Abstract: A computer-implemented method of changing a face within an output image or video frame that includes: receiving an input image that includes a face presenting a facial expression in a pose; processing the image with a neural network encoder to generate a latent space point that is an encoded representation of the image; decoding the latent space point to generate an initial output image in accordance with a desired facial identity but with the facial expression and pose of the face in the input image; identifying a feature of the facial expression in the initial output image to edit; applying an adjustment vector to a latent space point corresponding to the initial output image to generate an adjusted latent space point; and decoding the adjusted latent space point to generate an adjusted output image in accordance with the desired facial identity but with the facial expression and pose of the face in the input image altered in accordance with the adjustment vector

Abstract: Certain aspects of the present disclosure provide techniques for automated updates to code deployment pipelines. This includes identifying a proposed change to a plurality of source code repositories based on parsing a change template. It further includes determining one or more changes to one or more files in each respective source code repository, of the plurality of source code repositories, based on the proposed change. It further includes changing the one or more files in each respective source code repository, based on the determined one or more changes, and building a project in each respective source code repository using the changed one or more files.

Abstract: In some implementations, a controller may cause a robotic arm connector, of the robotic arm, to be connected to a first compartment connector of a passenger compartment of an amusement ride. The controller may cause a second compartment connector, of the passenger compartment, to be disconnected from a first structure connector of a first support structure. The controller may transport the passenger compartment from the first support structure to a second support structure after causing the second compartment connector to be disconnected from the first structure connector.

Abstract: A system includes a machine learning (ML) model-based video downsampler configured to receive an input video sequence having a first display resolution, and to map the input video sequence to a lower resolution video sequence having a second display resolution lower than the first display resolution. The system also includes a neural network-based (NN-based) proxy video codec configured to transform the lower resolution video sequence into a decoded proxy bitstream. In addition, the system includes an upsampler configured to produce an output video sequence using the decoded proxy bitstream.

Abstract: This disclosure presents systems and methods to facilitate interaction by one or more participants with content presented across multiple distinct physical locations. A current distinct physical location of a participant may be determined. In response to determining the current distinct physical location in which the participant is located, operation of one or more content devices physically present in the current distinct physical location may be effectuated.

Abstract: A system includes a computing platform including processing hardware and a memory storing software code, a trained machine learning (ML) model, and a content thumbnail generator. The processing hardware executes the software code to receive interaction data describing interactions by a user with content thumbnails, identify, using the interaction data, an affinity by the user for at least one content thumbnail feature, and determine, using the interaction data, a predetermined business rule, or both, content for promotion to the user. The software code further provides a prediction, using the trained ML model and based on the affinity by the user, of the desirability of each of multiple candidate thumbnails for the content to the user, generates, using the content thumbnail generator and based on the prediction, a thumbnail having features of one or more of the candidate thumbnails, and displays the thumbnail to promote the content to the user.

Abstract: A system includes a hardware processor that executes a software code to receive an authorization request on behalf of a user for a stacked resource including resources offered separately by multiple resource providers, determine resource provider computers associated with the stacked resource, and send a look-up request including an electronic identity of the user to those computers, where the electronic identity is used as a look-up key for determining user attribute(s) of the user. The software code further receives the user attribute(s) from the resource provider computers, generates an accumulated access profile of the user based on the user attribute(s), applies the profile to a rules engine to determine a stacked access result, and routes the authorization request and the stacked access result to one of the resource provider computers, where that computer completes an authorization process for access to the stacked resource based on the stacked access result.

Abstract: There is provided a wireless portable device for providing location-based data to a user in a defined geographical area including a plurality of points of interest, the wireless portable device comprising a wireless transmitter, a wireless receiver, and a display. The wireless transmitter can transmit location information to a wireless server over a wireless network. The wireless receiver can receive location-based data relating to a point of interest from the wireless server periodically and automatically, based on the location of the wireless portable device. By optimizing map routes and schedules using the location-based data and user preferences including wish lists, the wireless portable device can provide helpful recommendations via the display, enabling the user to plan an efficient schedule of activities in the defined geographical area optimized by walking distance, queue wait times, booking and arriving at reserved events, and/or by other user preferences.

Abstract: Embodiments provide for a system, comprising a plurality of encoders configured to generate a plurality of variant streams, and a cross-variant Instantaneous Decoder Refresh (IDR) identifier configured to inspect the plurality of variant streams, identify IDR frames in each of the plurality of variant streams, determine which IDR frames correspond to cross-variant boundaries, and demarcate the IDR frames corresponding to cross-variant boundaries.

Abstract: A method and device generates a fantasy sports recommendation. The method includes receiving a plurality of ranking values associated with a sport player, each of the ranking values being generated from a respective source. The method includes assigning a weight value to each of the ranking values, the weight value being associated with the respective source. The method includes generating a recommendation value for the sport player as a function of the ranking values and the corresponding weight values. The method includes receiving a selection value for the sport player. The method includes determining a further weight value for each of the sources as a function of the selection value, the recommendation value, and the weight value for the corresponding source.

