Abstract: Described is a task for an automobile interior having at least one subject that creates a video input, an audio input, and a context descriptor input. The video input relates to the at least one subject and is processed by a face detection module and a facial point registration module to produce a first output. The first output is further processed by at least one of: a facial point tracking module, a head orientation tracking module, a body tracking module, a social gaze tracking module, and an action unit intensity tracking module. The audio input relating to the at least one subject is processed by a valence and arousal affect states tracking module to produce a second output and to produce a valence and arousal scores output. A temporal behavior primitives buffer produce a temporal behavior output. Based on the foregoing, a mental state prediction module predicts the mental state of at least one subject in the automobile interior.

Abstract: A vane including an airfoil body extending from a root to a tip defining a longitudinal axis therebetween, wherein the airfoil body includes a leading edge between the root and the tip. The vane includes a pressure side and a suction side and a recess area on the leading edge. The recess area includes a pressure side recess area and a suction side recess area, and a metal is deposited on the recess area. A method of manufacturing the vane and a gas turbine engine including the vane are also disclosed.

Abstract: Described is a system to evaluate the efficacy of a set of candidate interactive tasks in eliciting fatigue markers in facial and vocal expressions. Input video and audio streams are processed, followed by face detection, followed by detecting the facial landmarks. Based on these, higher level features are derived, such as gaze vectors, head pose, action units and audio features based on the audio input. Higher level features are fused together over a time window and used to estimate the fatigue level as well as a confidence level for the estimate. The video and audio streams may either be collected organically (e.g., in a car/plane) or collected with the help of an app that presents the user with a stimulus task.

Abstract: A vane including an airfoil body extending from a root to a tip defining a longitudinal axis therebetween, wherein the airfoil body includes a leading edge between the root and the tip. The vane includes a pressure side and a suction side and a recess area on the leading edge. The recess area includes a pressure side recess area and a suction side recess area, and a metal is deposited on the recess area. A method of manufacturing the vane and a gas turbine engine including the vane are also disclosed.

Abstract: A computing system comprising a generative neural network (100) is disclosed. The generative neural network (100) is configured to receive a plurality of input videos. Each input video comprises a face defining an identity. Each input video comprises a behaviour. Each input video comprises the same behaviour as each of the other input videos, and a different identity to each of the other input videos. The generative neural network (100) is also configured synthesize an output video from the input videos. The output video comprises a synthetic face defining a synthetic identity. The generative neural network has been trained, with a loss function, to preserve the behaviour of the input videos while generating the synthetic identity that is different from each identity of the input videos.

Abstract: A system using large language models (LLMs) with multimodal inputs that has a low latency (within 500 ms) response time is described. This low latency produces a response that leads to a more engaging and empathetic user experience with all calculations done on consumer hardware. In so doing, the LLM derives the emotional state of the user using message sentiment analysis and/or face behavior and/or voice parameters that leads to a more engaging and empathetic user experience. This occurs by reviewing: (a) the user's mood state while providing an input prompt to the LLM in the current turn; (b) the user's mood and mental states while reacting to the LLM's response in the previous turn; (c) the sentiment of the LLM's response in the previous turn; and (d) the desired user mood and mental state as determined by the system's empathetic goal.

Abstract: A computing system comprising a generative neural network (100) is disclosed. The generative neural network (100) is configured to receive a plurality of input videos. Each input video comprises a face defining an identity. Each input video comprises a behaviour. Each input video comprises the same behaviour as each of the other input videos, and a different identity to each of the other input videos. The generative neural network (100) is also configured synthesize an output video from the input videos. The output video comprises a synthetic face defining a synthetic identity. The generative neural network has been trained, with a loss function, to preserve the behaviour of the input videos while generating the synthetic identity that is different from each identity of the input videos.

Abstract: A system using large language models (LLMs) with multimodal inputs that has a low latency (within 500 ms) response time is described. This low latency produces a response that leads to a more engaging and empathetic user experience with all calculations done on consumer hardware. In so doing, the LLM derives the emotional state of the user using message sentiment analysis and/or face behavior and/or voice parameters that leads to a more engaging and empathetic user experience. This occurs by reviewing: (a) the user's mood state while providing an input prompt to the LLM in the current turn; (b) the user's mood and mental states while reacting to the LLM's response in the previous turn; (c) the sentiment of the LLM's response in the previous turn; and (d) the desired user mood and mental state as determined by the system's empathetic goal.

Abstract: A system using large language models (LLMs) with multimodal inputs that has a low latency (within 500 ms) response time is described. This low latency produces a response that leads to a more engaging and empathetic user experience with all calculations done on consumer hardware. In so doing, the LLM derives the emotional state of the user using message sentiment analysis and/or face behavior and/or voice parameters that leads to a more engaging and empathetic user experience. This occurs by reviewing: (a) the user's mood state while providing an input prompt to the LLM in the current turn; (b) the user's mood and mental states while reacting to the LLM's response in the previous turn; (c) the sentiment of the LLM's response in the previous turn; and (d) the desired user mood and mental state as determined by the system's empathetic goal.

