Interactive image segmentation aims at obtaining a segmentation mask for an image using simple user annotations.
Single view-based reconstruction of hand-object interaction is challenging due to the severe observation missing caused by occlusions.
In our technique, the motion of visible regions is first estimated and combined with temporal information to infer the motion of the occluded regions through an LSTM-involved graph neural network.
In this paper, we propose a novel geometric-based approach called Tangent Attack (TA), which identifies an optimal tangent point of a virtual hemisphere located on the decision boundary to reduce the distortion of the attack.
The meta-gradients of this loss are then computed and accumulated from multiple tasks to update the Simulator and subsequently improve generalization.