← Search

Zedong Li

2 accepted papers

2025

PNetGPT: Proprietary Protocol Network Traffic Generation with Pre-trained Transformer

ICASSP 2025accepted

Generative pre-trained transformers are exceedingly effective as generative models and classifiers, widely used in natural language processing and computer vision. This work contributes to the exploration of generative pre-trained transformer-based models in the proprietary protocol network traffic.…

Cited by 0SourceScholar
2025

SMSTracker: Tri-path Score Mask Sigma Fusion for Multi-Modal Tracking

ICCV 2025poster

Multi-modal object tracking has emerged as a significant research focus in computer vision due to its robustness in complex environments, such as exposure variations, blur, and occlusions. Despite existing studies integrating supplementary modal information into pre-trained RGB trackers through visu…