Abstract: An electric bicycle charger assembly includes a trailer that can be attached to a seat post of an electric bicycle thereby facilitating the electric bicycle to tow the trailer. A pair of wheels is each of the wheels is rotatably attached to the trailer and a pair of charging units is each integrated into a respective one of the wheels generate electricity when the trailer is being towed. Each of the charging units is electrically coupled to the electric bicycle for charging the electric bicycle. A braking system is integrated into the trailer and the braking system is in communication with a braking apparatus of the electric bicycle thereby assisting with slowing and stopping.

Abstract: A computer-implemented method for generating feedback for a user performing hair care, the computer-implemented method includes receiving a sequence of images of a face of the user during a hair care process. The method also includes analysing a haircare performance by determining: a facial expression of the user in the sequence of images, and one or more performance parameters and/or one or more haircare events based on the facial expression of the user. The method also includes generating feedback for the user during the hair care process based on: the haircare performance, and the one or more performance parameters and/or the one or more haircare events. The feedback comprises one or more of an instruction, a recommendation, or guidance to improve the hair care process.

Abstract: A computer-implemented method for generating feedback for a user in performing personal care includes receiving a sequence of images of a face of a user and a personal care implement. The method also includes determining one or more implement parameters by tracking the personal care implement using the sequence of images. The method also includes determining one or more facial apparent emotional expressions of the user using the sequence of images. The method also includes analysing a personal care performance based on i) the one or more implement parameters and the one or more facial apparent emotional expressions of the user in a current personal care session and ii) the one or more implement parameters and the one or more facial apparent emotional expressions of the user from a previous personal care session, and determining one or more performance parameters or one or more personal care events.

Abstract: A computer-implemented method for generating feedback for a user performing haircare includes receiving a sequence of images of a head of the user and a haircare implement, the haircare implement being a hairstyling implement. The computer-implemented method also includes determining one or more implement motion parameters by tracking a position or an orientation of the haircare implement using the sequence of images. The computer-implemented method also includes determining a detangling event if one or more of: linear velocity, angular velocity, linear acceleration, and angular acceleration of the haircare implement is less than a corresponding detangling motion threshold, the detangling event being an event in which tangles from hair of the user are being removed. The computer-implemented method also includes generating feedback for providing to the user based on the determined detangling event.

Abstract: A method of tracking a user's toothcare activity comprises receiving video images of a user's face during, e.g. a toothbrushing session, and identifying, in each of a plurality of frames of the video images, predetermined features of the user's face. The features include at least two invariant landmarks associated with the user's face and one or more landmarks selected from at least mouth feature positions and eye feature positions. Predetermined marker features of a toothcare appliance, e.g. a brush in use are identified in each of the plurality of frames of the video images. From the at least two invariant landmarks associated with the user's nose, a measure of inter-landmark distance is determined. An appliance length normalised by the inter-landmark distance is determined. From the one or more landmarks selected from at least mouth feature positions and eye feature positions, one or more appliance-to-facial feature distances each normalised by the inter-landmark distance is determined.

Abstract: Described is a task for an automobile interior having at least one subject that creates a video input, an audio input, and a context descriptor input. The video input relates to the at least one subject and is processed by a face detection module and a facial point registration module to produce a first output. The first output is further processed by at least one of: a facial point tracking module, a head orientation tracking module, a body tracking module, a social gaze tracking module, and an action unit intensity tracking module. The audio input relating to the at least one subject is processed by a valence and arousal affect states tracking module to produce a second output and to produce a valence and arousal scores output. A temporal behavior primitives buffer produce a temporal behavior output. Based on the foregoing, a mental state prediction module predicts the mental state of at least one subject in the automobile interior.

Abstract: Wearable container systems for containing items. The wearable container systems include a strap and a container. The strap is configured to operatively secure to a person. The container is coupled to the strap and includes a body and an insert. The insert is disposed within the body. The insert is configured to support the items.

Abstract: Methods and apparatus provide a picture-in-picture (PIP) overlay window on a single physical monitor by displaying a first swap chain of the single physical monitor, reporting to an operating system (OS), a display level request for a fake connection to a non-existent second monitor, and displaying on the single physical monitor a virtual display defined by a second swap chain of the non-existent second monitor, as the PIP overlay window on the displayed content of the first swap chain on the single physical monitor.

Abstract: A computing system comprising a generative neural network (100) is disclosed. The generative neural network (100) is configured to receive a plurality of input videos. Each input video comprises a face defining an identity. Each input video comprises a behaviour. Each input video comprises the same behaviour as each of the other input videos, and a different identity to each of the other input videos. The generative neural network (100) is also configured synthesize an output video from the input videos. The output video comprises a synthetic face defining a synthetic identity. The generative neural network has been trained, with a loss function, to preserve the behaviour of the input videos while generating the synthetic identity that is different from each identity of the input videos.

Abstract: A method for determining the presence of a copy number imbalance in genomic DNA of a test sample is provided. The method can separately measure hybridization of a single test sample to a first hybridization array and hybridization of a plurality of reference samples to a plurality of other, respective test arrays. A determination of copy number can be based on the best fit reference array, relative to the test array. The best fit can be determined based on the closest or most similar signal-to-noise ratio of the measured signals.