Kai Li

Orcid: 0000-0001-7161-434X

Affiliations:
  • University of Chinese Academy of Sciences, School of Electronic, Electrical and Communication Engineering, Beijing, China
  • City University of Hong Kong, School of Data Science, Hong Kong


According to our database1, Kai Li authored at least 10 papers between 2024 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
DragOSM: Extract Building Roofs and Footprints from Aerial Images by Aligning Historical Labels.
CoRR, September, 2025

IRSAMap:Towards Large-Scale, High-Resolution Land Cover Map Vectorization.
CoRR, August, 2025

LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text.
CoRR, March, 2025

SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion.
CoRR, February, 2025

PCP: A Prompt-Based Cartographic-Level Polygonal Vector Extraction Framework for Remote Sensing Images.
IEEE Trans. Geosci. Remote. Sens., 2025

IRSAMap: Toward Large-Scale, High-Resolution Land Cover Map Vectorization.
IEEE Trans. Geosci. Remote. Sens., 2025

PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Images.
IEEE Trans. Geosci. Remote. Sens., 2025

CuSMer: Multimodal Intent Recognition in Customer Service via Data Augment and LLM Merge.
Proceedings of the Companion Proceedings of the ACM on Web Conference 2025, 2025

2024
Prompt-Driven Building Footprint Extraction in Aerial Images With Offset-Building Model.
IEEE Trans. Geosci. Remote. Sens., 2024

Extracting polygonal footprints in off-nadir images with Segment Anything Model.
CoRR, 2024


  Loading...