Abstract: Systems and methods are provided for interactively highlighting a region as pixel data on a screen and automatically retrieving context data associated with content of the highlighted region for contextual notetaking. The highlighted region includes at least a part of one or more windows and one or more applications associated with the one or more windows. The disclosed technology determines a context associated with content of the highlighted region and automatically retrieves context data that are contextually relevant to the content. Notes data are generated based on an aggregate of the highlighted content, window-specific context data, application-specific context data, and user-specific context data. A notetaking application retrieves stored the notes data from a notes database and displays the notes data for recall and for use. The contextual notetaking enables the user reducing a burden of performing manual operations for notetaking and utilizing notes that are enriched relevant data by context.

Abstract: A transformer-based neural network includes at least one mask attention network (MAN). The MAN computes an original attention data structure that expresses influence between pairs of data items in a sequence of data items. The MAN then modifies the original data structure by mask values in a mask data structure, to produce a modified attention data structure. Compared to the original attention data structure, the modified attention data structure better accounts for the influence of neighboring data items in the sequence of data items, given a particular data item under consideration. The mask data structure used by the MAN can have static and/or machine-trained mask values. In one implementation, the transformer-based neural network includes at least one MAN in combination with at least one other attention network that does not use a mask data structure, and at least one feed-forward neural network.

Abstract: Technologies for measuring and controlling live video latency are disclosed. Embodiments capture a live video scene, ingest the live video scene into a live video stream, and encode the live video stream with data that can be used to compute latency measurements. Embodiments communicate the live video stream to a content distribution network. The live video stream is distributed, directly or indirectly by the content distribution network, to one or more user systems. The one or more user systems present the live video stream to one or more users. Embodiments determine a latency of the live video stream based on, for example, a measurement that is obtained during the capturing of the live video stream and another measurement that is obtained during or in response to the presenting of the live video stream to the one or more users.

Abstract: Innovations in intra block copy (“BC”) prediction mode facilitate intra BC prediction that is more effective in terms of rate-distortion performance and/or computational efficiency of encoding and decoding. For example, some of the innovations provide ways to select block vector (“BV”) values more effectively. Other innovations provide ways to encode/decode BV values more efficiently. Still other innovations address how to perform in-loop deblock filtering when a block has intra BC prediction mode, or address how to perform intra BC prediction when constrained intra prediction is enabled.

Abstract: Methods, systems, apparatuses, and computer-readable storage mediums described herein are configured to detect anomalous post-authentication behavior/state change(s) with respect to a workload identity. For example, audit logs that specify actions performed with respect to the workload identity of a platform-based identity service, a causing state change(s), while another identity is authenticated with the platform-based identity service, are analyzed. The audit log(s) are analyzed via a model for anomaly prediction based on actions. The model generates an anomaly score indicating a probability whether a particular sequence of the actions is indicative of anomalous behavior/state change(s). A determination is made that an anomalous behavior has occurred based on the anomaly score, and when anomalous behavior has occurred, a mitigation action may be performed that mitigates the anomalous behavior.

Abstract: Disclosed herein are exemplary embodiments of methods, apparatus, and systems for performing content-adaptive deblocking to improve the visual quality of video images compressed using block-based motion-predictive video coding. For instance, in certain embodiments of the disclosed technology, edge information is obtained using global orientation energy edge detection (“OEED”) techniques on an initially deblocked image. OEED detection can provide a robust partition of local directional features (“LDFs”). For a local directional feature detected in the partition, a directional deblocking filter having an orientation corresponding to the orientation of the LDF can be used. The selected filter can have a filter orientation and activation thresholds that better preserve image details while reducing blocking artifacts. In certain embodiments, for a consecutive non-LDF region, extra smoothing can be imposed to suppress the visually severe blocking artifacts.

Abstract: A fabric control protocol is described for use within a data center in which a switch fabric provides full mesh interconnectivity such that any of the servers may communicate packet data for a given packet flow to any other of the servers using any of a number of parallel data paths within the data center switch fabric. The fabric control protocol enables spraying of individual packets for a given packet flow across some or all of the multiple parallel data paths in the data center switch fabric and, optionally, reordering of the packets for delivery to the destination. The fabric control protocol may provide end-to-end bandwidth scaling and flow fairness within a single tunnel based on endpoint-controlled requests and grants for flows. In some examples, the fabric control protocol packet structure is carried over an underlying protocol, such as the User Datagram Protocol (UDP).

Abstract: Techniques for generating a fused enhanced image. A first image is generated using a first camera of a first modality, and a second image is generated using a second camera of a second modality. Pixels that are common between the two images are identified. Textures for the common pixels are determined. A camera characteristic, which is linked to noise, is identified. A scaling factor is applied to the textures in the first image. A first saliency is determined using the scaled textures. A second saliency is determined using the textures from the second image. An alpha map is generated and reflects edge detection weights that have been computed for each one of the common pixels based on the two saliencies. Based on the alpha map, textures are merged from the common pixels to generate the fused enhanced image.

Abstract: Redundancy information can be included in nucleotide symbol strings encoding underlying data. To avoid propagation of errors during the decoding process, during encoding, a constrained encoding can be performed before the redundancy information is computed. The redundancy information can be an outer encoding across multiple nucleotide symbol strings. An inner coding within nucleotide symbol strings can also be supported. Such redundancy information can be interleaved into the underlying nucleotide symbol strings to which the constrained encoding has been applied, resulting in a relaxed constraint. Insertion/deletion redundancy information can also be included in the resulting strings, and an insertion/deletion-sensitive sequence can be included to assist in recovering accurate sequences during decoding operations.

