no code implementations • 28 Feb 2024 • Zhuoling Li, Xiaogang Xu, SerNam Lim, Hengshuang Zhao
To address these challenges, we build a detector based on the bird's-eye-view (BEV) detection paradigm, where the explicit feature projection is beneficial to addressing the geometry learning ambiguity when employing multiple scenarios of data to train detectors.
no code implementations • 18 Jul 2023 • Zhuoling Li, Chunrui Han, Zheng Ge, Jinrong Yang, En Yu, Haoqian Wang, Hengshuang Zhao, Xiangyu Zhang
Besides, GroupLane with ResNet18 still surpasses PersFormer by 4. 9% F1 score, while the inference speed is nearly 7x faster and the FLOPs is only 13. 3% of it.
1 code implementation • 16 Jun 2023 • Dongming Wu, Fan Jia, Jiahao Chang, Zhuoling Li, Jianjian Sun, Chunrui Han, Shuailin Li, Yingfei Liu, Zheng Ge, Tiancai Wang
We present the 1st-place solution of OpenLane Topology in Autonomous Driving Challenge.
no code implementations • 23 May 2023 • En Yu, Tiancai Wang, Zhuoling Li, Yuang Zhang, Xiangyu Zhang, Wenbing Tao
Although end-to-end multi-object trackers like MOTR enjoy the merits of simplicity, they suffer from the conflict between detection and association seriously, resulting in unsatisfactory convergence dynamics.
1 code implementation • 3 Apr 2023 • Zhuoling Li, Chuanrui Zhang, Wei-Chiu Ma, Yipin Zhou, Linyan Huang, Haoqian Wang, SerNam Lim, Hengshuang Zhao
In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks.
no code implementations • 3 Dec 2022 • En Yu, Songtao Liu, Zhuoling Li, Jinrong Yang, Zeming Li, Shoudong Han, Wenbing Tao
VLM joints the information in the generated visual prompts and the textual prompts from a pre-defined Trackbook to obtain instance-level pseudo textual description, which is domain invariant to different tracking scenes.
no code implementations • 8 Jun 2022 • Zhuoling Li, Chuanrui Zhang, En Yu, Haoqian Wang
(2) Combining depth estimation and 2D object detection is a promising M3OD pre-training baseline.
no code implementations • CVPR 2022 • Zhuoling Li, Zhan Qu, Yang Zhou, Jianzhuang Liu, Haoqian Wang, Lihui Jiang
To tackle this problem, we propose a depth solving system that fully explores the visual clues from the subtasks in M3OD and generates multiple estimations for the depth of each target.
no code implementations • CVPR 2022 • En Yu, Zhuoling Li, Shoudong Han
To this end, we propose a strategy, namely multi-view trajectory contrastive learning, in which each trajectory is represented as a center vector.
1 code implementation • 6 Dec 2021 • Zhuoling Li, Gaowei Zhang, Lingyu Xu, Jie Yu
The model acquires static and dynamic graph matrices from data to model long- and short-term patterns respectively.
no code implementations • 10 May 2021 • En Yu, Zhuoling Li, Shoudong Han, Hongwei Wang
Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID).
no code implementations • 24 Feb 2021 • Zhuoling Li, Haohan Wang, Tymoteusz Swistek, Weixin Chen, Yuanzheng Li, Haoqian Wang
Few-shot learning is challenging due to the limited data and labels.