Abstract: A control system comprises a memory storing a sequence of sensor data received from one or more sensors. The control system has a processor which processes the sensor data to compute a sequence of derived sensor data values. An autoencoder receives the sequence of derived sensor data values and computes a forward prediction of the sequence of derived sensor data values, the autoencoder having been trained imposing a relationship on positions of the derived sensor data values encoded in a latent space of the autoencoder. A processor initiates control of an apparatus using the forward prediction.

Abstract: A method for virtually representing human body poses includes receiving positioning data detailing parameters of one or more body parts of a human user based at least in part on input from one or more sensors. One or more mapping constraints are maintained that relate a model articulated representation to a target articulated representation. A model pose of the model articulated representation and a target pose of the target articulated representation are concurrently estimated based at least in part on the positioning data and the one or more mapping constraints. The previously-trained pose optimization machine is trained with training positioning data having ground truth labels for the model articulated representation. The target articulated representation is output for display with the target pose as a virtual representation of the human user.

Abstract: A neural optimizer is disclosed that is easily applicable to different fitting problems, can run at interactive rates without requiring significant efforts, does not require hand crafted priors, carries over information about previous iterations of the solve, controls the learning rate of each parameter independently for robustness and convergence speed, and combines updates from gradient descent and from a method capable of very quickly reducing the fitting energy. A neural fitter estimates the values of the parameters ? by iteratively updating an initial estimate ?0.

Abstract: A method for virtually representing human body poses includes receiving positioning data detailing parameters of one or more body parts of a human user based at least in part on input from one or more sensors. One or more mapping constraints are maintained that relate a model articulated representation to a target articulated representation. A model pose of the model articulated representation and a target pose of the target articulated representation are concurrently estimated based at least in part on the positioning data and the one or more mapping constraints. The previously-trained pose optimization machine is trained with training positioning data having ground truth labels for the model articulated representation. The target articulated representation is output for display with the target pose as a virtual representation of the human user.

Abstract: A control system comprises a memory storing a sequence of sensor data received from one or more sensors. The control system has a processor which processes the sensor data to compute a sequence of derived sensor data values. An autoencoder receives the sequence of derived sensor data values and computes a forward prediction of the sequence of derived sensor data values, the autoencoder having been trained imposing a relationship on positions of the derived sensor data values encoded in a latent space of the autoencoder. A processor initiates control of an apparatus using the forward prediction.

Abstract: A control system comprises a memory storing a sequence of sensor data received from one or more sensors. The control system has a processor which processes the sensor data to compute a sequence of derived sensor data values. An autoencoder receives the sequence of derived sensor data values and computes a forward prediction of the sequence of derived sensor data values, the autoencoder having been trained imposing a relationship on positions of the derived sensor data values encoded in a latent space of the autoencoder. A processor initiates control of an apparatus using the forward prediction.

Abstract: In various examples there is an apparatus with at least one processor and a memory storing instructions that, when executed by the at least one processor, perform a method for recognizing an action of a user. The method comprises accessing at least one stream of pose data derived from captured sensor data depicting the user; sending the pose data to a machine learning system having been trained to recognize actions from pose data; and receiving at least one recognized action from the machine learning system.

Abstract: A computing device, including a processor configured to receive a first video including a plurality of frames. For each frame, the processor may determine that a target region of the frame includes a target object. The processor may determine a surrounding region within which the target region is located. The surrounding region may be smaller than the frame. The processor may identify one or more features located in the surrounding region. From the one or more features, the processor may generate one or more manipulated object identifiers. For each of a plurality of pairs of frames, the processor may determine a respective manipulated object movement between a first manipulated object identifier of the first frame and a second manipulated object identifier of the second frame. The processor may classify at least one action performed in the first video based on the plurality of manipulated object movements.

Abstract: A data processing system is provided that includes a processor having associated memory, the processor being configured to execute instructions using portions of the memory to cause the processor to, at classification time, receive an input image frame from an image source. The input image frame includes an articulated object and a target object. The processor is further caused to process the input image frame using a trained neural network configured to, for each input cell of a plurality of input cells in the input image frame predict a three-dimensional articulated object pose of the articulated object and a three-dimensional target object pose of the target object relative to the input cell. The processor is further caused to output the three-dimensional articulated object pose and the three-dimensional target object pose from the neural network.

