Abstract: In response to detection that a capacity of the fronthaul link has been or will be exceeded, a software intelligence layer operating on a transport layer router that aggregates network traffic from the one or more radio units (RUs) causes a change in how in-phase and quadrature (IQ) data packets sent on the fronthaul link are handled to reduce use of the capacity of the fronthaul link. In another example embodiment, a software intelligence layer operating at an application layer of the wireless telecommunication network may perform one or more actions utilizing access to scheduler level information for the distributed units (DUs) to avoid the fronthaul link exceeding the capacity limit based on incoming IQ samples to a router that aggregates network traffic from one or more corresponding RUs.

Abstract: In response to detection that a capacity of the fronthaul link has been or will be exceeded, a software intelligence layer operating on a transport layer router that aggregates network traffic from the one or more radio units (RUs) causes a change in how in-phase and quadrature (IQ) data packets sent on the fronthaul link are handled to reduce use of the capacity of the fronthaul link. In another example embodiment, a software intelligence layer operating at an application layer of the wireless telecommunication network may perform one or more actions utilizing access to scheduler level information for the distributed units (DUs) to avoid the fronthaul link exceeding the capacity limit based on incoming IQ samples to a router that aggregates network traffic from one or more corresponding RUs.

Abstract: In some embodiments, techniques for producing user-generated content are provided. For example, a process may involve sending a product identifier; receiving a first candidate image that is associated with the product identifier; determining that a similarity between a user structure and a target structure satisfies a threshold condition, wherein the user structure characterizes a figure of a user in a first input image and the target structure is based on a pose guide associated with the first candidate image; and capturing, based on the determining, the first input image.

Abstract: Systems and methods are described for automated detection of border conflicts in physical radiofrequency (RF) communication network infrastructures. For example, proposed sector antennas in a greenfield physical network deployment may be licensed to radiate in certain spectrum blocks in the mapped licensed geographic regions (mLGR) where they are located, but the licenses may not permit radiated power in those spectrum blocks to cross into adjacent mLGRs. Embodiments compute radiation contours for the sector antennas indicating estimated local power levels computed based on antenna characteristics of the sector antennas and propagation model data that defines geographic morphologies for the mLGRs. The radiation contours are analyzed to detect any border conflict conditions where the estimated local power levels exceed defined threshold radiation levels in unlicensed regions. A culprit set of the sector antennas can be output to indicate those responsible for detected border conflict conditions.

Abstract: Techniques are provided herein for retrieving images that correspond to a target subject matter within a target context. Although useful in a number of applications, the techniques provided herein are particularly useful in contextual product association and visualization. A method is provided to apply product images to a neural network. The neural network is configured to classify the products in the images. The images are associated with a context representing the combination of classified products in the images. These techniques leverage both seller-provided images of products and user-generated content, which potentially includes hundreds or thousands of images of the same or similar products as the seller-provided images. A graphical user interface is configured to permit a user to select the context of interest in which to visualize the products.

Abstract: The present disclosure is directed to methods and systems for tuning a wireless network propagation model. A propagation model system can generate a nominal propagation model of a coverage area using collected geographical data and network equipment information. The nominal propagation model can provide a representation of the wireless network and coverage areas. The propagation model system can continuously calibrate the generated propagation models with continuous wave data and crowdsourced data from user devices. The crowdsourced data can provide a real-time representation of the coverage capability in an area as the terrain and clutter in an area can change.

Abstract: Techniques are disclosed for identifying and presenting video content that demonstrates features of a target product. The video content can be accessed, for example, from a media database of user-generated videos that demonstrate one or more features of the target product so that a user can see and hear the product in operation via a product webpage before making a purchasing decision. The product functioning videos supplement any static images of the target product and the textual product description to provide the user with additional context for each of the product's features, depending on the textual product description. The user can quickly and easily interact with the product webpage to access and playback the product functioning video to see and/or hear the product in operation.

Abstract: Review videos on product pages are enhanced with user interface elements that cause playback of the review videos at points at which particular topics are discussed. A review video is processed by converting speech to text and timestamping the text. Topics are identified in the text, and a time in the review video corresponding to each topic is identified from the timestamps for the text. In some configurations, sentiment is also determined for each topic. User interface elements corresponding to each identified topic are presented with the review video on the product page. When a user viewing the product page selects a user interface element, the review video is played at a time corresponding to the topic of the selected user interface element.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for removing objects from an image stream at capture time of a digital image. For example, the disclosed system contemporaneously detects and segments objects from a digital image stream being previewed in a camera viewfinder graphical user interface of a client device. The disclosed system removes selected objects from the image stream and fills a hole left by the removed object with a content aware fill. Moreover, the disclosed system displays the image stream with the removed object and content fill as the image stream is previewed by a user prior to capturing a digital image from the image stream.

Abstract: Methods and apparatuses for improving telecommunications services by intelligently deploying radio access network components and redundant links within a data center hierarchy to satisfy latency, power, availability, and quality of service requirements for one or more network slices are described. The radio access network components may include virtualized distributed units (VDUs) and virtualized centralized units (VCUs). To satisfy a latency requirement for a network slice, various components of a radio access network may need to be redeployed closer to user equipment. To satisfy a power requirement for the network slice, various components of the radio access network may need to be redeployed closer to core network components. Over time, the components of the radio access network may be dynamically reassigned to different layers within a data center hierarchy in order to satisfy changing latency requirements and power requirements for the network slice.

