Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals

Abstract

Recently, deep learning has achieved great success in visual tracking tasks, particularly in single-object tracking. This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based on deep learning. First, we introduce basic knowledge of deep visual tracking, including fundamental concepts, existing algorithms, and previous reviews. Second, we briefly review existing deep learning methods by categorizing them into data-invariant and data-adaptive methods based on whether they can dynamically change their model parameters or architectures. Then, we conclude with the general components of deep trackers. In this way, we systematically analyze the novelties of several recently proposed deep trackers. Thereafter, popular datasets such as Object Tracking Benchmark (OTB) and Visual Object Tracking (VOT) are discussed, along with the performances of several deep trackers. Finally, based on observations and experimental results, we discuss three different characteristics of deep trackers, i.e., the relationships between their general components, exploration of more effective tracking frameworks, and interpretability of their motion estimation components.

Generalisation and reliability of deep learning for digital pathology in a clinical setting

“…The core objective of DL research is to develop systems capable of learning intricate patterns from data and executing tasks with minimal human intervention. This spectrum of tasks encompasses diverse applications, ranging from automatic speech recognition [91] and multilingual text translation [105] to object tracking in videos [146] and analysis of medical imaging for disease diagnosis [85].…”

Causal Reasoning Meets Visual Representation Learning: A Prospective Study

“…Yang et al [134] proposed a cross-modal relationship extractor (CMRE) to adaptively highlight objects and relationships with a cross-modal attention mechanism, and represented the extracted information as a language-guided visual relation graph. Furthermore, Yang et al [22] proposed a cross-modal relationship extractor to adaptively highlight objects and relationships (spatial and semantic relations) related to the given expression with a cross-modal attention mechanism, and represent the extracted information as a language-guided visual relation graph. Yang et al [150] proposed a scene graph-guided modular network (SGMN), which performed reasoning over a semantic graph and a scene graph with neural modules under the guidance of the linguistic structure of the expression.…”

Improved DeepSORT-Based Object Tracking in Foggy Weather for AVs Using Sematic Labels and Fused Appearance Feature Network

“…Object tracking is constantly determining a moving objectʹs trajectory from measurements taken by one or more sensors [1]. Single-object tracking (SOT) [2] and Multi-object tracking (MOT) [3][4][5][6][7] are two main categories of object tracking methods (MOT). When using SOT, the tracker follows a single, predetermined object.…”