Lingpeng Wang — accepted AI-conference papers

2022

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

Le Hui, Lingpeng Wang, Linghua Tang, Kaihao Lan, Jin Xie, Jian Yang

ECCV 2022poster

"Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area. Due to the large appearance variation between the template and search area during tracking, how to learn the robust cross correlation between them…

Cited by 80 Source ↗PDF ↗code ↗Scholar ↗

2021

3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds

Le Hui, Lingpeng Wang, Mingmei Cheng, Jin Xie, Jian Yang

NeurIPS 2021poster

3D object tracking in point clouds is still a challenging problem due to the sparsity of LiDAR points in dynamic environments. In this work, we propose a Siamese voxel-to-BEV tracker, which can significantly improve the tracking performance in sparse 3D point clouds. Specifically, it consists of a S…

Cited by 93 Source ↗PDF ↗code ↗Scholar ↗