Abstract: Example embodiments are directed towards detecting a failure of a fifth-generation New Radio (5G NR) cellular telecommunication network containerized network function (CNF) running within a dedicated node group of cloud compute instances hosting a plurality of CNFs of a wireless telecommunication service provider or a failure of a specific cloud compute instance hosting the CNF within the node group. In response to the detection of a failure of the CNF within the node group or a failure of the specific cloud compute instance hosting the CNF within the node group, automatically switching to host the CNF on a spare cloud compute instance within the node group dedicated to the wireless telecommunication service provider and pre-provisioned to host CNFs of a same type as the CNF for the wireless telecommunication service provider.

Abstract: Example embodiments are directed towards detecting a failure of one or more of a CU-UP pod and a CU-CP pod running on a first cloud compute instance within a node group of a cluster being hosted on a first cloud compute instance. In response to the detection of a failure of one or more of a CU-UP pod or a CU-CP pod of a node group within a cluster being hosted on a first cloud compute instance, the system automatically switches from the one or more pods for which failure was detected to one or more standby pods running a second cloud compute instance with user equipment (UE) context corresponding to the one or more pods for which failure was detected.

Abstract: Methods and apparatuses for improving telecommunications services by intelligently deploying radio access network components and redundant links within a data center hierarchy to satisfy latency, power, availability, and quality of service requirements for one or more network slices are described. The radio access network components may include virtualized distributed units (VDUs) and virtualized centralized units (VCUs). To satisfy a latency requirement for a network slice, various components of a radio access network may need to be redeployed closer to user equipment. To satisfy a power requirement for the network slice, various components of the radio access network may need to be redeployed closer to core network components. Over time, the components of the radio access network may be dynamically reassigned to different layers within a data center hierarchy in order to satisfy changing latency requirements and power requirements for the network slice.

Abstract: Methods and apparatuses for improving telecommunications services by intelligently deploying radio access network components and redundant links within a data center hierarchy to satisfy latency, power, availability, and quality of service requirements for one or more network slices are described. The radio access network components may include virtualized distributed units (VDUs) and virtualized centralized units (VCUs). To satisfy a latency requirement for a network slice, various components of a radio access network may need to be redeployed closer to user equipment. To satisfy a power requirement for the network slice, various components of the radio access network may need to be redeployed closer to core network components. Over time, the components of the radio access network may be dynamically reassigned to different layers within a data center hierarchy in order to satisfy changing latency requirements and power requirements for the network slice.

Abstract: Example embodiments are directed towards detecting a failure of one or more microservices of a CU-UP pod or a CU-CP pod running on a first cloud compute instance within a node group of a cluster. In response to the detection of a failure of one or more microservices of a CU-UP pod or a CU-CP pod of a node group within a cluster being hosted on a first cloud compute instance, the system automatically switches to run the one or more microservices for which failure was detected on a standby pod running on a second cloud compute instance with user equipment (UE) context corresponding to the one or more microservices for which failure was detected. The standby pods running on the other cloud compute instance are generated with anti-affinity between the CU-CP microservices of the primary CNF instance and CU-CP microservices of the standby pod.

Abstract: An image generation system generates images of objects under different lighting conditions. An image of an object and lighting conditions for an output image are received. The lighting conditions may specify, for instance, a location and/or color of one or more light sources. The image of the object is decomposed into a shading component and a reflectance component. A machine learning model takes the reflectance component and specified lighting conditions as input, and generates an output image of the object under the specified lighting conditions.

Abstract: Methods, systems, and non-transitory computer readable media are disclosed for determining a sub-set of user-submitted images that are similar to a curated image and presenting the sub-set of user-submitted images in connection with the curated image. The disclosed system presents a curated image depicting a product via a graphical user interface (e.g., on an e-commerce platform). In one or more embodiments, the disclosed system extracts feature vectors from the curated image and a plurality of user-submitted images. The disclosed system compares the feature vectors from the curated image and the plurality of user-submitted images to determine a sub-set of user-submitted images that are similar to the curated image. The disclosed system presents the sub-set of user-submitted images based on a user selection of the curated image.

Abstract: Systems and methods are described for automated detection of border conflicts in physical radiofrequency (RF) communication network infrastructures. For example, proposed sector antennas in a greenfield physical network deployment may be licensed to radiate in certain spectrum blocks in the mapped licensed geographic regions (mLGR) where they are located, but the licenses may not permit radiated power in those spectrum blocks to cross into adjacent mLGRs. Embodiments compute radiation contours for the sector antennas indicating estimated local power levels computed based on antenna characteristics of the sector antennas and propagation model data that defines geographic morphologies for the mLGRs. The radiation contours are analyzed to detect any border conflict conditions where the estimated local power levels exceed defined threshold radiation levels in unlicensed regions. A culprit set of the sector antennas can be output to indicate those responsible for detected border conflict conditions.

Abstract: Systems and methods are described for automated sector creation in greenfield physical radiofrequency (RF) communication network infrastructures. For example, a network operator is granted licenses to use multiple spectrum blocks in multiple geographic regions for which the network operator does not currently have physical infrastructure. An RF network design defines a number of template antennas located at template site locations to meet a link budget over a target coverage area. For each template site location, embodiments can automatically compute sectors based on the associated template antennas and local spectrum licensing information. The computed sectors can effectively define a physical network deployment, including locations and configurations for sector antennas, by which the network operator can provide a desired quality of coverage to subscribers in the target coverage area.

Abstract: Described herein is a system and techniques for classification of subjects within image information. In some embodiments, a set of subjects may be identified within image data obtained at two different points in time. For each of the subjects in the set of subjects, facial landmark relationships may be assessed at the two different points in time to determine a difference in facial expression. That difference may be compared to a threshold value. Additionally, contours of each of the subjects in the set of subjects may be assessed at the two different points in time to determine a difference in body position. That difference may be compared to a different threshold value. Each of the subjects in the set of subjects may then be classified based on the comparison between the differences and the threshold values.