Abstract: Methods, systems, and computer-readable media for multi-model processing on resource-constrained devices. A resource-constrained device can determine, based on a battery-life for a battery of the device, whether to process input through a first model or a second model. The first model can be a gating model that is more energy efficient to execute, and the second model can be a main model that is more accurate than the gating model. Depending on the current battery-life and/or other criteria, the system can process, through the gating model, sensor input that can record activity performed by a user of the resource-constrained device. If the gating model predicts an activity performed by the user that is recorded by the sensor data, the device can process the same or additional input through the main model. Overall power consumption can be reduced with a minimum accuracy maintained over processing input only through the main model.

Abstract: Systems and methods for training a restoration model can leverage training for two sub-tasks to train the restoration model to generate realistic and identity-preserved outputs. The systems and methods can balance the training of the generation task and the reconstruction task to ensure the generated outputs preserve the identity of the original subject while generating realistic outputs. The systems and methods can further leverage a feature quantization model and skip connections to improve the model output and overall training.

Abstract: Methods, systems, and computer-readable media for multi-model processing on resource-constrained devices. A resource-constrained device can determine, based on a battery-life for a battery of the device, whether to process input through a first model or a second model. The first model can be a gating model that is more energy efficient to execute, and the second model can be a main model that is more accurate than the gating model. Depending on the current battery-life and/or other criteria, the system can process, through the gating model, sensor input that can record activity performed by a user of the resource-constrained device. If the gating model predicts an activity performed by the user that is recorded by the sensor data, the device can process the same or additional input through the main model. Overall power consumption can be reduced with a minimum accuracy maintained over processing input only through the main model.

Abstract: Methods, systems, and computer-readable media for multi-model processing on resource-constrained devices. A resource-constrained device can determine, based on a battery-life for a battery of the device, whether to process input through a first model or a second model. The first model can be a gating model that is more energy efficient to execute, and the second model can be a main model that is more accurate than the gating model. Depending on the current battery-life and/or other criteria, the system can process, through the gating model, sensor input that can record activity performed by a user of the resource-constrained device. If the gating model predicts an activity performed by the user that is recorded by the sensor data, the device can process the same or additional input through the main model. Overall power consumption can be reduced with a minimum accuracy maintained over processing input only through the main model.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving one or more data streams captured by one or more sensors sensing a candidate face. In a plurality of stages that each comprises a different analysis, one or more of the data streams are analyzed, and the stages comprise determining whether a plurality of candidate face depth points lies on a single flat plane or a curving plane. Based at least in part on determining that the plurality of candidate face depth points lies on the single flat plane, an indication of the false representation of the human face is outputted.

Abstract: Examples are disclosed herein that relate to detecting spoofed human faces. One example provides a computing device comprising a processor configured to compute a first feature distance between registered image data of a human face in a first spectral region and test image data of the human face in the first spectral region, compute a second feature distance between the registered image data and test image data of the human face in a second spectral region, compute a test feature distance between the test image data in the first spectral region and the test image data in the second spectral region, determine, based on a predetermined relationship, whether the human face to which the test image data in the first and second spectral regions corresponds is a real human face or a spoofed human face, and modify a behavior of the computing device.

Abstract: A technique for multi-camera object tracking is disclosed that preserves privacy of imagery from each camera or group of cameras. This technique uses secure multi-party computation to compute a distance metric across data from multiple cameras without revealing any information to operators of the cameras except whether or not an object was observed by both cameras. This is achieved by a distance metric learning technique that reduces the computing complexity of secure computation while maintaining object identification accuracy.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving one or more data streams captured by one or more sensors sensing a candidate face. In a plurality of stages that each comprises a different analysis, one or more of the data streams are analyzed, and the stages comprise determining whether a plurality of candidate face depth points lies on a single flat plane or a curving plane. Based at least in part on determining that the plurality of candidate face depth points lies on the single flat plane, an indication of the false representation of the human face is outputted.

Abstract: Examples are disclosed herein that relate to detecting spoofed human faces. One example provides a computing device comprising a processor configured to compute a first feature distance between registered image data of a human face in a first spectral region and test image data of the human face in the first spectral region, compute a second feature distance between the registered image data and test image data of the human face in a second spectral region, compute a test feature distance between the test image data in the first spectral region and the test image data in the second spectral region, determine, based on a predetermined relationship, whether the human face to which the test image data in the first and second spectral regions corresponds is a real human face or a spoofed human face, and modify a behavior of the computing device.

