Abstract: Systems and methods of the present disclosure include animating virtual avatars or agents according to input audio and one or more selected or determined emotions and/or styles. For example, a deep neural network can be trained to output motion or deformation information for a character that is representative of the character uttering speech contained in audio input. The character can have different facial components or regions (e.g., head, skin, eyes, tongue) modeled separately, such that the network can output motion or deformation information for each of these different facial components. During training, the network can use a transformer-based audio encoder with locked parameters to train an associated decoder using a weighted feature vector. The network output can be provided to a renderer to generate audio-driven facial animation that is emotion-accurate.

Abstract: In various examples, a virtually animated and interactive agent may be rendered for visual and audible communication with one or more users with an application. For example, a conversational artificial intelligence (AI) assistant may be rendered and displayed for visual communication in addition to audible communication with end-users. As such, the AI assistant may leverage the visual domain—in addition to the audible domain—to more clearly communicate with users, including interacting with a virtual environment in which the AI assistant is rendered. Similarly, the AI assistant may leverage audio, video, and/or text inputs from a user to determine a request, mood, gesture, and/or posture of a user for more accurately responding to and interacting with the user.

Abstract: In various examples, a virtually animated and interactive agent may be rendered for visual and audible communication with one or more users with an application. For example, a conversational artificial intelligence (AI) assistant may be rendered and displayed for visual communication in addition to audible communication with end-users. As such, the AI assistant may leverage the visual domain—in addition to the audible domain—to more clearly communicate with users, including interacting with a virtual environment in which the AI assistant is rendered. Similarly, the AI assistant may leverage audio, video, and/or text inputs from a user to determine a request, mood, gesture, and/or posture of a user for more accurately responding to and interacting with the user.

Abstract: In various examples, animations may be generated using audio-driven body animation synthesized with voice tempo. For example, full body animation may be driven from an audio input representative of recorded speech, where voice tempo (e.g., a number of phonemes per unit time) may be used to generate a 1D audio signal for comparing to datasets including data samples that each include an animation and a corresponding 1D audio signal. One or more loss functions may be used to compare the 1D audio signal from the input audio to the audio signals of the datasets, as well as to compare joint information of joints of an actor between animations of two or more data samples, in order to identify optimal transition points between the animations. The animations may then be stitched together—e.g., using interpolation and/or a neural network trained to seamlessly stitch sequences together—using the transition points.

Abstract: A detachable, self-balancing, pod for an unmanned aerial vehicle. The pod is configured to hold a plurality of different payloads, and to dynamically shift the location of these payloads in order to maintain an optimal center of mass (center of gravity) for the combination pod and UAV. The pod will have its own processor, as well as processor-controlled actuators to shift the payload location inside the pod to optimize balance, and to dispense the different individual payloads in different locations as directed.

Abstract: A deep neural network can be trained to output motion or deformation information for a character that is representative of the character uttering speech contained in audio input, which is accurate for an emotional state of the character. The character can have different facial components or regions (e.g., head, skin, eyes, tongue) modeled separately, such that the network can output motion or deformation information for each of these different facial components. During training, the network can be provided with emotion and/or style vectors that indicate information to be used in generating realistic animation for input speech, as may relate to one or more emotions to be exhibited by the character, a relative weighting of those emotions, and any style or adjustments to be made to how the character expresses that emotional state. The network output can be provided to a renderer to generate audio-driven facial animation that is emotion-accurate.

Abstract: In examples, locations of facial landmarks may be applied to one or more machine learning models (MLMs) to generate output data indicating profiles corresponding to facial expressions, such as facial action coding system (FACS) values. The output data may be used to determine geometry of a model. For example, video frames depicting one or more faces may be analyzed to determine the locations. The facial landmarks may be normalized, then be applied to the MLM(s) to infer the profile(s), which may then be used to animate the mode for expression retargeting from the video. The MLM(s) may include sub-networks that each analyze a set of input data corresponding to a region of the face to determine profiles that correspond to the region. The profiles from the sub-networks, along global locations of facial landmarks may be used by a subsequent network to infer the profiles for the overall face.

Abstract: Apparatuses, systems, and techniques are presented to generate media content.

