Abstract: As disclosed herein, a computer-implemented method for detecting avatar impersonation is provided. The computer-implemented method may include generating, from a first type of image data associated with a first user, a digital representation of the first user. The computer-implemented method may include generating, from a second type of image data associated with a second user, a digital representation of the second user. The computer-implemented method may include determining a similarity score associated with a degree of correspondence between the digital representations. The computer-implemented method may include determining, based on the similarity score, whether an identity of the first user matches an identity of the second user. The computer-implemented method may include allowing, based on determining the identity of the first user matches an identity of the second user, an access to an asset associated with the first user.

Abstract: The present disclosure provides systems and methods for allocating processing resources based on an online presence score. In various examples, systems and methods may receive user interaction data associated with a platform for a predetermined period of time. In response to receiving user interaction data, an online presence score associated with a user may be determined. A plurality of advertisements may be ranked, where allocation of processing resources may be based on the online presence score in relation to a plurality of intervals. Online presence scores associated with a first interval may trigger more processing resources to be allocated for ranking advertisements. Conversely, online presence scores associated with a second interval may trigger less processing resources to be allocated for ranking advertisements.

Abstract: Systems and methods to generate stylized content are provided. The system may select a first video including frames including a dynamic style of motion associated with content of the frames. The system may further analyze images associated with a first scene. The system may further apply the motion associated with the content of the frames of the first video to the analyzed images to generate a second scene including motion of media content associated with the images. The motion may provide a movement pattern to the media content during different viewpoints at respective timesteps of the second scene.

Abstract: An embodiment includes encoding a first 32-bit floating point depth value, in a plurality of 32-bit floating point depth values, into a first signed 8-bit integer and a second signed 8-bit integer. An embodiment includes predicting, using a trained convolutional neural network (CNN), the first signed 8-bit integer, and the second signed 8-bit integer, a plurality of depth layer maps and a probability map. An embodiment includes generating, by selecting pixels from the plurality of depth layer maps according to the probability map, a depth map of a scene.

Abstract: The subject application is at least directed to methods and systems for employing a semi-supervised machine learning model to generate a subject audio quality score for audio obtained via real-time applications. Additionally, various systems, methods, or devices are also described for facilitating communication between one or more nodes in distributed training or inference. In some examples, the method may include sending, by a first node of a plurality of nodes, a message, where the message includes, information associated with the first node of the plurality of nodes. Also, the method may include receiving, from one or more nodes of the plurality of nodes, one or more response messages to the message. Furthermore, the method may include sending, by the first node of the plurality of nodes, data associated with computations at the first node.

Abstract: A holographic calling system can capture and encode holographic data at a sender-side of a holographic calling pipeline and decode and present the holographic data as a 3D representation of a sender at a receiver-side of the holographic calling pipeline. The holographic calling pipeline can include stages to capture audio, color images, and depth images; densify the depth images to have a depth value for each pixel while generating parts masks and a body model; use the masks to segment the images into parts needed for hologram generation; convert depth images into a 3D mesh; paint the 3D mesh with color data; perform torso disocclusion; perform face reconstruction; and perform audio synchronization. In various implementations, different of these stages can be performed sender-side or receiver side. The holographic calling pipeline also includes sender-side compression, transmission over a communication channel, and receiver-side decompression and hologram output.

Abstract: One embodiment of the present invention sets forth a technique for combining a color image and a monochrome image. The technique includes inputting a first set of pixel values from the color image and a second set of pixel values from the monochrome image into a neural network. The technique also includes applying, via a first set of neural network layers, one or more downsampling operations and one or more upsampling operations to feature maps associated with the inputted pixel values to generate a first output image that includes a first set of color values for a first set of pixel locations in the monochrome image. The technique further includes applying a second set of neural network layers to the first set of color values to generate a second output image that includes a second set of color values that is larger than the first set of color values.

