Abstract: A system for applying metadata tags based on metadata tag groups is described. The system includes a plurality of compute nodes configured to provide a plurality of computing resources for clients of a provider network and a resource tag manager for the provider network. The resource tag manager is configured to receive, from a first client of an account of the provider network, a creation request to establish a resource attribute group comprising a plurality of resource keys and a plurality of resource values, wherein respective metadata keys correspond to respective resource values. The resource tag manager may receive, from a second client of the account, an application request to apply the resource attribute group to a computing resource and apply the plurality of resource keys and the plurality of resource values to metadata maintained for the computing resource.

Abstract: A protected covering for displays used in outdoor environments is provided. Particularly, the protective covering may be provided over a display screen of a delivery locker system. The protective covering may protect the display screen from overheating from sun rays and other heat sources that may exist in an external environment. The protective covering may be configured to be moved between a first position in which the protective covering is covering the display screen and a second position in which the protective covering is not covering the display screen. This allows the protective covering to protect the display screen when not in use but also allow a user to move the protective covering to access the display screen when needed. The protective covering may also include magnets to secure the protective covering to the delivery locker system in the first position or the second position.

Abstract: Systems and methods for performing anomalous activity monitoring for a service provider network are disclosed. In response to receiving an activity log, a machine learning-based activity monitor may parse the activity log into segments, generate event objects from a segment of the activity log, encode the event objects, and then reconstruct the event objects based on decoding the encoded event objects. The encoding and decoding may be performed based on a model that was trained using training data with no known malicious activity. The event objects may comprise at least two or more event defining characteristics and an event count. By comparing the reconstructed event objects to corresponding initial versions of the event objects, the machine learning-activity monitor may determine an anomaly score and may provide an indication of events determined to be anomalous based on the score.

Abstract: Techniques for coordinating output of inferred content using various components and systems are described. A supplemental content system and a notification system may each receive inferred content to be output. When the supplemental content system or the notification system outputs the inferred content, the respective system stores a record of the output of the content in a historical output storage. Thereafter, when the other system is ready to output the inferred content, the other system may prevent the inferred content from being output based on the inferred content having already been output, as represented in the historical output storage.

Abstract: An attestation service is configured to receive a request to enable attestation for a compute instance according to an attestation policy indicating one or more baseline health measurement values for validating compute instances. The attestation service provides a network endpoint for the compute instance to request attestation. The attestation service receives, via the network endpoint from a compute instance, one or more health measurement values of the compute instance. The attestation service validates the compute instance based at least on a comparison of the one or more current health measurement values and the one or more baseline health measurement values. The attestation service, in response to validating the compute instance, generates an attestation token indicating that the compute instance is authorized to access a secured resource of the provider network.

Abstract: Systems and methods are provided for providing a consistent experience for users of cloud-based block storage volumes. While cloud storage aims to remove hardware considerations for an end user's experience, block storage performance can nevertheless vary according to the underlying hardware used to support a volume or the specific network location of that hardware. Embodiments of the present disclosure address that inconsistent performance by associating a volume with a performance profile that sets a target latency for the volume. A storage client can then monitor observed latency for the volume and inject synthetic latency into input/output operations for the volume as calculated via a proportional-integral-derivative algorithm, such that the observed latency matches the target within the performance profile. This enables the cloud provider to vary physical hardware or network configurations without effect on block storage performance from the point of view of an end user.

Abstract: Techniques for reducing the latency of annotating a replay video segment may include receiving a video segment with content involving multiple individuals. An annotation task is performed concurrently with a tracking task. The annotation task receives annotation data to indicate which of the individuals is an individual of interest in a subset of frames of the video segment, and the tracking task tracks the individuals in the video segment by generating bounding objects corresponding to the individuals. The annotation data can be associated with the bounding objects to detect a bounding object for the individual of interest, and a visualization emphasis object is generated based on the detected bounding object in a replay video segment to identify the individual of interest.

Abstract: Methods and systems are described for registering a sports field to a video. Video of a live event may feature participants at a venue. A template of the venue, including virtual markings that represent real markings on the venue, may be obtained. A homographic transformation between an image plane and a ground plane may be determined by matching virtual markings to corresponding real markings captured in at least one frame of the video. The determined homographic transformation may be used in the automated analysis of sports statistics and in improving inserted annotations and visualizations.

Abstract: Technologies are disclosed for managing composite storefront images. The composite storefront images can be generated utilizing portions of media content (e.g., visual content, such as videos, trailers, etc.), and templates generated based on sets of existing storefront images. Objects can be extracted from frames and composited together to generate course composite images. The course composite storefront images can be utilized to map the object portions onto the media content artwork styles to generate refined composite storefront images based on the templates.

Abstract: A first set of instructions, which is provided access to a first address space, is scheduled for execution at a first hardware thread of a processor. Prior to executing an instruction of a second set of instructions, which accesses a second address space, at the first hardware thread, a determination is made that the second address space is accessible from a second hardware thread of the processor.

