Abstract: A method for evaluating gesture input comprises receiving input data for sequential data frames, including hand tracking data for hands of a user. A first neural network is trained to recognize features indicative of subsequent gesture interactions and configured to evaluate input data for a sequence of data frames and to output an indication of a likelihood of the user performing gesture interactions during a predetermined window of data frames. A second neural network is trained to recognize features indicative of whether the user is currently performing one or more gesture interactions and configured to adjust parameters for gesture interaction recognition during the predetermined window based on the indicated likelihood. The second neural network evaluates the predetermined window for performed gesture interactions based on the adjusted parameters, and outputs a signal as to whether the user is performing one or more gesture interactions during the predetermined window.

Abstract: A method for evaluating gesture input comprises receiving input data for sequential data frames, including hand tracking data for hands of a user. A first neural network is trained to recognize features indicative of subsequent gesture interactions and configured to evaluate input data for a sequence of data frames and to output an indication of a likelihood of the user performing gesture interactions during a predetermined window of data frames. A second neural network is trained to recognize features indicative of whether the user is currently performing one or more gesture interactions and configured to adjust parameters for gesture interaction recognition during the predetermined window based on the indicated likelihood. The second neural network evaluates the predetermined window for performed gesture interactions based on the adjusted parameters, and outputs a signal as to whether the user is performing one or more gesture interactions during the predetermined window.

Abstract: A method for evaluating gesture input comprises receiving input data for sequential data frames, including hand tracking data for hands of a user. A first neural network is trained to recognize features indicative of subsequent gesture interactions and configured to evaluate input data for a sequence of data frames and to output an indication of a likelihood of the user performing gesture interactions during a predetermined window of data frames. A second neural network is trained to recognize features indicative of whether the user is currently performing one or more gesture interactions and configured to adjust parameters for gesture interaction recognition during the predetermined window based on the indicated likelihood. The second neural network evaluates the predetermined window for performed gesture interactions based on the adjusted parameters, and outputs a signal as to whether the user is performing one or more gesture interactions during the predetermined window.

Abstract: A method for evaluating gesture input comprises receiving input data for sequential data frames, including hand tracking data for hands of a user. A first neural network is trained to recognize features indicative of subsequent gesture interactions and configured to evaluate input data for a sequence of data frames and to output an indication of a likelihood of the user performing gesture interactions during a predetermined window of data frames. A second neural network is trained to recognize features indicative of whether the user is currently performing one or more gesture interactions and configured to adjust parameters for gesture interaction recognition during the predetermined window based on the indicated likelihood. The second neural network evaluates the predetermined window for performed gesture interactions based on the adjusted parameters, and outputs a signal as to whether the user is performing one or more gesture interactions during the predetermined window.

Abstract: Examples are disclosed that relate to computer-based tracking of a process performed by a user. In one example, multi-modal sensor information is received via a plurality of sensors. A world state of a real-world physical environment and a user state in the real-world physical environment are tracked based on the multi-modal sensor information. A process being performed by the user within a working domain is recognized based on the world state and the user state. A current step in the process is detected based on the world state and the user state. Domain-specific instructions directing the user how to perform an expected action are presented via a user interface device. A user action is detected based on the world state and the user state. Based on the user action differing from the expected action, domain-specific guidance to perform the expected action is presented via the user interface device.

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: 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: A method for predicting three-dimensional body poses from image sequences of an object, the method performed on a processor of a computer having memory, the method including the steps of accessing the image sequences from the memory, finding bounding boxes around the object in consecutive frames of the image sequence, compensating motion of the object to form spatio-temporal volumes, and learning a mapping from the spatio-temporal volumes to a three-dimensional body pose in a central frame based on a mapping function.