Abstract: Systems and methods for multi-task joint training of a neural network including an encoder module and a multi-headed attention mechanism are provided. In one aspect, the system includes a processor configured to receive input data including a first set of labels and a second set of labels. Using the encoder module, features are extracted from the input data. Using a multi-headed attention mechanism, training loss metrics are computed. A first training loss metric is computed using the extracted features and the first set of labels, and a second training loss metric is computed using the extracted features and the second set of labels. A first mask is applied to filter the first training loss metric, and a second mask is applied to filter the second training loss metric. A final training loss metric is computed based on the filtered first and second training loss metrics.

Abstract: A dolly zoom effect can be applied to one or more images captured via a resource-constrained device (e.g., a mobile smartphone) by manipulating the size of a target feature while the background in the one or more images changes due to physical movement of the resource-constrained device. The target feature can be detected using facial recognition or shape detection techniques. The target feature can be resized before the size is manipulated as the background changes (e.g., changes perspective).

Abstract: A sensorless collision detection method of robotic arm based on motor current includes acquiring an output current of a robotic arm joint motor; building a neural network, and using a backpropagation algorithm to update the weights and the deviations of the neural network to obtain an estimated current value; judging whether collision occurs by comparing the collision detection threshold with the error value between the output current of the robotic arm joint motor and the estimated output current of the neural network. The detection method is easy to operate and has higher universality.