Regular biography
Hongsheng Li is an Associate Professor (by courtesy) in the Department of Computer Science at The Chinese University of Hong Kong. His research interests include areas related to computer science, though specific details are not provided. Li's profile page can be accessed at https://www.ee.cuhk.edu.hk/en-gb/people/academic-staff/professors/prof-hongsheng-li. Further information about his work and contributions may be found on his official website.
Scholar-generated biography
Hongsheng Li is a researcher at the Chinese University of Hong Kong, specializing in Computer Vision, Multimodal Learning, and Medical Image Analysis. His work focuses on advancing deep learning techniques for image synthesis, 3D object detection, and vision-language modeling. Key contributions include StackGAN for text-to-image synthesis, PointRCNN and PV-RCNN for 3D object detection from point clouds, and CLIP-Adapter for improving vision-language models. His research also explores efficient fine-tuning methods and cross-scene crowd counting. Li's publications highlight innovations in attention mechanisms, domain adaptation, and LiDAR segmentation, emphasizing practical applications in computer vision and multimodal systems.