publié le: 2023
We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel train...
Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Advers...
In this survey, we present a systematic review of 3D hand pose estimation from the perspective of efficient annotation and learning. 3D hand pose esti...
Model filter pruning has shown efficiency in compressing deep convolutional neural networks by removing unimportant filters without sacrificing the pe...
Predicting future actions is an essential feature of intelligent systems and embodied AI. However, compared to the traditional recognition tasks, the...
