Related papers: Multi-Correlation Siamese Transformer Network with…
Feature fusion and similarity computation are two core problems in 3D object tracking, especially for object tracking using sparse and disordered point clouds. Feature fusion could make similarity computing more efficient by including…
Many multi-object tracking (MOT) methods follow the framework of "tracking by detection", which associates the target objects-of-interest based on the detection results. However, due to the separate models for detection and association, the…
Siamese approaches address the visual tracking problem by extracting an appearance template from the current frame, which is used to localize the target in the next frame. In general, this template is linearly combined with the accumulated…
Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed. Unlike classification-based CNNs, deep similarity networks are specifically designed to address the image similarity problem,…
3D single object tracking is a key issue for autonomous following robot, where the robot should robustly track and accurately localize the target for efficient following. In this paper, we propose a 3D tracking method called 3D-SiamRPN…
Siamese visual trackers have recently advanced through increasingly sophisticated fusion mechanisms built on convolutional or Transformer architectures. However, both struggle to deliver pixel-level interactions efficiently on…
In this work, we propose a novel staged depthwise correlation and feature fusion network, named DCFFNet, to further optimize the feature extraction for visual tracking. We build our deep tracker upon a siamese network architecture, which is…
In this paper, we propose a novel on-line visual tracking framework based on the Siamese matching network and meta-learner network, which run at real-time speeds. Conventional deep convolutional feature-based discriminative visual tracking…
Tracking a target of interest in both sparse and crowded environments is a challenging problem, not yet successfully addressed in the literature. In this paper, we propose a new long-term visual tracking algorithm, learning discriminative…
In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in the current search point cloud given a template point cloud. Motivated by the success of transformers, we propose Point Tracking…
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.…
Single Object Tracking in LiDAR point cloud is one of the most essential parts of environmental perception, in which small objects are inevitable in real-world scenarios and will bring a significant barrier to the accurate location.…
The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the computational…
Siamese network based trackers develop rapidly in the field of visual object tracking in recent years. The majority of siamese network based trackers now in use treat each channel in the feature maps generated by the backbone network…
Siamese network based trackers formulate tracking as convolutional feature cross-correlation between target template and searching region. However, Siamese trackers still have accuracy gap compared with state-of-the-art algorithms and they…
LiDAR-based 3D single object tracking is a challenging issue in robotics and autonomous driving. Currently, existing approaches usually suffer from the problem that objects at long distance often have very sparse or partially-occluded point…
Point clouds are challenging to process due to their sparsity, therefore autonomous vehicles rely more on appearance attributes than pure geometric features. However, 3D LIDAR perception can provide crucial information for urban navigation…
In this paper, we study the challenging problem of multi-object tracking in a complex scene captured by a single camera. Different from the existing tracklet association-based tracking methods, we propose a novel and efficient way to obtain…
3D Single Object Tracking (SOT) stands a forefront task of computer vision, proving essential for applications like autonomous driving. Sparse and occluded data in scene point clouds introduce variations in the appearance of tracked…
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…