CVMay 16, 2024

Beyond Traditional Single Object Tracking: A Survey

arXiv:2405.10439v11 citationsh-index: 2
Originality Synthesis-oriented
AI Analysis

It addresses the challenging problem of single object tracking for computer vision researchers by synthesizing recent advancements and suggesting future directions, but it is incremental as a survey.

This survey reviews cutting-edge techniques like Sequence Models and Generative Models applied to single object tracking, proposing a novel categorization and comparing their performance on popular benchmarks.

Single object tracking is a vital task of many applications in critical fields. However, it is still considered one of the most challenging vision tasks. In recent years, computer vision, especially object tracking, witnessed the introduction or adoption of many novel techniques, setting new fronts for performance. In this survey, we visit some of the cutting-edge techniques in vision, such as Sequence Models, Generative Models, Self-supervised Learning, Unsupervised Learning, Reinforcement Learning, Meta-Learning, Continual Learning, and Domain Adaptation, focusing on their application in single object tracking. We propose a novel categorization of single object tracking methods based on novel techniques and trends. Also, we conduct a comparative analysis of the performance reported by the methods presented on popular tracking benchmarks. Moreover, we analyze the pros and cons of the presented approaches and present a guide for non-traditional techniques in single object tracking. Finally, we suggest potential avenues for future research in single-object tracking.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes