Transformer 是一种基于自注意力机制, 并行化处理数据的深度神经网络. 近几年基于
Transformer 的模型成为计算机视觉任务的重要研究方向. 针对目前国内基于Transformer …

Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a
traffic sign with high-level semantics, whereas it owns the specific local pattern which needs …

Existing state-of-the-art saliency detection methods heavily rely on CNN-based
architectures. Alternatively, we rethink this task from a convolution-free sequence-to …

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with
an encoder-decoder architecture. The encoder progressively reduces the spatial resolution …

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 …

This paper presents a novel parametric curve-based method for lane detection in RGB
images. Unlike state-of-the-art segmentation-based and point detection-based methods that …

Vectorized high-definition map online construction has garnered considerable attention in
the field of autonomous driving research. Most existing approaches model changeable map …

High-definition (HD) map provides abundant and precise environmental information of the
driving scene, serving as a fundamental and indispensable component for planning in …

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 …

Vectorized high-definition map (HD-map) construction, which focuses on the perception of
centimeter-level environmental information, has attracted significant research interest in the …