Abstract: Various systems, methods, and devices are described for utilizing artificial intelligence (AI) bot (e.g., a chatbot) to fetch or create content associated with a third-party platform based on an input associated with an electronic device. In an example, systems and methods of AI bot fetching or creating content may include receiving an input, via a user device. The input may be textual, audible, or any other suitable method. Based on the input, one or more content items may be fetched or created. The machine learning model may be utilized to determine context associated with the input. The machine leaning model may determine a number of content items associated with the input and data sources related to the retrieval generators. A result may be presented to a user, where the result may comprise the one or more content items determined.

Abstract: In one embodiment, a method includes accessing a video captured by cameras which is associated with a first framerate lower than a threshold framerate, for any two adjacent frames of the accessed video: generating a warped frame from the two adjacent frames based on an optical flow associated with the two adjacent frames, determining alignments for the two adjacent frames, respectively, fusing the determined alignments for the two adjacent frames, and generating a reconstructed frame based on the fused alignment, and reconstructing the accessed video based on the any two adjacent frames and their respective reconstructed frames, wherein the reconstructed video is associated with a second framerate higher than the threshold framerate.

Abstract: A computer-implemented method includes parsing, by a processor set, text comprised by an alert corresponding to an information technology (IT) abnormality incident, resulting in alert data. The processor set uses a generative machine learning (ML) model to generate a natural language summary of the incident. The natural language summary includes a symptom-resource pairing corresponding to the alert and is based on the alert data and on a topology of keywords comprised by the alert. In one or more embodiments, the computer-implemented method further comprises employing, by the processor set, graph connectivity distances between elements of the topology to verify the symptom-resource pairing.

Abstract: A method for managing a plurality of wireless devices. The method includes obtaining a plurality of base Machine Learning (ML) models, wherein each base ML model is operable to provide an output on the basis of which at least one RAN operation performed by a wireless device may be configured. The method further includes transmitting characterising information for individual models of the plurality of base ML models and configuration information for the plurality of base ML models over the RAN. The method further includes receiving an indication of which one or more of the plurality of base ML models the wireless device will be using as an ensemble ML model in connection with a RAN operation performed by the wireless device, and setting a value of at least one configuration parameter associated with the RAN operation performed by the wireless device based on the received indication.

Abstract: A method for generating an output depth map is provided. The method is performed by a computing device. When the computing device executes this method, it receives input image data of a scene, and receives an input depth map of the scene, the input depth map having an input resolution. Using a machine-learning model, the device generates multiple kernels for upsampling the input depth map to produce an output depth map with a higher resolution than the one of the input depth map. These kernels are generated based on the input image data and the input depth map, with each kernel consisting of multiple weights. Subsequently, the computing device applies these kernels to the input depth map to generate the output depth map. Each kernel is applied to a portion of the input depth map to generate a depth value for a pixel of the output depth map.

Abstract: A device may generate, based on a first input frame and a second input frame of an input video, a first feature map and a second feature map. The device may generate a forward optical flow map and a backward optical flow map based on the first feature map and the second feature map. The device may generate an error estimate for the interpolated frame using the forward optical flow map and backward optical flow map. The device may select, based on a comparison of the error estimate and one or more criteria, an interpolation module from a plurality of interpolation modules. The device may generate the interpolated frame using the selected interpolation module. The device may combine the interpolated frame with the two input frames to generate at least a part of an output video.

Abstract: The subject disclosure provides for systems and methods for generating a dense depth map. The method may include determining a first region of interest via input from a first sensor device configured to capture supplemental pixel images. The method may include determining a second region of interest via input from a second sensor device configured to capture supplemental pixel images. The method may include receiving depth measurements from a third sensor device configured to capture depth measurements. The method may include determining a plurality of depth maps from the pixel images from the first sensor device, the supplemental pixel images from the second sensor device, and the depth measurements from the third sensor device. The method may include generating from the plurality of depth maps a foveated region comprising a high-resolution image and a low-resolution image oriented on the periphery of the foveated region.

