Abstract: A robot control method, and associated robot controllers and robots operating with such methods and controllers, providing real-time vibration suppression. The control method involves learning to support real-time, vibration-suppressing control. The method uses state-of-the-art machine learning techniques in conjunction with a differentiable dynamics simulator to yield fast and accurate vibration suppression. Vibration suppression using offline simulation approaches that can be computationally expensive may be used to create training data for the controller, which may be provide by a variety of neural network configurations. In other cases, sensory feedback from sensors onboard the robot being controlled can be used to provide training data to account for wear of the robot's components.

Abstract: Techniques are disclosed for learning a machine learning model that maps control data, such as renderings of skeletons, and associated three-dimensional (3D) information to two-dimensional (2D) renderings of a character. The machine learning model may be an adaptation of the U-Net architecture that accounts for 3D information and is trained using a perceptual loss between images generated by the machine learning model and ground truth images. Once trained, the machine learning model may be used to animate a character, such as in the context of previsualization or a video game, based on control of associated control points.

Abstract: Systems and methods for tracking objects in a field of view are disclosed. In one embodiment a method may include capturing, via a camera, a real-world object in the field of view; generating a first object data associating the real-world object with a first position of the real-world object in a real-world environment at a first time; generating a virtual object representative of the real-world object depicting the real-world object in the first position at the first time; generating a second object data associating the real-world object with a second position of the real-world object in the real-world environment at a second time, determining a displacement value of the real-world object between the first position and the second position, modifying the virtual object to include an indication that the real-world object has been displaced when the displacement value is greater than a threshold value.

Abstract: Systems and methods for dynamically and automatically generating digital watermarks are provided. Watermark payloads utilized in generating the digital watermarks are altered based upon changing conditions, such as environmental characteristics associated with playback or distribution of media content. Changing conditions may also encompass a change in the distribution/presentation chain of devices associated with the playback or distribution of the media content.

Abstract: Techniques for personalized gamification of media content. An engagement level of a consumer is identified based on prior gamification data. A difficulty level is identified using machine learning based on the engagement level. A content element personalized for the consumer is generated based on biographical information or viewing habits. A prompt requesting the consumer to find and access multimedia content scenes depicting the content element is generated. A multimedia content scene found by the consumer is analyzed to determine whether the multimedia content scene has an association with the content element and whether the consumer has accessed the multimedia content element scene.

Abstract: The embodiments herein describe a firewall for a media production system to provide flexible security between an on-premises production environment and remote media production applications and devices (e.g., cloud-based virtual production environments). As new media devices and applications (referred to generally as media nodes) are added at remote locations, the firewall is updated to permit the media nodes to communicate with the on-premises production environment. The embodiments herein described an automatic (e.g., software driven) process where a network orchestrator can detect a change in the media nodes and update the rule set in the firewall accordingly.

Abstract: A system for providing default content enhanced with supplemental content includes processing hardware and a memory storing a software code. The processing hardware executes the software code to receive a content stream including multiple video frames, a first video frame of the multiple video frames including first default content, first supplemental content, and first encoded metadata, and to decode the first encoded metadata of the first video frame to produce first decoded metadata. The processing hardware further executes the software code to select, using the first decoded metadata, at least a first portion of the first supplemental content for use in enhancing the first default content, transfer, using the first decoded metadata, the selected first portion of the first supplemental content to one or more predetermined locations in the first default content to produce an enhanced first video content, and output the enhanced first video content to a display device.

Abstract: A surface covering for use as a moss covering or patch of grass via application to a surface or substrate. The surface covering provides a decorative and durable and easily maintained surface covering. The covering is fabricated using groups of fibers, such as metallic, plastic, or other material fibers, e.g., stainless steel fibers or strands available commercially as steel wool or the like. The fibers or strands provide a core of a body of each blade or piece of the surface covering, which is useful to replicate a blade of grass or moss or to mimic a strand of hair. Each body of the strands further includes an outer layer or coating, which can be formed by painting, e.g., with an epoxy or other useful material that may be colored, the mesh of metal fibers to provide a durable body with a desired look and feel.

Abstract: In various embodiments, an interactive streaming application plays back a media title via a client device. In operation, while a client device plays back a first chunk of the media title, the interactive streaming application determines a first movement of an internet of things (“IoT”) device. The interactive streaming application then determines, from multiple target states, a target state that is associated with the first movement. Based on the target state, the interactive streaming application determines that a second chunk of the media title should be a next chunk of the media title that is streamed to the client device for playback. The interactive streaming application then causes the second chunk of the media title to be streamed to the client device. Advantageously, the interactive streaming application can automatically personalize the playback of the media title for a user based, at least in part, on movements of the IoT device.

Abstract: There is provided systems and methods for performing actions based on light signatures. An exemplary system includes a light source, a light detector, a non-transitory memory storing a plurality of light signatures and a hardware processor. The hardware processor executes an executable code to illuminate, using the light source, a target object with a first light, collect, using the light detector, a second light being a reflection of the first light by the target object, match the second light with one of the plurality of light signatures, and perform an action in response to matching the second light with the one of the plurality of light signatures.

Abstract: There is provided a method including receiving a playback system identifier corresponding to a playback system, generating a blockchain corresponding to a content identifier identifying a content, wherein the blockchain is uniquely associated with the content identifier, establishing, in the blockchain, a block corresponding to the playback system identifier, sending an encrypted version of the content to the playback system, and in response to one or more updates to the blockchain by the playback system, providing a content encryption key to the playback system for decrypting the encrypted version of the content.

