A Deep Dive into Generic Object Tracking: A Survey

TL;DR

This survey comprehensively reviews the evolution of generic object tracking methods, emphasizing recent transformer-based approaches, analyzing their core principles, limitations, and benchmarking progress in the field.

Contribution

It provides a unified categorization, visual comparison, and analysis of all major tracking paradigms, with a focus on the rapidly advancing transformer-based methods.

Findings

Transformer-based trackers show significant improvements in robustness.

Unified comparison highlights strengths and limitations of different paradigms.

The field is rapidly evolving with new benchmarks and methods.

Abstract

Generic object tracking remains an important yet challenging task in computer vision due to complex spatio-temporal dynamics, especially in the presence of occlusions, similar distractors, and appearance variations. Over the past two decades, a wide range of tracking paradigms, including Siamese-based trackers, discriminative trackers, and, more recently, prominent transformer-based approaches, have been introduced to address these challenges. While a few existing survey papers in this field have either concentrated on a single category or widely covered multiple ones to capture progress, our paper presents a comprehensive review of all three categories, with particular emphasis on the rapidly evolving transformer-based methods. We analyze the core design principles, innovations, and limitations of each approach through both qualitative and quantitative comparisons. Our study introduces a novel categorization and offers a unified visual and tabular comparison of representative methods. Additionally, we organize existing trackers from multiple perspectives and summarize the major evaluation benchmarks, highlighting the fast-paced advancements in transformer-based tracking driven by their robust spatio-temporal modeling capabilities.