Transformer, first applied to the field of natural language processing, is a type of deep neural
network mainly based on the self-attention mechanism. Thanks to its strong representation …

We present a new method, called MEsh TRansfOrmer (METRO), to reconstruct 3D human
pose and mesh vertices from a single image. Our method uses a transformer encoder to …

In this paper, we present a neat yet effective transformer-based framework for visual
grounding, namely TransVG, to address the task of grounding a language query to the …

Most existing Siamese-based tracking methods execute the classification and regression of
the target object based on the similarity maps. However, they either employ a single map …

The field of vision-based human hand three-dimensional (3D) shape and pose estimation
has attracted significant attention recently owing to its key role in various applications, such …

While CNN-based models have made remarkable progress on human pose estimation,
what spatial dependencies they capture to localize keypoints remains unclear. In this work …

Transformer, first applied to the field of natural language processing, is a type of deep neural
network mainly based on the self-attention mechanism. Thanks to its strong representation …

As the size of transformer-based models continues to grow, fine-tuning these large-scale
pretrained vision models for new tasks has become increasingly parameter-intensive …

Hands are often severely occluded by objects, which makes 3D hand mesh estimation
challenging. Previous works often have disregarded information at occluded regions …

Quantization is one of the most effective methods to compress neural networks, which has
achieved great success on convolutional neural networks (CNNs). Recently, vision …