In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …

Abstract 3D object detectors usually rely on hand-crafted proxies, eg, anchors or centers,
and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be …

This paper is not motivated to seek innovation within the attention mechanism. Instead it
focuses on overcoming the existing trade-offs between accuracy and efficiency within the …

The rapid advancement of deep learning models is often attributed to their ability to leverage
massive training data. In contrast such privilege has not yet fully benefited 3D deep learning …

In the context of autonomous driving the significance of effective feature learning is widely
acknowledged. While conventional 3D self-supervised pre-training methods have shown …

Self-supervised image backbones can be used to address complex 2D tasks (eg semantic
segmentation object discovery) very efficiently and with little or no downstream supervision …

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

Recent advance in 2D CNNs has revealed that large kernels are important. However, when
directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where …

The booming of 3D recognition in the 2020s began with the introduction of point cloud
transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models …

In recent years, collaborative classification of multimodal data, eg, hyperspectral image (HSI)
and light detection and ranging (LiDAR), has been widely used to improve remote sensing …