Abstract: There is provided a system including a memory storing an executable code and a processor executing the executable code to provide access to a plurality of users to curate video clips stored in a content repository, wherein each video clip is associated with one of a plurality of ownership identifications, receive curation inputs from a user of one of a plurality of user devices arranging two or more video clips into a video compilation, wherein a first video clip is associated with the first ownership identification of a first content owner and a second video clip is associated with the second ownership identification of a second content owner, stream the video compilation to one or more of the plurality of user devices, and distribute a first fee to the first content owner and a second fee to the second content owner, in response to streaming the video compilation.

Abstract: A system includes a computing platform having processing hardware, one or more sensor(s), and a memory storing perception software and animation software, as well as an augmented reality (AR) headset including another processing hardware. The computing platform is configured to obtain an environmental data using the sensor(s), determine the location and orientation of the AR headset using the perception software and the environmental data, identify an action for execution by the computing platform, using the animation software and the location and orientation of the AR headset, and transmit performative data corresponding to the identified action to the AR headset. The AR headset is configured to receive, from the computing platform, the performative data, and to render at least one AR effect corresponding to the identified action using the performative data.

Abstract: A system providing a multi-persona social agent includes a computing platform having a hardware processor, a system memory storing a software code, and multiple neural network (NN) based predictive models accessible by the software code. The hardware processor executes the software code to receive input data corresponding to an interaction with a user, determine a generic expression for use in the interaction, and identify one of the character personas as a persona to be assumed by the multi-persona social agent. The software code also generates, using the generic expression and one of the NN based predictive models corresponding to the persona to be assumed by the multi-persona social agent, a sentiment driven personified response for the interaction with the user based on a vocabulary, phrases, and one or more syntax rules idiosyncratic to the persona to be assumed, and renders the sentiment driven personified response using the multi-persona social agent.

Abstract: Various embodiments disclosed herein provide techniques for performing incremental natural language understanding on a natural language understanding (NLU) system. The NLU system acquires a first audio speech segment associated with a user utterance. The NLU system converts the first audio speech segment into a first text segment. The NLU system determines a first intent based on a text string associated with the first text segment, wherein the text string represents a portion of the user utterance. The NLU system generates a first response based on the first intent prior to when the user utterance completes.

Abstract: Systems and methods are presented for generating statistics associated with a performance of a participant in an event, wherein pose data associated with the participant, performing in the event, are processed in real time. Pose data associated with the participant may comprise positional data of a skeletal representation of the participant. Actions performed by the participant may be determined based on a comparison of segments of the participant's pose data to motion patterns associated with actions of interests.

Abstract: According to one implementation, a system includes a computing platform having processing hardware, a system memory storing a software code; and a machine learning model based classifier. The processing hardware is configured to execute the software code to receive tagging quality assurance (QA) data including multiple terms applied as tags and corrections to those tags, to identify, using the tagging QA data, a first problematic term, and to classify, using the machine learning model based classifier, the first problematic term as one of confusing or flawed. The processing hardware is further configured to execute the software code to obtain, when the first problematic term is classified as confusing, a comparative sample for clarifying use of the first problematic term, and to obtain, when the first problematic term is classified as flawed, modification data for editing a predetermined annotation taxonomy including the first problematic term.

Abstract: In various embodiments, a prediction subsystem automatically predicts a level of network availability of a device network. The prediction subsystem computes a set of predicted attribute values for a set of devices attributes associated with the device network based on a trained recurrent neural network (RNN) and set(s) of past attribute values for the set of device attributes. The prediction subsystem then performs classification operation(s) based on the set of predicted attribute values and one or more machine-learned classification criteria. The result of the classification operation(s) is a network availability data point that predicts a level of network availability of the device network. Preemptive action(s) are subsequently performed on the device network based on the network availability data point. By performing the preemptive action(s), the amount of time during which network availability is below a given level can be substantially reduced compared to prior art, reactive approaches.

Abstract: A method includes assessing an input in a buffer against a rule in a first node of a rule tree to determine that an action should be performed and updating the buffer with results of performing the action. The method also includes inserting an indication of the input, the rule, and the results of performing the action into a tracker log and passing the updated buffer to a second node in the rule tree in response to determining that the first node points to the second node.

Abstract: A domain security assurance system includes a computing platform having processing hardware and a memory storing software code. The processing hardware is configured to execute the software code to obtain domain inventory data identifying multiple domains, to predict, using the domain inventory data, which of the domains are owned by the same entity to identify commonly owned domains, and to determine, using the domain inventory data and the commonly owned domains, which of the commonly owned domains are controlled by the same administrator to identify one or more group(s) of commonly administered domains. When executed, the software code also removes, using the domain inventory data, duplicate domains included in the group(s) to identify non-duplicate domains, evaluates a susceptibility of each of the non-duplicate domains to a cyber-attack to identify one or more target domain(s) vulnerable to the cyber-attack, and identifies the target domain(s) for a security assessment.