Microsoft Technology Licensing, LLC

Lyft, Inc.

Amazon Technologies, Inc.

Woven Planet North America, Inc.

Other

Kumar Hemachandra Chellapilla

Patrice Y Simard

Anton Mityagin

Denis X Charles

Paul A Viola

David Tse-Zhou Lu

Sameer Qureshi

Emilie Jeanne Anne Danna

Reid Andersen

Xuanhui Wang

Tanner Cotant Christensen

Suneet Rajendra Shah

Joan Devassy

Newton Ko Yue Der

Alexis Weill

Rupsha Chaudhuri

Daniel Allen Rosenfeld

Radoslav Petrov Nickolov

Jack W Stokes

Li Erran Li

Gregory T Buehrer

Chinmay Karande

Patrick Guy Haffner

John Carlton Platt

David Maxwell Chickering

Cormac E Herley

Ismail Cem Paya

David Bargeron

Junaid Ahmed

Ahmad A Abdulkader

Michael Shilman

Abhishek Kumar Singh

Nikita Igorevych Lytkin

David W Steinkraus

Wolf Kienzle

David Max Chickering

Leon Bottou

Walter Sun

Erren Dusan Lester

Alexey Maykov

Trausti Thor Kristjansson

Fabrice Canel

Thomas Francis McElroy

Alex Williams

Ajit Paul Singh

Vishnu Challam

Weifeng Chen

Nikolai Avteniev

Eran Leshem

Greg Buehrer

Shannon A Kallin

Brandon Duncan

Patrice Y Simmard

Jonathan Buck

Min Bai

Matthew Alan Lease

This disclosure describes automatically identifying videos of a video dataset having high-content similarity and grouping the videos together with one or more possible tags for the videos for consideration by annotators. A labeling service of a service provider network receives (i) a dataset of unlabeled videos and (ii) category tags for labeling the videos from a client device associated with a user. A video data modeling engine analyzes the dataset to provide a set of ranked unlabeled videos from the dataset, wherein the set of ranked unlabeled videos are ranked according to confidence scores with respect to at least one tag. Based at least in part on the confidence scores, at least some of the unlabeled videos are labeled with the at least one tag to provide a dataset of labeled videos. The dataset of labeled videos is provided to a database and/or the user.

Automated identification of labels for videos with a labeling service within a service provider network

Systems, methods, and non-transitory computer-readable media can determine a first utility metric associated with a region and first autonomous vehicle eligibility criteria, wherein the first utility metric is determined based on a first plurality of rides and a subset of the first plurality of rides that can be successfully executed within the region based on the first autonomous vehicle eligibility criteria. A second utility metric associated with the region and second autonomous vehicle eligibility criteria can be determined, wherein the second utility metric is determined based on a second plurality of rides and a subset of the second plurality of rides that can be successfully executed within the region based on the second autonomous vehicle eligibility criteria. An autonomous vehicle associated with the first autonomous vehicle eligibility criteria can be selected to drive in the region based on a comparison of the first utility metric and the second utility metric.

Systems and methods for autonomous vehicle performance evaluation

Adjustments to bounding shapes for detected objects in image data may be independently determined. A bounding shape for an object detected in image data may be obtained. Independently determined adjustments for one or more edges of the bounding shape may be determined according to a multi-scale feature map generated from different resolutions of the image data that is provided as input to different dimension decoders to determine the adjustments to the bounding shape and respective confidence scores for the adjustments. The confidence scores are evaluated with respect to a confidence threshold to determine whether to provide the adjustments to the one or more edges of the bounding shape.

Independently determining adjustments to bounding shapes for detected objects in image data

Systems, methods, and non-transitory computer-readable media can receive transportation information associated with a transportation request, the transportation information comprising a pick up location and a drop off location. A first route associated with the transportation request and a non-autonomous vehicle can be determined. A second route associated with the transportation request and an autonomous vehicle can be determined based on an operating design domain (ODD) associated with one or more autonomous vehicles in a fleet of vehicles. At least one performance metric associated with the second route can be determined. The second route can be selected based at least in part on the at least one performance metric and a comparison of the first route and the second route. An autonomous vehicle from the fleet of vehicles can be assigned to the transportation request based on selection of the second route.

Examples disclosed herein may involve (i) based on an analysis of 2D data captured by a vehicle while operating in a real-world environment during a window of time, generating a 2D track for at least one object detected in the environment comprising one or more 2D labels representative of the object, (ii) for the object detected in the environment: (a) using the 2D track to identify, within a 3D point cloud representative of the environment, 3D data points associated with the object, and (b) based on the 3D data points, generating a 3D track for the object that comprises one or more 3D labels representative of the object, and (iii) based on the 3D point cloud and the 3D track, generating a time-aggregated, 3D visualization of the environment in which the vehicle was operating during the window of time that includes at least one 3D label for the object.

