Xiaotao Liu

Papers

Total Citations

H-Index

About

Xiaotao Liu is a leading researcher in computer vision, with a primary focus on RGBT tracking—a critical technology for robotics, surveillance, and autonomous driving. His work addresses the fundamental challenge of fusing visible (RGB) and thermal (T) modalities to achieve robust object tracking under adverse conditions like low light or occlusion. Liu’s major contribution is the development of the "Temporal Adaptive RGBT Tracking with Modality Prompt" (2024), which has already garnered 61 citations. This innovative framework moves beyond conventional spatial-matching approaches by introducing temporal adaptation and modality prompts, enabling the tracker to dynamically leverage complementary visual and thermal cues over time. By tackling the limitations of appearance-based matching, Liu’s work significantly enhances tracking reliability in real-world scenarios. His research not only advances the theoretical understanding of multi-modal fusion but also offers practical solutions for high-stakes applications. With a growing citation impact, Xiaotao Liu is recognized as a rising authority in intelligent tracking systems, pushing the boundaries of how machines perceive and follow objects across challenging environments.