Abstract: Provided herein is a liner that can be loosely inserted in process pipe to form a lined pipe and to decrease the rate of heat transfer between process fluids flowing through the liner and the process pipe. The liner provided herein can reduce applied thermal loading on the outer pipe resulting from, for example, turbulent mixing between fluids having different temperatures (with or without stratification), circumferential thermal gradients, and/or longitudinal thermal gradients. An annulus between the process pipe and liner can be at least partially filled by process fluids, thereby creating a thermal buffer to further decrease the rate of heat transfer between the fluids and the process pipe.

Abstract: A tube and tubesheet assembly is provided, which includes a tubesheet, the tubesheet comprising at least one tube insertion aperture therethrough; at least one tube inserted in the at least one tube insertion aperture; and a damage-resistant layer applied to an edge of the at least one tube and along an inner surface of a portion of the tube that is positioned within the corresponding tube insertion aperture. A heat exchanger including the assembly is also provided. A method is also provided for coupling a tube to a tubesheet. The method includes applying a damage-resistant layer to an edge of the tube and along an inner surface of a portion of the tube that is positioned within a tube insertion aperture in the tubesheet. The method can also be used to repair tubes and retrofit pre-existing tube-to-tubesheet joints.

Abstract: In various examples, a virtually animated and interactive agent may be rendered for visual and audible communication with one or more users with an application. For example, a conversational artificial intelligence (AI) assistant may be rendered and displayed for visual communication in addition to audible communication with end-users. As such, the AI assistant may leverage the visual domain—in addition to the audible domain—to more clearly communicate with users, including interacting with a virtual environment in which the AI assistant is rendered. Similarly, the AI assistant may leverage audio, video, and/or text inputs from a user to determine a request, mood, gesture, and/or posture of a user for more accurately responding to and interacting with the user.

Abstract: Provided herein is a liner that can be loosely inserted in process pipe to form a lined pipe and to decrease the rate of heat transfer between process fluids flowing through the liner and the process pipe. The liner provided herein can reduce applied thermal loading on the outer pipe resulting from, for example, turbulent mixing between fluids having different temperatures (with or without stratification), circumferential thermal gradients, and/or longitudinal thermal gradients. An annulus between the process pipe and liner can be at least partially filled by process fluids, thereby creating a thermal buffer to further decrease the rate of heat transfer between the fluids and the process pipe.

Abstract: Provided herein is a liner that can be loosely inserted in process pipe to form a lined pipe and to decrease the rate of heat transfer between process fluids flowing through the liner and the process pipe. The liner provided herein can reduce applied thermal loading on the outer pipe resulting from, for example, turbulent mixing between fluids having different temperatures (with or without stratification), circumferential thermal gradients, and/or longitudinal thermal gradients. An annulus between the process pipe and liner can be at least partially filled by process fluids, thereby creating a thermal buffer to further decrease the rate of heat transfer between the fluids and the process pipe.

Abstract: Various embodiments of systems and methods for deforming a virtual geometric object are disclosed. In accordance with at least one embodiment, a method for deforming a virtual geometric object substantially real-time includes the operations of relaxing a hi-res mesh defining a shape of the object, wherein the hi-res mesh corresponds to a proxy mesh, relaxing the hi-res mesh at least once, recording the location of the elements of the hi-res mesh as relaxed, deforming the proxy mesh, adjusting the location of one or more elements on the hi-res mesh relative to the as deformed proxy mesh, relaxing the adjusted elements on the deformed hi-res mesh, and adjusting the location of the hi-res mesh as deformed in view of the previously recorded elements of the hi-res mesh as relaxed both pre and after deformation.

Abstract: Various embodiments of systems and methods for deforming a virtual geometric object are disclosed. In accordance with at least one embodiment, a method for deforming a virtual geometric object substantially real-time includes the operations of relaxing a hi-res mesh defining a shape of the object, wherein the hi-res mesh corresponds to a proxy mesh, relaxing the hi-res mesh at least once, recording the location of the elements of the hi-res mesh as relaxed, deforming the proxy mesh, adjusting the location of one or more elements on the hi-res mesh relative to the as deformed proxy mesh, relaxing the adjusted elements on the deformed hi-res mesh, and adjusting the location of the hi-res mesh as deformed in view of the previously recorded elements of the hi-res mesh as relaxed both pre and after deformation.