Abstract: A method for signal processing includes receiving a definition associated with a task, and based on the definition, selecting a first sensor modality having a first operational cost from multiple sensor modalities each associated with respective operational costs. The method further includes capturing a first sensor signal using the first sensor modality, and making a first determination that the first sensor signal is not sufficient to perform the task. The method further includes selecting, from the sensor modalities, a second sensor modality having a second operational cost, the second operational cost being higher than the first operational cost and capturing a second sensor signal using the second sensor modality. The method further includes making a second determination that the second sensor signal may be used to perform the task and using the second sensor signal to perform the task.

Abstract: In one embodiment, a method by a computing system associated with an image sensor including a quad-Bayer color filter array includes accessing image-sensor data generated by the image sensor, where the quad-Bayer color filter array comprises sixteen sets of filters, each corresponding to a pixel location within a quad-Bayer pattern, splitting the image-sensor data into sixteen packed channels, where each of the sixteen packed channels corresponds to one of the sixteen sets of filters, producing three channels of interpolated pixels by processing the sixteen packed channels using a machine-learning model, where the three channels comprise red, green, and blue channels, and constructing an output image using the three channels of the interpolated pixels.

Abstract: A display device includes a diffusion layer providing a single well, an optical element configured to receive light and output the received image light including a concentric series of lens segments made up of active facets, and a waveguide having an in-coupling grating and a waveguide body optically coupled to the image light, where a polarizing component is disposed over an output surface of the optical element. A method to improve a yield of silicon backplane displays includes connecting a diode having a resolution to a backplane and repairing a defect on a pixel display area by dividing the pixel display area into at least one subcircuit, while improving geometry stylization transfer for 3D models of real-world environments. A method for suppressing crosstalk for user conversations includes receiving multiple speech signals captured by multiple microphones and generating directional data for the multiple speech signals based on spatial filtering.

Abstract: A holographic calling system can capture and encode holographic data at a sender-side of a holographic calling pipeline and decode and present the holographic data as a 3D representation of a sender at a receiver-side of the holographic calling pipeline. The holographic calling pipeline can include stages to capture audio, color images, and depth images; densify the depth images to have a depth value for each pixel while generating parts masks and a body model; use the masks to segment the images into parts needed for hologram generation; convert depth images into a 3D mesh; paint the 3D mesh with color data; perform torso disocclusion; perform face reconstruction; and perform audio synchronization. In various implementations, different of these stages can be performed sender-side or receiver side. The holographic calling pipeline also includes sender-side compression, transmission over a communication channel, and receiver-side decompression and hologram output.

Abstract: A method, a user equipment, UE, a network node, and a computer program product for classifying channel state information, CSI, compression quality in a wireless communication network are provided. The method is performed in a UE in the wireless communication network. The method includes obtaining CSI associated with one or more radio channels. Further, the method includes compressing the CSI into an encoded format representing a compressed CSI. The method further includes classifying a CSI compression quality related to reconstruction of the one or more radio channels of the compressed CSI using a classifier predicting a resulting performance loss associated with the reconstruction of the one or more radio channels. The classification of the CSI compression quality is based on a level of predicted performance loss.

Abstract: Embodiments include methods for a radio access network (RAN) node configured to serve one or more user equipment (UEs). Such methods include transmitting reference signals (RS) for a downlink (DL) channel and receiving, from a UE, a report including encoded feedback representing the DL channel. The encoded feedback comprises a UE DL channel estimate mapped to a channel feature set based on a first mapping that is proprietary to the UE. The channel feature set is compressed based on a second mapping that is known by the UE and the RAN node. Such methods also include, using a decoder function of a neural-network autoencoder (NNAE), decoding the encoded feedback to obtain a reconstruction of the channel feature set. Other embodiments include complementary methods for a UE, as well as RAN nodes and UEs configured to perform such methods.