Abstract: Systems and methods are described for implementing a device isolation service. A device isolation service creates and administers per-device virtual networks for individual computing devices, thereby isolating the computing devices from each other and limiting device-to-device communication. The device isolation service may further provide a monitored and access-controlled network that facilitates access to the isolated devices, thereby allowing “administrator” devices to access and administer devices while preventing a compromised device from seeing, probing, or compromising other devices on the network. The device isolation service may group devices by category or function, and may put devices that communicate with each other on the same virtual network while isolating other devices to different virtual networks.

Abstract: A filtration system for a datacenter or other building can include filter media arranged in an airflow path between an inlet and an outlet each configured for air flow therethrough relative to a chamber. The chamber may be defined at least in part by walls and a floor of a room of the building, for example. The filtration system can further include a dust dislodgment system that dislodges dust accumulated in the filter media. For example, dislodged dust may be permitted to fall toward the floor. The filtration system can further include a dust collection system for collecting and/or removing dislodged dust, such as from the floor.

Abstract: Systems and methods are disclosed for handling items for custom-sized multi-item packages. In one embodiment, an example system may include a multi-item loading component configured to support multiple items, the multi-item loading component including a first surface, a second surface disposed at an angle with respect to the first surface, a first sidewall configured to slide in a vertical direction from a raised position to a lowered position, and a second sidewall configured to slide in the vertical direction from the raised position to the lowered position. The system may include a pusher component configured to push the plurality of items off the multi-item loading component when the first sidewall and the second sidewall are in the lowered position.

Abstract: A data storage interface layer provides access management and transformation of data stored in various backend storage clusters. The data storage interface can serve as a point of access for data accessors to access stored data via a consistent data access protocol, even when a data storage cluster on which requested data is stored may use a different protocol. The data storage interface can also provide in-line transformation of requested data and/or control of access to requested data.

Abstract: The application is directed to an electronic that includes multiple motion sensors, such as passive infrared sensors, that the electronic device uses to detect characteristics of objects. For instance, the motion sensors may be substantially vertically aligned and/or substantially horizontally aligned with one another, where each motion sensor is positioned at a respective angle with respect to a ground plane. When the motion sensors detect an object, the electronic device can then determine a direction at which the object is moving and/or a speed at which the object is moving. In some instances, the direction may include towards the electronic device or away from the electronic device. Additionally, based on the characteristics of the object, the electronic device may perform an action, such as generating image data using a camera and/or sending a user alert.

Abstract: A method and system for establishing two-way trust between a short-range communication device and a hub device. The method includes: obtaining, from a hub device, a digitally signed request for determining whether the hub device is a trusted communication device for a short-range communication device and a cryptographic key generated by the short-range communication device; generating a response to the request; encrypting the response to the request by using the cryptographic key provided by the short-range communication device, so that the encrypted response can be decrypted only by the short-range communication device; and providing the encrypted response to the hub device. The short-range communication device may decrypt the response and determine whether the hub device is the trusted communication device based on information indicated in the response.

Abstract: Techniques are disclosed for setting a breakpoint for debugging a neural network. User input is received by a debugger program executable by a host processor indicating a target layer of a neural network at which to halt execution of the neural network. The neural network includes a first set of instructions to be executed by a first execution engine and a second set of instructions to be executed by a second execution engine. A first halt point is set within the first set of instructions and a second halt point is set within the second set of instructions. It is then determined that operation of the first execution engine and the second execution engine has halted. It is then determined that the first execution engine has reached the first halt point. The second execution engine is then caused to move through instructions until reaching the second halt point.

Abstract: A network device can include packet processing circuitry to provide support for virtual functions. The packet processing circuitry can perform operations such as receiving data traffic from a virtual machine, determining an egress rule for the data traffic based on a rule table, and encapsulating the data traffic according to the egress rule.

Abstract: A trained model and/or an edge client running on an edge device may obtain data from a data source (e.g., a security video camera) and determine, based on a result of processing the data using the model, whether to send an indication of an upcoming data/video stream to the provider network (e.g., indicating a bearer modification). The received indication may be used by the provider network to send a request to a serving wireless infrastructure (e.g., telco operator/wireless mobile core) for configuration of one or more resources on behalf of the edge device to process the upcoming data stream. The received indication may be used by the provider network in order to configure one or more resources at the provider network to process the upcoming data stream. The edge device initiates transmission of the data stream from the data source to the provider network via the serving wireless infrastructure.

Abstract: Systems and methods for automatically adjusting the exposure settings (e.g., exposure time, analog gain, etc.) of imaging device(s) and/or camera(s) utilized in machine vision systems. According to embodiments of the present disclosure, one or more images or frames of a stream of images captured by an imaging device of a machine vision system can be processed and analyzed to determine exposure settings that may be applied to capture subsequent images by the imaging device. For example, a frame of the stream of images can be partitioned into a plurality of zones, and the pixels of each zone can be non-uniformly sorted into a histogram to represent the distribution of pixels in each zone.