This chapter focuses on multi-modal visual object tracking (VOT), exploring the integration of different data modalities such as RGB, depth, thermal, LiDAR, and language to enhance tracking robustness in complex environments. Multi-modal VOT is vital for intelligent systems operating under challenging conditions, including low light and occlusions. The chapter introduces key fusion strategies—early, mid-level, and late fusion—detailing their mechanisms, benefits, and trade-offs. It systematically categorizes tracking methods by modality pairings and fusion stages, analyzing their applications in indoor, outdoor, and cross-modal scenarios. Experimental comparisons are presented to illustrate performance differences. Additionally, the chapter identifies major challenges in the field, such as high computational costs, feature misalignment, limited data availability, and poor cross-domain transferability. The chapter concludes by outlining future research directions aimed at improving efficiency, adaptability, and generalization. Through comprehensive analysis and structured exposition, this chapter offers essential insights for advancing robust and versatile multi-modal tracking systems.