activity
20242026
most citedFast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Tracking

2 citations · 2 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2026

MatchFusion: Explicit-Implicit Instance Matching for Spatio-Temporal Multimodal Autonomous Driving

Xiaoyu Li, Jiajia Fu, Long Shi +7

Sparse instance representations provide a compact interface for spatial LiDAR-camera and temporal past-current interaction in multimodal perception and E2EAD. Effective interaction…

cs.CV2026

Offline-Poly: A Polyhedral Framework For Offline 3D Multi-Object Tracking

Xiaoyu Li, Yitao Wu, Xian Wu +3

Offline 3D multi-object tracking (MOT) is a critical component of the 4D auto-labeling (4DAL) process. It enhances pseudo-labels generated by high-performance detectors through the…

cs.CV2025

Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception

Xiaoyu Li, Peidong Li, Xian Wu +7

Spatio-temporal alignment is crucial for temporal modeling of end-to-end (E2E) perception in autonomous driving (AD), providing valuable structural and textural prior information.…

cs.CV2024

RockTrack: A 3D Robust Multi-Camera-Ken Multi-Object Tracking Framework

Xiaoyu Li, Peidong Li, Lijun Zhao +5

3D Multi-Object Tracking (MOT) obtains significant performance improvements with the rapid advancements in 3D object detection, particularly in cost-effective multi-camera setups.…

cs.CV2024★ 2 cited

Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Tracking

Xiaoyu Li, Dedong Liu, Yitao Wu +3

3D Multi-Object Tracking (MOT) captures stable and comprehensive motion states of surrounding obstacles, essential for robotic perception. However, current 3D trackers face issues…