Peishan Cong

ShanghaiTech University

Papers

3

Total Citations

17

H-Index

2

About

Peishan Cong is pioneering the integration of 3D vision and natural language for real-world, dynamic environments. Her research centers on two transformative areas: non-intrusive biometric identification and multi-modal 3D scene understanding. Cong’s seminal work on LiDAR-based gait recognition, published in 2022, demonstrates how single-sensor depth data can reliably identify individuals by their walking patterns, achieving 10 citations and laying the groundwork for privacy-preserving security and healthcare monitoring. More recently, she introduced **WildRefer**, a groundbreaking framework for 3D object localization in large-scale, dynamic scenes using natural language descriptions alongside multi-modal data (2D images and 3D LiDAR point clouds). This work, presented in 2023 and 2024, tackles the immense challenge of grounding objects in unconstrained outdoor settings, earning a combined 7 citations. By fusing rich appearance cues from images with precise spatial information from LiDAR, Cong enables machines to understand complex environments through human-like queries. Her contributions are vital for advancing autonomous navigation, augmented reality, and interactive AI systems, positioning her as a rising leader in embodied vision and language-guided perception.

Research Focus

Key Achievements

2
H-Index
3
Papers
17
Total Citations
6
Avg Citations/Paper
🏆 Most Cited Paper
Gait Recognition in Large-scale Free Environment via Single LiDAR
10 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 12
🏛 Institutions: ShanghaiTech University

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago