Abstract: In some embodiments, a method selects first content and second content. The first content and the second content are configured to be delivered to clients. First labels are determined for categories for the first content. The first labels are based on an analysis of the first content. Second labels are determined for the categories for the second content. The second labels are based on an analysis of the second content. The method compares the first labels and the second labels to determine scores for the first labels. The scores is based on parameters of a matching tool that is configured to determine a match between instances of content. A weight of a category is used to adjust a score in the scores to generate an adjusted score. The score is for the label that is determined for the category. The method outputs information for the adjusted score and other scores.

Abstract: In some embodiments, a method determines a break in a delivery of an instance of catalog content and determines instances of supplemental content. A plurality of transition scores is generated for a plurality of combinations of one or more instances of supplemental content and the instance of catalog content based on a comparison of first metadata for the one or more instances of supplemental content to second metadata for the instance of catalog content. The first metadata is based on an analysis of content characteristics of the instance of supplemental content and the second metadata is based on an analysis of content characteristics of the instance of catalog content. The method uses the transition scores to select a combination of one or more instances of supplemental content. A transition score rates a transition between the instance of catalog content and the combination of one or more instances of supplemental content.

Abstract: Techniques for electronic privacy protection are disclosed. A first data record is received, including one or more sensitive data fields and one or more non-sensitive data fields. One or more encrypted data fields are generated by encrypting the one or more sensitive data fields using an encryption key. One or more hashed data fields are generated by hashing the one or more sensitive data fields using a hash function. A first mapping is stored, associating at least a portion of the first data record with the encryption key. A second data record is stored, including the one or more non-sensitive data fields, the one or more encrypted data fields, and the one or more hashed data fields.

Abstract: A content recommendation system includes a computing platform having a hardware processor and a system memory storing a content surfacing software code providing a user interface. The hardware processor executes the content surfacing software code to receive an initiation signal identifying a user, and, in response, identify content items as desirable content items to the user based on the user and metadata describing each of the desirable content items. In addition, the content surfacing software code generates a networked map of nodes corresponding respectively to the desirable content items, where the distances between nodes are based on the similarity of the metadata describing the desirable content items corresponding to the nodes. The content surfacing software code further outputs the networked map for display to the user via the user interface, the nodes being displayed as thumbnail images depicting the desirable content and selectable by the user.

Abstract: A system for simulating human-like affect-driven behavior includes a hardware processor and a system memory storing software code providing a virtual agent. The hardware processor executes the software code to identify a character assumed by the virtual agent and having a personality, a target state of motivational fulfillment, a baseline mood, and emotions. The software code identifies current physical and motivational fulfillment states, and currently active emotions of the character, and determines a current mood of the character based on the baseline mood and the currently active emotions. The software code further detects an experience by the character and plans multiple behaviors including a first behavior based on the experience and the current physical state, the second behavior based on the experience, the personality, the current mood, and the currently active emotions, and a third behavior based on the target and current states of motivational fulfillment.

Abstract: Embodiment of the present invention sets forth techniques for performing face reconstruction. The techniques include generating an identity mesh based on an identity encoding that represents an identity associated with a face in one or more images. The techniques also include generating an expression mesh based on an expression encoding that represents an expression associated with the face in the one or more images. The techniques also include generating, by a machine learning model, an output mesh of the face based on the identity mesh and the expression mesh.

Abstract: A technique for rendering an input geometry includes generating a first segmentation mask for a first input geometry and a first set of texture maps associated with one or more portions of the first input geometry. The technique also includes generating, via one or more neural networks, a first set of neural textures for the one or more portions of the first input geometry. The technique further includes rendering a first image corresponding to the first input geometry based on the first segmentation mask, the first set of texture maps, and the first set of neural textures.

Abstract: Embodiments provide for methods, computer program products, and systems to improve media playback comprising receiving a variant stream, identifying respective maximum segment durations for a plurality of different types of client devices that will play media content contained in the variant stream, generating, using the variant stream, a respective playlist for each of the plurality of different types of client devices, wherein the respective playlists each contain different maximum segment durations, and delivering the respective playlists to at least one of the plurality of different types of client devices via a distribution network.

Abstract: A system includes processing hardware and a memory storing software code. The processing hardware executes the software code to receive automation data for media content having a default playback experience, analyze, using the automation data, at least one parameter of the media content, and generate, based on the analyzing, one or more automation instruction(s) for at least one portion(s) of the media content. The automation instruction(s) include at least one of: one or more bounding timestamps of the media content portion(s), an increased or reduced playback speed for the media content portion(s) relative to the default playback experience, or a variable playback speed for the media content portion(s). The software code is further executed to outputs the automation instruction(s) to a media delivery platform configured to distribute and control the quality of the media content or to a media player configured to automate playback of the media content.

Abstract: Techniques are disclosed for generating photorealistic images of objects, such as heads, from multiple viewpoints. In some embodiments, a morphable radiance field (MoRF) model that generates images of heads includes an identity model that maps an identifier (ID) code associated with a head into two codes: a deformation ID code encoding a geometric deformation from a canonical head geometry, and a canonical ID code encoding a canonical appearance within a shape-normalized space. The MoRF model also includes a deformation field model that maps a world space position to a shape-normalized space position based on the deformation ID code. Further, the MoRF model includes a canonical neural radiance field (NeRF) model that includes a density multi-layer perceptron (MLP) branch, a diffuse MLP branch, and a specular MLP branch that output densities, diffuse colors, and specular colors, respectively. The MoRF model can be used to render images of heads from various viewpoints.

Abstract: Techniques for animatronic design are provided. A plurality of simulated meshes is generated using a physics simulation model, where the plurality of simulated meshes corresponds to a plurality of actuator configurations for an animatronic mechanical design. A machine learning model is trained based on the plurality of simulated meshes and the plurality of actuator configurations. A plurality of predicted meshes is generated for the animatronic mechanical design, using the machine learning model, based on a second plurality of actuator configurations. Virtual animation of the animatronic mechanical design is facilitated based on the plurality of predicted meshes.

Abstract: A plush toy having an outer fabric shell with an outer surface defining a desired shape for the plush toy and an in inner surface defining a void. A fiberfill layer covers an inner surface of the outer fabric shell. A foam inner inside the defined void, where the foam inner and the fiberfill layer are sized to completely fill the void such that the foam inner is not compressed while in a relaxed state, but can be compressed as a user interacts with the plush toy and that the fiberfill completely buffers the foam inner form direct contact with the outer fabric shell.

Abstract: A computing platform including a processing hardware and a memory storing a software code is coupled to at least first and second workstations and a production asset library. The processing hardware executes the software code to send, from the first workstation, a request identifying a production asset and metadata specification to the second workstation, and receive, from the second workstation, a payload including the production asset and production asset data including preview metadata describing a 3D image of the production asset. The software code further provides the 3D image for display on the first workstation or a third workstation, receives, at the first workstation or the third workstation, a validation input for the production asset, and publishes, in response to receiving the validation input, the production asset data to the production asset library.

Abstract: A themed aerial vehicle entertainment system or platform useful for generating crowd-pleasing shows or displays through the use of dynamically-coordinated show systems. Instead of use of a fixed flight plan, the new entertainment platform is configured to include one or more UAVs that is enclosed within or supports thematic cladding such as the outer shell of a spacecraft or flying character, and the show is dynamically coordinated to present a cohesive performance. Onboard show effects provided by onboard or UAV supported show system components such as high brightness lights are dynamically adjusted in the new system/platform to ensure the best show appearance to the audience while providing safer operations. The dynamic adjustments may involve selecting or generating a second script or “B show” in a contingent manner based on the current location or timing of movement of the UAV along a flight plan.

Abstract: One embodiment of the present invention sets forth a technique for generating actuation values based on a target shape such that the actuation values cause a simulator to output a simulated soft body that matches the target shape. The technique includes inputting a latent code that represents a target shape and a point on a geometric mesh into a first machine learning model. The technique further includes generating, via execution of the first machine learning model, one or more simulator control values that specify a deformation of the geometric mesh, where each of the simulator control values is based on the latent code and corresponds to the input point, and generating, via execution of the simulator, a simulated soft body based on the one or more simulator control values and the geometric mesh. The technique further includes causing the simulated soft body to be outputted to a computing device.

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: One embodiment of the present invention sets forth a technique for inserting content into a media program. The technique includes determining a plurality of markers corresponding to a plurality of locations within a media program. The technique also includes for each marker included in the plurality of markers, automatically analyzing a first set of intervals within the media program that lead up to the marker and a second set of intervals within the media program that immediately follow the marker and determine a set of audio characteristics associated with the first set of intervals and the second set of intervals. The technique further includes generating a plurality of scores for the plurality of markers based on the set of audio characteristics for each marker and inserting additional content at one or more markers included in the plurality of markers based on the plurality of scores.

Abstract: A system for providing a physical projection routine includes a hardware processor, a system memory storing a software code, and a projection platform. The hardware processor is configured to execute the software code to measure an environmental parameter of a venue, determine, based on the environmental parameter, a desired orientation of the projection platform for executing the physical projection routine, and orient the projection platform according to the desired orientation determined based on the environmental parameter. The hardware processor and software code then execute the physical projection routine by the projection platform oriented using the desired orientation determined based on the environmental parameter.

Abstract: A system includes a computing platform having processing hardware and a memory storing a software code. The processing hardware executes the software code to receive a dataset including at least some data samples having multiple metadata labels, and identify a partitioning constraint and a partitioning of the dataset into data subsets. The software code also executed obtains, for each metadata label, a desired distribution ratio based on the number of the data subsets and a total number of instances that each metadata label has been applied to the data samples, aggregates, using the partitioning constraint, the data samples into data sample groups, assigns, using the partitioning constraint and the desired distribution ratio for each of the metadata labels, each of the data sample groups to one of the data subsets, wherein each of the data subsets are unique, and trains, using one of the data subsets, a machine learning model.