Abstract: A technique for multi-camera object tracking is disclosed that preserves privacy of imagery from each camera or group of cameras. This technique uses secure multi-party computation to compute a distance metric across data from multiple cameras without revealing any information to operators of the cameras except whether or not an object was observed by both cameras. This is achieved by a distance metric learning technique that reduces the computing complexity of secure computation while maintaining object identification accuracy.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving a plurality of different data streams captured by a respective plurality of sensors of differing sensor types sensing a candidate face. In a cascading plurality of stages, one or more of the different data streams are analyzed, wherein each of the stages comprises a different analysis. In one of the cascading plurality of stages, the method determines that one or more of the different data streams corresponds to a false representation of the human face. Based on determining that one or more of the different data streams corresponds to a false representation of a human face, an indication of the false representation is outputted.

Abstract: A technique for multi-camera object tracking is disclosed that preserves privacy of imagery from each camera or group of cameras. This technique uses secure multi-party computation to compute a distance metric across data from multiple cameras without revealing any information to operators of the cameras except whether or not an object was observed by both cameras. This is achieved by a distance metric learning technique that reduces the computing complexity of secure computation while maintaining object identification accuracy.

Abstract: Examples are disclosed herein that relate to eye tracking based on two-dimensional image data. One example provides, on a computing device, a method of tracking an eye. The method includes receiving image data from an image sensor, detecting a face of the user in the image data, locating the eye in a region of the face in the image data to obtain an eye image, normalizing one or more of a scale and an illumination of the eye image, fitting an ellipse to an iris of the eye in the eye image, and outputting a determination of an eye gaze direction based upon the ellipse fitted.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving a plurality of different data streams captured by a respective plurality of sensors of differing sensor types sensing a candidate face. In a cascading plurality of stages, one or more of the different data streams are analyzed, wherein each of the stages comprises a different analysis. In one of the cascading plurality of stages, the method determines that one or more of the different data streams corresponds to a false representation of the human face. Based on determining that one or more of the different data streams corresponds to a false representation of a human face, an indication of the false representation is outputted.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving a plurality of different data streams captured by a respective plurality of sensors of differing sensor types sensing a candidate face. In a cascading plurality of stages, one or more of the different data streams are analyzed, wherein each of the stages comprises a different analysis. In one of the cascading plurality of stages, the method determines that one or more of the different data streams corresponds to a false representation of the human face. Based on determining that one or more of the different data streams corresponds to a false representation of a human face, an indication of the false representation is outputted.

Abstract: Examples are disclosed herein that relate to eye tracking based on two-dimensional image data. One example provides, on a computing device, a method of tracking an eye. The method includes receiving image data from an image sensor, detecting a face of the user in the image data, locating the eye in a region of the face in the image data to obtain an eye image, normalizing one or more of a scale and an illumination of the eye image, fitting an ellipse to an iris of the eye in the eye image, and outputting a determination of an eye gaze direction based upon the ellipse fitted.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving a plurality of different data streams captured by a respective plurality of sensors of differing sensor types sensing a candidate face. In a cascading plurality of stages, one or more of the different data streams are analyzed, wherein each of the stages comprises a different analysis. In one of the cascading plurality of stages, the method determines that one or more of the different data streams corresponds to a false representation of the human face. Based on determining that one or more of the different data streams corresponds to a false representation of a human face, an indication of the false representation is outputted.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving a plurality of different data streams captured by a respective plurality of sensors of differing sensor types sensing a candidate face. In a cascading plurality of stages, one or more of the different data streams are analyzed, wherein each of the stages comprises a different analysis. In one of the cascading plurality of stages, the method determines that one or more of the different data streams corresponds to a false representation of the human face. Based on determining that one or more of the different data streams corresponds to a false representation of a human face, an indication of the false representation is outputted.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving a plurality of different data streams captured by a respective plurality of sensors of differing sensor types sensing a candidate face. In a cascading plurality of stages, one or more of the different data streams are analyzed, wherein each of the stages comprises a different analysis. In one of the cascading plurality of stages, the method determines that one or more of the different data streams corresponds to a false representation of the human face. Based on determining that one or more of the different data streams corresponds to a false representation of a human face, an indication of the false representation is outputted.

Abstract: Machine learning may be personalized to individual users of computing devices, and can be used to increase machine learning prediction accuracy and speed, and/or reduce memory footprint. Personalizing machine learning can include hosting, by a computing device, a consensus machine learning model and collecting information, locally by the computing device, associated with an application executed by the client device. Personalizing machine learning can also include modifying the consensus machine learning model accessible by the application based, at least in part, on the information collected locally by the client device. Modifying the consensus machine learning model can generate a personalized machine learning model. Personalizing machine learning can also include transmitting the personalized machine learning model to a server that updates the consensus machine learning model.