We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the
memory and computational cost, existing point-based pipelines usually adopt task-agnostic …

Visual semantic segmentation aims at separating a visual sample into diverse blocks with
specific semantic attributes and identifying the category for each block, and it plays a crucial …

Few-shot learning is an important and challenging research topic for remote sensing image
scene classification. Many existing approaches address this challenge by using meta …

We present RoReg, a novel point cloud registration framework that fully exploits oriented
descriptors and estimated local rotations in the whole registration pipeline. Previous …

Recent advancements in vision foundation models (VFMs) have opened up new
possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a …

Although various 3D datasets with different functions and scales have been proposed
recently, it remains challenging for individuals to complete the whole pipeline of large-scale …

Recently, several attempts have demonstrated that 3D deep learning models are as
vulnerable to adversarial example attacks as 2D models. However, these methods are still …

This work presents FG-Net, a general deep learning framework for large-scale point cloud
understanding without voxelizations, which achieves accurate and real-time performance …

Due to the extensive use and evolution in the cyber world, different network attacks have
recently increased significantly. Distributed Denial-of-Service (DDoS) attack has become …

Abstract Domain adaptation is critical for success when confronting with the lack of
annotations in a new domain. As the huge time consumption of labeling process on 3D point …