LiDAR-based 3D point cloud recognition has benefited various applications. Without
specially considering the LiDAR point distribution, most current methods suffer from …

Abstract 3D point cloud segmentation has made tremendous progress in recent years. Most
current methods focus on aggregating local features, but fail to directly model long-range …

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 …

Capsule networks emerged as a promising alternative to convolutional neural networks for
learning object-centric representations. The idea is to explicitly model part-whole hierarchies …

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 …

While local-window self-attention performs notably in vision tasks, it suffers from limited
receptive field and weak modeling capability issues. This is mainly because it performs self …

Recent advances in image editing techniques have posed serious challenges to the
trustworthiness of multimedia data, which drives the research of image tampering detection …

Recently, transformer-based methods have dominated 3D instance segmentation, where
mask attention is commonly involved. Specifically, object queries are guided by the initial …

Recently, learned image compression methods have outperformed traditional hand-crafted
ones including BPG. One of the keys to this success is learned entropy models that estimate …

The quadratic computational complexity to the number of tokens limits the practical
applications of Vision Transformers (ViTs). Several works propose to prune redundant …