Abstract: A special effects system designed to provide a projection surface or screen that can be animated or dynamically altered in its shape and/or size over time while video content is being concurrently projected from a video projector onto the altering projection surface. The video content and projection surface alterations are synchronized in time, e.g., on a pixel basis or other level of precision in some cases, such that the size and/or shape of the projected imagery, e.g., of a character, an animated object, and/or the like, matches that of the size and shape or outline of the present state of the dynamically alterable projection surface.

Abstract: Various embodiments set forth systems and techniques for identifying issues associated with a domain name system (DNS) ecosystem. The techniques include receiving a first target domain name; identifying a plurality of DNS elements included in the DNS ecosystem that should be tested based on the first target domain name; performing one or more validation operations on the plurality of DNS elements based on the first target domain name to generate a first set of validation results; and identifying a first DNS issue associated with the first target domain name based on the first set of validation results.

Abstract: A system for performing authentication of content based on intrinsic attributes includes a computing platform having a hardware processor and a memory storing a content authentication software code. The hardware processor executes the content authentication software code to receive a content file including digital content and authentication data created based on a baseline version of the digital content, to generate validation data based on the digital content, to compare the validation data to the authentication data, and to identify the digital content as baseline digital content in response to determining that the validation data matches the authentication data based on the comparison. The hardware processor is also configured to execute the content authentication software code to identify the digital content as manipulated digital content in response to determining that the validation data does not match the authentication data based on the comparison.

Abstract: A system includes a computing platform having processing hardware, and a memory storing software code. The software code is executed to receive content having a sequence of content segments, and marker data identifying a location within the sequence, identify, using the content and the marker data, segment boundaries of a content segment containing the location, determine, using the location and the segment boundaries, whether the location is situated within a predetermined interval of one of the segment boundaries, and re-encode a subsection of the sequence to produce a new segment boundary at the location. When the location is not situated within the predetermined interval, the subsection of the sequence includes the content segment containing the location. When the location is situated within the predetermined interval, the subsection of the sequence includes the content segment containing the location and a content segment adjoining the content segment containing the location.

Abstract: A system includes a computing platform having processing hardware and a memory storing software code, a workstation database, and a station database. When executed, the software code receives workflow data describing a workflow for a station, obtains from the station database, using the workflow data, a configuration data for execution of the workflow by the station, and identifies, using the configuration data, multiple application programming interfaces (APIs). The software code further identifies, using the workstation database, a workstation for use by the station to execute the workflow, configures, using the configuration data, the workstation for execution of the workflow, and translates, during execution of the workflow, communications among the station and the multiple APIs into a common communication protocol.

Abstract: One embodiment of a method for migrating a multi-region network including multiple autonomous systems into a single autonomous system comprises allocating a unique identifier to each autonomous system of a plurality of autonomous systems, wherein each autonomous system includes a corresponding regional route reflector; tagging the routing instruction advertised to a global route reflector by a regional route reflector included in one of the plurality of autonomous systems with the unique identifier of the autonomous system corresponding to the regional route reflector that advertised the routing instruction; instructing the regional route reflectors included in the plurality of autonomous systems to ignore routing instructions received from the global route reflector that are tagged with one of the unique identifiers allocated to the plurality of autonomous systems; and migrating one autonomous system of the plurality of autonomous systems by: removing the unique identifier from routing instructions advertise

Abstract: Some implementations of the disclosure are directed to capturing facial training data for one or more subjects, the captured facial training data including each of the one or more subject's facial skin geometry tracked over a plurality of times and the subject's corresponding jaw poses for each of those plurality of times; and using the captured facial training data to create a model that provides a mapping from skin motion to jaw motion. Additional implementations of the disclosure are directed to determining a facial skin geometry of a subject; using a model that provides a mapping from skin motion to jaw motion to predict a motion of the subject's jaw from a rest pose given the facial skin geometry; and determining a jaw pose of the subject using the predicted motion of the subject's jaw.

Abstract: A system processing hardware executes a machine learning (ML) model-based video compression encoder to receive uncompressed video content and corresponding motion compensated video content, compare the uncompressed and motion compensated video content to identify an image space residual, transform the image space residual to a latent space representation of the uncompressed video content, and transform, using a trained image compression ML model, the motion compensated video content to a latent space representation of the motion compensated video content.

Abstract: A system includes a computing platform including a hardware processor and a system memory storing a software code. The hardware processor is configured to execute the software code to track interactions with a user application during use of the user application, generate, based on tracking the interactions, interaction data identifying multiple interaction events during the use, and perform a validity assessment of the interaction data. The hardware processor is further configured to execute the software code to identify, based on the validity assessment, one or more anomalies in the interaction data, and output, based on identifying the one or more anomalies in the interaction data, one or more of the interaction events corresponding respectively to the one or more anomalies.