Systems and methods for computer-based labeling of sensor data captured by a vehicle

Systems, methods, and non-transitory computer-readable media can receive disengagement information associated with one or more autonomous vehicles, the disengagement information identifying a plurality of disengagements of an autonomy system during operation of the one or more autonomous vehicles. Each disengagement of the plurality of disengagements can be categorized based on a plurality of categories, wherein a first category of the plurality of categories is associated with disengagement that would not have led to a negative outcome. A performance metric associated with the one or more autonomous vehicles can be determined based on the categorizing each disengagement of the plurality of disengagements. Autonomous vehicle performance of the one or more autonomous vehicles can be evaluated based on the performance metric.

Examples disclosed herein may involve (i) identifying, in a 3D point cloud representative of a real-world environment in which a vehicle was operating during a window of time, a set of 3D data points associated with an object detected in the environment that comprises different subsets of 3D data points corresponding to different capture times within the window of time, (ii) based at least on the 3D data points, evaluating a trajectory of the object and thereby determining that the object was in motion during some portion of the window of time, (iii) in response to determining that the object was in motion, reconstructing the different subsets of 3D data points into a single, assembled 3D representation of the object, and (iv) generating a time-aggregated, 3D visualization of the environment that presents the single, assembled 3D representation of the object at one or more points along the trajectory of the object.

Systems and methods for presenting a reconstructed representation of a moving object detected in a scene

Disclosed in some examples are methods, systems, and machine-readable mediums which automatically determine network-based data sources for information ingestion and profile data completion. This method can be applied to automatically increase the library of network-based data sources utilized by the system to ingest profile information. This allows for more a complete tracking of member accomplishments and attributes and ultimately, allows for more complete member profiles. Before specific methods and systems for automatically determining network-based data sources are discussed, an overview of the process of ingesting information from network-based data sources and matching that information to members of the social networking service will be described.

Discovery of network based data sources for ingestion and recommendations

Methods, systems, and computer-storage media having computer-usable instructions embodied thereon for calculating event probabilities are provided. The event may be a click probability. Event probabilities are calculated using a system optimized for runtime model accuracy with an operable learning algorithm. Bin counting techniques are used to calculate event probabilities based on a count of event occurrences and non-event occurrences. Linear parameters, such and counts of clicks and non-clicks, may also be used in the system to allow for runtime adjustments.

Click prediction using bin counting

A client application installed on end user computers generates metadata from the content of web pages visited by end users and provides the metadata to a search engine. When an end user visits a web page, the end user's computer downloads and displays the web page to the end user. The client application may simultaneously access the web page content and generate this metadata in the form of a content signature of the web page from the web page content. The client application then provides the content signature to a search engine. The search engine may employ content signatures to identify new web pages to crawl and index. Additionally, the search engine may employ content signatures to identify changes to web pages and determine the crawl frequency of web pages.

Content signature notification

A printer, scanner device and methods for using same are described herein. A printer device may include a dedicated input that, when actuated, generates and sends a request to a computer for known data or a predetermined print job, e.g., schedule information from a personal information management (PIM) application. A scanner device may include another dedicated input that, when actuated, automatically scans a document fed to the device by the user and sends the scanned image to IM (or other) software on a computer, bypassing the need to manipulate the scanned image using scanner software. The device may be used with printed metapaper, which includes a barcode or other indicia identifying the metapaper and corresponds to a stored template image of the metapaper. When the metapaper is rescanned, the scan can be compared to the stored template information to identify changes and synchronize the changes with the IM software.

Interactive paper system

A human or hand-labeled ranking of URL results for a search query is compared against actual click data for the respective query/URL pairs (e.g., which URLs were actually clicked on by users when the URLs were presented to users when the search query was run in the real world). The human ranking or ordering of the URL results (e.g., pre-existing relevance ranking) for the query can then be adjusted, if necessary, based upon the real world click data (e.g., click relevance ranking). The modified pre-existing relevance ranking can be used in providing future search results.

Web searching

The behavior of browser applications, such as web browsers, can be controlled in part by script-based instructions present within documents read by those browsers. To analyze such scripts in an efficient manner, a script analyzer can identify the scripts in the document, divide them into script modules, and order the modules to represent an interpretational flow. The script can be interpreted and executed on a line-by-line basis and its behavior analyzed. Prior to interpretation, the scripts can be reviewed for delay conditionals, and such statements can be modified for more efficient interpretation. Additionally, if, during interpretation, the script generates new script, or modifies existing script, such new scripts can be themselves interpreted. External function calls made by the script can be intercepted and responded to in a generic fashion, limiting the need to create a document object model, based on the document's data, solely for script analysis purposes.

High performance script behavior detection through browser shimming

Short paths are found with a small query time in scale-free directed graphs using a two-phase process by which data structures comprising shortest path trees are first pre-computed for a group of central vertices called 'hubs' that have short paths to most other vertices in the graph. In a query time phase, a short path between two vertices of interest in the graph is found by looking up the path to the root in each of the shortest path trees.

Short paths in web graphs with small query time

Growing community of inventors

Redmond, WA, United States of America

Kumar Hemachandra Chellapilla