Compared with previous two-stream trackers, the recent one-stream tracking pipeline, which
allows earlier interaction between the template and search region, has achieved a …

Flow-based propagation and spatiotemporal Transformer are two mainstream mechanisms
in video inpainting (VI). Despite the effectiveness of these components, they still suffer from …

The landscape of image generation has been forever changed by open vocabulary diffusion
models. However, at their core these models use transformers, which makes generation …

While transformers have begun to dominate many tasks in vision, applying them to large
images is still computationally difficult. A large reason for this is that self-attention scales …

Although vision transformers (ViTs) have shown promising results in various computer vision
tasks recently, their high computational cost limits their practical applications. Previous …

DETR-like models have significantly boosted the performance of detectors and even
outperformed classical convolutional models. However, all tokens are treated equally …

Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs
more efficient by removing redundant information in the processed tokens. While different …

High-resolution images enable neural networks to learn richer visual representations.
However, this improved performance comes at the cost of growing computational …

Recently, the vision transformer and its variants have played an increasingly important role
in both monocular and multi-view human pose estimation. Considering image patches as …

Token compression aims to speed up large-scale vision transformers (eg ViTs) by pruning
(dropping) or merging tokens. It is an important but challenging task. Although recent …