Leyuan Xing — accepted AI-conference papers

2026

TACO: Task-Aware Contrastive Learning for Joint LiDAR Localization and 3D Object Detection

Leyuan Xing, Huanjia Zhang, Dongyu Pan, Hai Wu, Qiming Xia, Kezheng Xiong +3

CVPR 2026

Reliable navigation and decision-making of autonomous vehicles require both accurate localization and object detection. Traditionally, these two tasks are handled separately, leading to redundant computation and limited cross-task knowledge transfer. This paper proposes TACO, the first Task-Aware CO

Cited by 0 Source ↗code ↗Scholar ↗

2024

HINTED: Hard Instance Enhanced Detector with Mixed-Density Feature Fusion for Sparsely-Supervised 3D Object Detection

Qiming Xia, Wei Ye, Hai Wu, Shijia Zhao, Leyuan Xing, Xun Huang +4

CVPR 2024poster

Current sparsely-supervised object detection methods largely depend on high threshold settings to derive high-quality pseudo labels from detector predictions. However hard instances within point clouds frequently display incomplete structures causing decreased confidence scores in their assigned pse…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