Abstract: A storytelling system includes location-based content (LBC) servers and LBC effects databases for use in a real-world story venue, and a computing platform communicatively coupled to those LBC servers and databases. A processor of the computing platform executes software code to receive story selection data from a user device, obtain a story template including story arcs each associated with one or more LBC effect(s) that corresponds to the story selection data, and determine, using a location of the user device, one of the story arcs as an active story arc. The software code also identifies an LBC interaction zone for the LBC effect(s), designates one LBC server and one LBC effects database for supporting the active story arc, and distributes one or more of the LBC effect(s) to the designated database. The designated server enables instantiation of the one or more of the LBC effect(s) at the LBC interaction zone.

Abstract: The present disclosure relates to calibration, customization, and improved user experiences for smart or bionic lenses that are worn by a user. The calibration techniques include detecting and correcting distortion of a display of the bionic lenses, as well as distortion due to characteristics of the lens or eyes of the user. The customization techniques include utilizing the bionic lenses to detect eye characteristics that can be used to improve insertion of the bionic lenses, track health over time, and provide user alerts. The user experiences include interactive environments and animation techniques that are improved via the bionic lenses.

Abstract: There is provided a method for use by a mobile device. The method includes launching a software application requiring an identity verification of each of a plurality of users for performing a requested action, the plurality of users including a first user and a second user, receiving a first biometric information of the first user and a second biometric information of the second user, sending the first biometric information of the first user and the second biometric information of the second user to a server, receiving notifications from the server as to whether the first and second biometric information corresponding to biometric information in first user and second user profiles, respectively, and performing the requested action, if the notifications indicate a match.

Abstract: A system for performing digital rights protected content playing includes a computing platform having a hardware processor and a memory storing a software code. The hardware processor executes the software code to receive, from a first user, metadata identifying one or more content segment(s), determine whether the first user has a right to access the content segment(s), produce a playlist using the metadata when the first user has the right, and output the playlist to the first user and/or a second user. The hardware processor may further execute the software code to receive the playlist from the second user, determine each content segment identified by the playlist that the second user has a right to access, generate a content compilation that omits any content segment identified by the playlist to which the second user lacks the right, and playout the content compilation to the second user.

Abstract: A system includes a computing platform having a hardware processor and a memory storing a software code and a neural network (NN) having multiple layers including a last activation layer and a loss layer. The hardware processor executes the software code to identify different combinations of layers for testing the NN, each combination including candidate function(s) for the last activation layer and candidate function(s) for the loss layer. For each different combination, the software code configures the NN based on the combination, inputs, into the configured NN, a training dataset including multiple data objects, receives, from the configured NN, a classification of the data objects, and generates a performance assessment for the combination based on the classification. The software code determines a preferred combination of layers for the NN including selected candidate functions for the last activation layer and the loss layer, based on a comparison of the performance assessments.

Abstract: In various embodiments, a training application generates training items for three-dimensional (3D) pose estimation. The training application generates multiple posed 3D models based on multiple 3D poses and a 3D model of a person wearing a costume that is associated with multiple visual attributes. For each posed 3D model, the training application performs rendering operation(s) to generate synthetic image(s). For each synthetic image, the training application generates a training item based on the synthetic image and the 3D pose associated with the posed 3D model from which the synthetic image was rendered. The synthetic images are included in a synthetic training dataset that is tailored for training a machine-learning model to compute estimated 3D poses of persons from two-dimensional (2D) input images. Advantageously, the synthetic training dataset can be used to train the machine-learning model to accurately infer the orientations of persons across a wide range of environments.

Abstract: In some implementations, a device may provide a data structure storing first data, wherein the first data indirectly identifies second data, and wherein the second data identifies a particular individual. The device may obtain, from the data structure, the first data. The device may generate a cryptographically random value using a secure generator. The device may combine the first data and the cryptographically random value to generate hashing input data. The device may perform, using a hashing algorithm, a hashing operation on the hashing input data to generate de-identified first data, wherein re-identification of the de-identified first data requires knowledge of at least the first data, the cryptographically random value, and the de-identified first data. The device may perform an action using the de-identified first data.

Abstract: This disclosure relates to systems and methods for using augmented reality with the internet of things. An augmented reality experience may be provided based on an operation of an object. Operation status information of a detected object may be obtained and a visual effect may be determined based on the operation status information. An object may be controlled using augmented reality. Operation status information of a detected object may be obtained and a control option may be determined based on the operation status information. A visual effect may be determined based on the control option and a user input regarding the control option may be obtained. A control information configured to effectuate a change in the operation of the object may be transmitted to the object.

Abstract: Techniques for using holographic imagery for eyeline reference for performers. A first computer generated object is identified for display to a first performer at a designated physical position on a set. A first holographic projection of the first computer generated object is generated using a first holographic display. The first holographic display is configured to make the first holographic projection appear, to the first performer, to be located at the designated physical position on the set. One or more images of the performer are captured using an image capture device with a field of view that encompasses both the first performer and the designated physical position on the set. The captured one or more images depict the first performer and do not depict the first holographic projection. The first computer generated object is added to the captured one or more images after the capturing.