Abstract: Implementations of the subject matter described herein provide a solution for rate control based on reinforcement learning. In this solution, an encoding state of a video encoder is determined, the encoding state being associated with encoding of a first video unit by the video encoder. An encoding parameter associated with rate control in the video encoder is determined by a reinforcement learning model and based on the encoding state of the video encoder. A second video unit different from the first video unit is encoded based on the encoding parameter. In this way, it is possible to achieve a better quality of experience (QOE) for real time communication with computation overhead being reduced.

Abstract: A computer implemented method includes rendering a document page as an image; detecting tables, columns, and other associated table objects within the image via one or more table recognition models that model objects in the image as overlapping bounding boxes; transforming the set of objects into a structured representation of the table; extracting data from the objects into the structured representation; and exporting the table into the desired output format.

Abstract: Methods, systems, apparatuses, and computer program products are provided herein for rendering secured content. For instance, a computing device may be utilized to view content that is to be displayed via a display device coupled thereto. However, rather than rendering the content, the computing device generates and/or provides a graphical representation of the content to a rendering device coupled between the computing device and the display device. The rendering device analyzes the graphical representation to determine characteristics of the graphical representation, characteristics of a display region of an application window in which the content is to be rendered, and a network address at which the actual content is located. The rendering device retrieves the content using the network address and renders the retrieved content over the display region of the application window in accordance with the characteristics determined for the graphical representation and the display region of the application window.

Abstract: A method, computer program product, and computing system for processing audio information associated with a speech processing system and encoding a watermark in a non-disruptive portion of the audio information.

Abstract: The present disclosure relates to methods and systems for monitoring release pipelines. The methods and systems calculate health metrics of release pipelines using telemetry data from the release pipelines. The methods and systems determine whether the release pipelines are healthy based on the health metrics. The methods and systems automatically trigger one or more actions in response to determining that the release pipelines are unhealthy and continue to monitor the release pipelines in response to determining that the release pipelines are healthy.

Abstract: Permitting a claims holder to get a limited verifiable credential leveraging off of a previously-issued verifiable credential. This is done by having the limited verifiable credential include only a selected subset of the verifiable claims present within the previously-issued verifiable credential. The limited verifiable credential may then be exposed to a relying entity computing system so that the relying entity computing system can verify any of the selected subset of verifiable claims, but not verifiable claims that are outside of the selected subset of verifiable claims.

Abstract: Methods, systems, apparatuses, and computer-readable storage mediums described herein are directed to determining and recommending an optimal compute resource configuration for a cloud-based resource (e.g., a server, a virtual machine, etc.) for migrating a customer to the cloud. The embodiments described herein utilize a statistically robust approach that makes recommendations that are more flexible (elastic) and account for the full distribution of the amount of resource usage. Such an approach is utilized to develop a personalized rank of relevant recommendations to a customer. To determine which compute resource configuration to recommend to the customer, the customer's usage profile is matched to a set of customers that have already migrated to the cloud. The compute resource configuration that reaches the performance most similar to the performance of the configurations utilized by customers in the matched set is recommended to the user.

Abstract: A resilient incident management system is provided that continues operation when certain outages occur. An RSS feed is utilized to indicate incident-related information despite the certain outages. In an embodiment, the incident management system includes a redundant architecture that comprises a traffic manager and a backup traffic manager. The incident management system receives a client request for incident-related information and determines a priority level or a performance level of end points associated with the request. Based on a status of the traffic manager and the backup traffic manager, as well as based on the priority level or the performance level, the incident management system causes a computer operation to be executed via the redundant architecture to retrieve a response from a producer and generate the RSS feed.

Abstract: Embodiments of the present disclosure include techniques for encoding and decoding metadata in error correction codes. During read operation, a decoder generates a first output corresponding to the at least one metadata bit having a first state and a second output corresponding to the at least one metadata bit having a second state. When one of the first and second outputs have a zero value, the decoder sets a value of the at least one metadata bit to the first state or the second state corresponding to the first output or the second output having the zero value. When both the first and second outputs are non-zero, the decoder decodes the codeword with the assumption of both the metadata bit having the first state and the second state to determine if the codeword is correctable with the at least one metadata bit.

Abstract: Methods for detecting and mitigating abusive network activity based on versioned browser usage are performed by systems and devices. Usage values for network activity of legacy web browser versions are determined, where the usage values represent benign network activity associated with active instances of the legacy versions over prior time periods. The number of active instances of legacy browser versions is assumed to generally be monotonically decreasing over time, and thus a bound of benign network activity for each of the legacy versions can be estimated by associating an approximate percentage of benign traffic with a minimum past usage value. Current network activity is monitored to determine current usage values for the legacy versions, and network actions are performed based on current usage values deviating from past usage values according to the bound.

Abstract: A computing device executing software displays a view of a search assignment in a user interface to a learning platform. The device receives user input comprising search terms associated with the search assignment, and generates queries based on the user input. The device submits the queries to a search engine, whereupon the search engine performs searches based on the queries, and the device displays the results. As a user evaluates resources provided in the results, the device updates the user interface to include an option selectable for adding evaluated ones of the resources to a collection of resources for the search assignment. In response to the user selecting the option with respect to a resource of the evaluated ones of the resources, the device adds the resource to the collection of resources.