determine the acquisition locations of images, such as within a building interior based on automatically determined shapes of rooms of the building, and for using the determined image acquisition location information in further automated manners. The image may be a panorama image or of another type (e.g., a rectilinear perspective image) and acquired at an acquisition location in a multi-room building's interior, and the determined acquisition location for such an image may be at least a location on the building's floor plan and optionally an orientation/direction for at least a part of the image&#x2014;in addition, the automated image acquisition location determination may be further performed without having or using information from any depth sensors or other distance-measuring devices about distances from an image's acquisition location to walls or other objects in the surrounding building.

Automated determination of acquisition locations of acquired building images based on determined surrounding room data

Techniques are described for using computing devices to perform automated operations for determining the acquisition location of an image using an analysis of the image's visual contents. In at least some situations, images to be analyzed include panorama images acquired at acquisition locations in an interior of a multi-room building, and the determined acquisition location information includes a location on a floor plan of the building and in some cases orientation direction information&#x2014;in at least some such situations, the acquisition location determination is performed without having or using information from any distance-measuring devices about distances from an image's acquisition location to objects in the surrounding building. The acquisition location information may be used in various automated manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.

Automated analysis of image contents to determine the acquisition location of the image

An improved method of performing object segmentation and classification that reduces the memory required to perform these tasks, while increasing predictive accuracy. The improved method utilizes a capsule network with dynamic routing. Capsule networks allow for the preservation of information about the input by replacing max-pooling layers with convolutional strides and dynamic routing, allowing for the reconstruction of an input image from output capsule vectors. The present invention expands the use of capsule networks to the task of object segmentation and medical image-based cancer diagnosis for the first time in the literature; extends the idea of convolutional capsules with locally-connected routing and propose the concept of deconvolutional capsules; extends the masked reconstruction to reconstruct the positive input class; and proposes a capsule-based pooling operation for diagnosis. The convolutional-deconvolutional capsule network shows strong results for the tasks of object segmentation and classification with substantial decrease in parameter space.

Growing community of inventors

Seattle, WA, United States of America

Naji Khosravan