Abstract: A playset comprises a plurality of hotspots positioned within a plurality of scenes. A switching mechanism is configured to selectively couple to the each of the plurality of hotspots and is communicatively coupled with a controller. The controller is configured to establish communication with a first object using a first hotspot and determine an object type of the first object and a location of the first object within the playset. The location of the first object corresponds to a scene that contains the first hotspot. The controller is further configured to select an interactive media based on the object type and the location of the first object, select a first media file based on the selected interactive media, and instruct the first media file to be output on an output device.

Abstract: In some embodiments, a method receives a first value for a feature. The first value is associated with an entity. A cohort is determined for the entity where a cohort is associated with a dimension, and the entity is associated with a dimension value for the dimension. The method determines a normalization value for the cohort based on the dimension value for the entity. The normalization value is generated based on second values at the dimension value for the feature, and the second values are associated with entities in the cohort. A cohort-agnostic feature value is generated based on the first value and the normalization value. The cohort-agnostic feature value is input into a model to generate a prediction for the entity.

Abstract: Various embodiments set forth systems and techniques for changing a face within an image. The techniques include receiving a first image including a face associated with a first facial identity; generating, via a machine learning model, at least a first texture map and a first position map based on the first image; rendering a second image including a face associated with a second facial identity based on the first texture map and the first position map, wherein the second facial identity is different from the first facial identity.

Abstract: An entertainment system for a vehicle is disclosed. In one embodiment, the entertainment system includes an at least partially enclosed structure configured to receive an on-road vehicle, where the structure defines a path along which the on-road vehicle is configured to move autonomously; a content output system configured to generate content based on one or more characteristics of the on-road vehicle; and a guide system configured to guide the on-road vehicle along the path.

Abstract: A system includes a hardware processor and a memory storing software code and one or more machine learning (ML) model(s) trained to transform content. The hardware processor executes the software code to ingest content components each corresponding respectively to a different feature of multiple features included in a content file, receive sensor data describing at least one of an action or an environment of a system user, and identify, using the sensor data, at least one of the content components as content to be transformed. The hardware processor further executes the software code to transform, using the ML model(s), that identified content to provide at least one transformed content component, combine a subset of the ingested content components with the at least one transformed content component to produce a dynamically transformed content, and output the dynamically transformed content in real-time with respect to ingesting the content components.

Abstract: A method to project content from a moving projector. The method includes analyzing an object to identify a projection surface; determining a first position of a projector relative to the projection surface; modifying a first frame of a content for projection onto the projection surface based on the projection surface and the first position of the projector; projecting the first frame of the content from the projector onto the projection surface; determining a second position of the projector relative to the projection surface; modifying a second frame of the content based on the projection surface and the second position; and projecting the second frame of the content from the projector onto the projection surface.

Abstract: In some embodiments, a system includes a first component to extract temporal features from a current frame being coded and a previous frame of a video. A second component uses a first transformer to fuse spatial features from the current frame with the temporal features to generate spatio-temporal features as first output. A third component uses a second transformer to perform entropy coding using the first output and at least a portion of the temporal features to generate a second output. A fourth component uses a third transformer to reconstruct the current frame based on the first output that is processed using the second output and the temporal features.

Abstract: In some embodiments, a method generates a first representation of a first relationship between bitrate and quality based on first features of a first portion of a video. Also, the method generates a second representation of a second relationship between bitrate and quality based on second features of a second portion of a video. The first representation is analyzed to determine a first list of bitrates for the first portion of video and the second representation is analyzed to determine a second list of bitrates for the second portion of video. The first list of bitrates is different from the second list of bitrates. The method outputs the first list of bitrates for use encoding the first portion of video and the second list of bitrates for use encoding the second portion of video.

Abstract: According to one implementation, an image compression system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive an input image, transform the input image to a latent space representation of the input image, and quantize the latent space representation of the input image to produce multiple quantized latents. The hardware processor further executes the software code to encode the quantized latents using a probability density function of the latent space representation of the input image, to generate a bitstream, and convert the bitstream into an output image corresponding to the input image. The probability density function of the latent space representation of the input image is obtained based on a normalizing flow mapping of one of the input image or the latent space representation of the input image.

Abstract: A database engine uses bitmap slice indices (BSIs) to combine result bitmaps derived from parent and child tables related via one or more foreign key relationships. To execute a query that involves a parent table and a child table, the database engine parses the query into a parent predicate corresponding to the parent table and a child predicate corresponding to the child table. The database engine executes the parent predicate using a parent bitmap index to generate a parent result bitmap and executes the child predicate using a child bitmap index to generate a child result bitmap. The database engine transforms the child result bitmap, based on the BSI, to generate a transformed child result bitmap having columns that correspond to the primary key of the parent table. The database engine can then combine the parent result bitmap directly with the transformed child result bitmap to generate query results.

Abstract: One embodiment of the present invention sets forth a technique for performing appearance capture. The technique includes receiving a first sequence of images of an object, wherein the first sequence of images includes a first set of images interleaved with a second set of images, and wherein the first set of images is captured based on illumination of the object using a first lighting pattern and the second set of images is captured based on illumination of the object using one or more lighting patterns that are different from the first lighting pattern. The technique also includes generating a first set of appearance parameters associated with the object based on a first inverse rendering associated with the first sequence of images.