This chapter introduces visual object tracking (VOT), a core task in computer vision that involves continuously locating a target across video frames. It begins by defining the tracking objective and highlighting its importance in real-world applications such as surveillance, autonomous driving, robotics, and healthcare. The chapter then outlines key challenges faced in VOT, including deformation, occlusion, scale variation, motion blur, illumination changes, and background clutter. Following this, it categorizes tracking methods based on single and multi-modal data inputs, including RGB, thermal, LiDAR, event-based sensors, and combinations such as RGB-LiDAR or RGB language. Each modality is analyzed in terms of its strengths, weaknesses, and application contexts. Finally, the chapter emphasizes the growing importance of multi-modal fusion in enhancing robustness and adaptability under complex environmental conditions. Structured around concept definition, challenge identification, and modality-based method analysis, this chapter provides foundational knowledge for designing resilient tracking systems.