Related papers: Hard Negative Samples Emphasis Tracker without Anc…
This survey presents a deep analysis of the learning and inference capabilities in nine popular trackers. It is neither intended to study the whole literature nor is it an attempt to review all kinds of neural networks proposed for visual…
Achieving state-of-the-art results in face verification systems typically hinges on the availability of labeled face training data, a resource that often proves challenging to acquire in substantial quantities. In this research endeavor, we…
Siamese network has been a de facto benchmark framework for 3D LiDAR object tracking with a shared-parametric encoder extracting features from template and search region, respectively. This paradigm relies heavily on an additional matching…
Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference…
In recent years, Siamese network based trackers have significantly advanced the state-of-the-art in real-time tracking. Despite their success, Siamese trackers tend to suffer from high memory costs, which restrict their applicability to…
Most of the existing trackers usually rely on either a multi-scale searching scheme or pre-defined anchor boxes to accurately estimate the scale and aspect ratio of a target. Unfortunately, they typically call for tedious and heuristic…
In this paper, we present a novel siamese motion-aware network (SiamMan) for visual tracking, which consists of the siamese feature extraction subnetwork, followed by the classification, regression, and localization branches in parallel.…
In the same vein of discriminative one-shot learning, Siamese networks allow recognizing an object from a single exemplar with the same class label. However, they do not take advantage of the underlying structure of the data and the…
Siamese network based trackers formulate the visual tracking task as a similarity matching problem. Almost all popular Siamese trackers realize the similarity learning via convolutional feature cross-correlation between a target branch and…
Despite the eye-catching breakthroughs achieved by deep visual networks in detecting region-level surface defects, the challenge of high-quality pixel-wise defect detection remains due to diverse defect appearances and data scarcity. To…
Trackers that follow Siamese paradigm utilize similarity matching between template and search region features for tracking. Many methods have been explored to enhance tracking performance by incorporating tracking history to better handle…
Multi-object tracking has recently become an important area of computer vision, especially for Advanced Driver Assistance Systems (ADAS). Despite growing attention, achieving high performance tracking is still challenging, with…
The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotations…
Recently, the Siamese-based method has stood out from multitudinous tracking methods owing to its state-of-the-art (SOTA) performance. Nevertheless, due to various special challenges in UAV tracking, \textit{e.g.}, severe occlusion and fast…
Similarity matching is a core operation in Siamese trackers. Most Siamese trackers carry out similarity learning via cross correlation that originates from the image matching field. However, unlike 2-D image matching, the matching network…
Existing deep trackers mainly use convolutional neural networks pre-trained for generic object recognition task for representations. Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep…
Visual tracking problem demands to efficiently perform robust classification and accurate target state estimation over a given target at the same time. Former methods have proposed various ways of target state estimation, yet few of them…
Vehicle tracking task plays an important role on the internet of vehicles and intelligent transportation system. Beyond the traditional GPS sensor, the image sensor can capture different kinds of vehicles, analyze their driving situation…
In contrast to fully-supervised models, self-supervised representation learning only needs a fraction of data to be labeled and often achieves the same or even higher downstream performance. The goal is to pre-train deep neural networks on…
The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object's appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only…