Related papers: Siamese Instance Search for Tracking
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…
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…
Point cloud-based 3D object tracking is an important task in autonomous driving. Though great advances regarding Siamese-based 3D tracking have been made recently, it remains challenging to learn the correlation between the template and…
In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch. We identify that three major challenges, i.e., moving object discovery, rich temporal variation exploitation, and online update, are the central…
We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking. We combine this with a novel tracklet-based dynamic programming algorithm, which…
Trackers based on Siamese network have shown tremendous success, because of their balance between accuracy and speed. Nevertheless, with tracking scenarios becoming more and more sophisticated, most existing Siamese-based approaches ignore…
The problem of tracking multiple objects in a video sequence poses several challenging tasks. For tracking-by-detection, these include object re-identification, motion prediction and dealing with occlusions. We present a tracker (without…
3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. However, LiDAR point clouds are usually textureless and…
Object tracking becomes critical especially when similar objects are present in the same area. Recent state-of-the-art (SOTA) approaches are proposed based on taking a matching network with a heavy structure to distinguish the target from…
The problem of visual object tracking has traditionally been handled by variant tracking paradigms, either learning a model of the object's appearance exclusively online or matching the object with the target in an offline-trained embedding…
Accurate detection and tracking of objects is vital for effective video understanding. In previous work, the two tasks have been combined in a way that tracking is based heavily on detection, but the detection benefits marginally from the…
Siamese trackers turn tracking into similarity estimation between a template and the candidate regions in the frame. Mathematically, one of the key ingredients of success of the similarity function is translation equivariance.…
Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area. Due to the large appearance variation between the template and search area during…
While remarkable progress has been made in robust visual tracking, accurate target state estimation still remains a highly challenging problem. In this paper, we argue that this issue is closely related to the prevalent bounding box…
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…
Recently, most siamese network based trackers locate targets via object classification and bounding-box regression. Generally, they select the bounding-box with maximum classification confidence as the final prediction. This strategy may…
Similarity learning has been recognized as a crucial step for object tracking. However, existing multiple object tracking methods only use sparse ground truth matching as the training objective, while ignoring the majority of the…
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…
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…
Thermal infrared (TIR) object tracking often suffers from challenges such as target occlusion, motion blur, and background clutter, which significantly degrade the performance of trackers. To address these issues, this paper pro-poses a…