S2SiamFC

Sio, Chon Hou; Ma, Yu-Jen; Shuai, Hong-Han; Chen, Jun-Cheng; Cheng, Wen-Huang

doi:10.1145/3394171.3413611

Cited by 34 publications

(4 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unsupervised Learning in 2D Tracking. To train a 2D tracker without labels, some methods construct templatesearch pairs from still frames to explore the self-supervised signals of the videos in the spatial dimension [47], [48]. However, these approaches are sensitive to appearance change, which is common in LiDAR data.…”

Section: Related Workmentioning

confidence: 99%

Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

Zheng

Zhang

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

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 incomplete, which hinders effective appearance matching. Besides, previous methods greatly overlook the critical motion clues among targets. In this work, beyond 3D Siamese tracking, we introduce a motion-centric paradigm to handle LiDAR SOT from a new perspective. Following this paradigm, we propose a matching-free two-stage tracker M 2 -Track. At the 1 st -stage, M 2 -Track localizes the target within successive frames via motion transformation. Then it refines the target box through motion-assisted shape completion at the 2 nd -stage. Due to the motion-centric nature, our method shows its impressive generalizability with limited training labels and provides good differentiability for end-to-end cycle training. This inspires us to explore semi-supervised LiDAR SOT by incorporating a pseudo-label-based motion augmentation and a self-supervised loss term. Under the fully-supervised setting, extensive experiments confirm that M 2 -Track significantly outperforms previous state-of-the-arts on three large-scale datasets while running at 57FPS (∼ 8%, ∼ 17% and ∼ 22% precision gains on KITTI, NuScenes, and Waymo Open Dataset respectively). While under the semi-supervised setting, our method performs on par with or even surpasses its fully-supervised counterpart using fewer than half labels from KITTI. Further analysis verifies each component's effectiveness and shows the motion-centric paradigm's promising potential for auto-labeling and unsupervised domain adaptation. The code is available at https://github.com/Ghostish/Open3DSOT.

show abstract

Section: Related Workmentioning

confidence: 99%

Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

Zheng

Zhang

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…In subsequent research, SiamRPN 28 incorporates a region proposal network into the tracking framework for joint classification and regression. In addition, some further studies [29][30][31] have been completed, such as the deeper backbone, feature aggregation architecture, and anchor-free methods. Transformer structure 32 has been applied to machine translation and target detection with remarkable effects.…”

Section: Aerial Trackingmentioning

confidence: 99%

Aerial tracking of camouflaged people in woodlands

Liu,

Wang,

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

With the remarkable advances of unmanned aerial vehicles (UAVs) and machine vision, aerial tracking has attracted wide attention from scholars. Previous tracking methods were mostly implemented in clean and well-lit environments, making it challenging to track camouflaged people rapidly and accurately in woodlands. We develop a framework for camouflaged people aerial tracking (CPAT) based on transformer. Specifically, a camouflaged people discovery strategy is proposed to rapidly generate training samples from the unlabeled videos captured by the UAV. Dynamic programming is also employed to filter noises to generate smooth candidate frames. To exploit multilevel feature information, a transformer fusion framework is designed to integrate shallow spatial information and in-depth semantic features. For reducing computing consumption, the spatial attention reduction mechanism is embedded in the multihead attention for fast tracking. Further, we build a dataset for evaluating the effect of camouflaged people tracking called Cam235, which consists of 85 manually labeled test sequences and more than 100k frames of the unlabeled training set. Exhaustive experiments on Cam235-test and popular tracking datasets prove that the CPAT is superior to other trackers for practical application. Under the most challenging condition of camouflaged people tracking, the CPAT achieves the precision of 67.9%, surpassing the state-of-the-art trackers by large margins.

show abstract

“…CycleSiam [ 31 ] extends the concept of consistency learning to Siamese network structures, while JSLTC [ 32 ] models video frames by computing an inter-frame affinity matrix and uses the obtained correlations for tracking. S2SiamFC [ 33 ] focuses on spatial monitoring and utilizes static frames to create training pairs. On the other hand, PUL [ 34 ] introduces contrastive learning to build a more discriminative model and uses robust loss functions during training to explore temporal correspondence blocks.…”

Section: Related Workmentioning

confidence: 99%

DLUT: Decoupled Learning-Based Unsupervised Tracker

Xu,

Huang,

Huang

et al. 2023

Sensors

View full text Add to dashboard Cite

Unsupervised learning has shown immense potential in object tracking, where accurate classification and regression are crucial for unsupervised trackers. However, the classification and regression branches of most unsupervised trackers calculate object similarities by sharing cross-correlation modules. This leads to high coupling between different branches, thus hindering the network performance. To address the above issue, we propose a Decoupled Learning-based Unsupervised Tracker (DLUT). Specifically, we separate the training pipelines of different branches to unlock their inherent learning potential so that different branches can fully explore the focused feature regions of interest. Furthermore, we design independent adaptive decoupling-correlation modules according to the characteristics of each branch to obtain more discriminative and easily locatable feature response maps. Finally, to suppress the noise interference brought by unsupervised pseudo-label training and highlight the foreground object, we propose a novel suppression-ranking-based unsupervised training strategy. Extensive experiments demonstrate that our DLUT outperforms state-of-the-art unsupervised trackers.

show abstract

S2SiamFC

Cited by 34 publications

References 58 publications

Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

Aerial tracking of camouflaged people in woodlands

DLUT: Decoupled Learning-Based Unsupervised Tracker

Contact Info

Product

Resources

About