We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR
point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant …

Very recently, a variety of vision transformer architectures for dense prediction tasks have
been proposed and they show that the design of spatial attention is critical to their success in …

For years, the YOLO series has been the de facto industry-level standard for efficient object
detection. The YOLO community has prospered overwhelmingly to enrich its use in a …

BiSeNet has been proved to be a popular two-stream network for real-time segmentation.
However, its principle of adding an extra path to encode spatial information is time-consuming, …

There is a great desire to develop the high-efficient anodes materials for Li batteries, which
require not only large capacity but also high stability and mobility. In this work, the …

Using a structural search method in combination with first-principles calculations, we found
lots of low energy 2D carbon allotropes and examined all possible Dirac points around their …

Background The presence of COVID-19 in low-and middle-income countries (LMICs) is raising
important concerns about effective pandemic response and preparedness in the context …

We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and
propose the SegViT. Previous ViT-based segmentation networks usually learn a pixel-level …

Transition metal chalcogenides have attracted considerable attention for the further
development of nanoscale devices, however low carrier mobility seriously prevents its further …

Weakly Supervised Semantic Segmentation (WSSS) with image-level annotation uses class
activation maps from the classifier as pseudo-labels for semantic segmentation. However, …