Abstract: An apparatus for detecting pose of an object is described. The apparatus has a processor configured to receive captured sensor data depicting the object. The apparatus has a memory storing a model of a class of object of which the depicted object is a member, the model comprising a plurality of parameters specifying the pose, comprising global position and global orientation, of the model. The processor is configured to compute values of the parameters of the model by calculating an optimization to fit the model to the captured sensor data, wherein the optimization comprises iterated computation of updates to the values of the parameters and updates to values of variables representing correspondences between the captured sensor data and the model, the updates being interdependent in computation. The processor is configured to discard updates to values of the variables representing correspondences without applying the updates.

Abstract: A control system comprises a memory storing a sequence of sensor data received from one or more sensors. The control system has a processor which processes the sensor data to compute a sequence of derived sensor data values. An autoencoder receives the sequence of derived sensor data values and computes a forward prediction of the sequence of derived sensor data values, the autoencoder having been trained imposing a relationship on positions of the derived sensor data values encoded in a latent space of the autoencoder. A processor initiates control of an apparatus using the forward prediction.

Abstract: Examples are disclosed that relate to representing recorded hand motion. One example provides a computing device comprising instructions executable by a logic subsystem to receive video data capturing hand motion relative to an object, determine a first pose of the object, and associate a first coordinate system with the object based on the first pose. The instructions are further executable to determine a representation of the hand motion in the first coordinate system, the representation having a time-varying pose relative to the first pose of the object, and configure the representation for display relative to a second instance of the object having a second pose in a second coordinate system, with a time-varying pose relative to the second pose that is spatially consistent with the time-varying pose relative to the first pose.

Abstract: A data processing system is provided that includes a processor having associated memory, the processor being configured to execute instructions using portions of the memory to cause the processor to, at classification time, receive an input image frame from an image source. The input image frame includes an articulated object and a target object. The processor is further caused to process the input image frame using a trained neural network configured to, for each input cell of a plurality of input cells in the input image frame predict a three-dimensional articulated object pose of the articulated object and a three-dimensional target object pose of the target object relative to the input cell. The processor is further caused to output the three-dimensional articulated object pose and the three-dimensional target object pose from the neural network.

Abstract: A computing device, including a processor configured to receive a first video including a plurality of frames. For each frame, the processor may determine that a target region of the frame includes a target object. The processor may determine a surrounding region within which the target region is located. The surrounding region may be smaller than the frame. The processor may identify one or more features located in the surrounding region. From the one or more features, the processor may generate one or more manipulated object identifiers. For each of a plurality of pairs of frames, the processor may determine a respective manipulated object movement between a first manipulated object identifier of the first frame and a second manipulated object identifier of the second frame. The processor may classify at least one action performed in the first video based on the plurality of manipulated object movements.

Abstract: An apparatus for detecting pose of an object is described. The apparatus has a processor configured to receive captured sensor data depicting the object. The apparatus has a memory storing a model of a class of object of which the depicted object is a member, the model comprising a plurality of parameters specifying the pose, comprising global position and global orientation, of the model. The processor is configured to compute values of the parameters of the model by calculating an optimization to fit the model to the captured sensor data, wherein the optimization comprises iterated computation of updates to the values of the parameters and updates to values of variables representing correspondences between the captured sensor data and the model, the updates being interdependent in computation. The processor is configured to discard updates to values of the variables representing correspondences without applying the updates.

Abstract: A system to predict a location of a feature point of an articulated object from a plurality of data points relating to the articulated object of which some possess and some are missing 2D location data. The data points are input into a machine learning model that is trained to predict 2D location data for each feature point of the articulated object that was missing location data.

Abstract: A ground truth engine is described which has a memory holding a plurality of captured images depicting an articulated item. A processor of the engine is configured to access a parameterized, three dimensional (3D) model of the item. An optimizer of the ground truth engine is configured to compute ground truth values of the parameters of the 3D model for individual ones of the captured images, such that the articulated item depicted in the captured image fits the 3D model, the optimizer configured to take into account feedback data from one or more humans, about accuracy of a plurality of the computed values of the parameters.

Abstract: A ground truth engine is described which has a memory holding a plurality of captured images depicting an articulated item. A processor of the engine is configured to access a parameterized, three dimensional (3D) model of the item. An optimizer of the ground truth engine is configured to compute ground truth values of the parameters of the 3D model for individual ones of the captured images, such that the articulated item depicted in the captured image fits the 3D model, the optimizer configured to take into account feedback data from one or more humans, about accuracy of a plurality of the computed values of the parameters.