Abstract Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks across different data modalities. A PFM (eg, BERT, ChatGPT, GPT-4) is …

Abstract Transformers are Deep Neural Networks (DNN) that utilize a self-attention
mechanism to capture contextual relationships within sequential data. Unlike traditional …

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 …

Lidar-based sensing drives current autonomous vehicles. Despite rapid progress, current
Lidar sensors still lag two decades behind traditional color cameras in terms of resolution …

LiDAR-camera fusion methods have shown impressive performance in 3D object detection.
Recent advanced multi-modal methods mainly perform global fusion, where image features …

Query-based transformer has shown great potential in constructing long-range attention in
many image-domain tasks, but has rarely been considered in LiDAR-based 3D object …

Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is
a fundamental problem in 3D perception. Compared with the customized sparse …

Methods for 3D lane detection have been recently proposed to address the issue of
inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.) …

Autonomous driving, in recent years, has been receiving increasing attention for its potential
to relieve drivers' burdens and improve the safety of driving. In modern autonomous driving …

Transformer, as an alternative to CNN, has been proven effective in many modalities (eg,
texts and images). For 3D point cloud transformers, existing efforts focus primarily on …