SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
By Dongyan Guo, Jun Wang, Ying Cui, Zhenhua Wang, Shengyong Chen. Computer Vision and Pattern Recognition, 2019
759 citations recorded by the source corpus.
By decomposing the visual tracking task into two subproblems as classification for pixel category and regression for object bounding box at this pixel, we propose a novel fully convolutional Siamese network to solve visual tracking end-to-end in a per-pixel manner. The proposed framework SiamCAR consists of two simple subnetworks: one Siamese subnetwork for feature extraction and one classification-regression subnetwork for bounding box prediction. Different from state-of-the-art trackers like Siamese-RPN, SiamRPN++ and SPM, which are based on region proposal, the proposed framework is both proposal and anchor free. Consequently, we are able to avoid the tricky hyper-parameter tuning of anchors and reduce human intervention. The proposed framework is simple, neat and effective. Extensive experiments and comparisons with state-of-the-art trackers are conducted on challenging benchmarks including GOT-10K, LaSOT, UAV123 and OTB-50. Without bells and whistles, our SiamCAR achieves the leading performance with a considerable real-time speed. The code is available at https://github.com/ohhhyeahhh/SiamCAR.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/738165f33c50b059e87b14d8b4a129230e14eacd
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
Citations in the corpus
- Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “8GHz CPU, 64GB RAM, GTX 1080Ti GPU Python PyTorch 40 BB SiamCAR [199] ResNet-50 ILSVRC-DET, COCO, ILSVRC-VID, YTBB DAF N/A, 4 RTX 2080Ti GPU Python PyTorch 52.”
- STMTrack: Template-free Visual Tracking with Space-time Memory Networks (2021, methodology): “The representative template-matching methods are siamese trackers [1, 65, 61, 14, 50, 6, 24, 23, 56, 15].”
- Transformer Tracking (2021, background): “In this subsection, we compare our TransT method with twelve state-of-the-art trackers published in 2020 (SiamR-CNN [39], Ocean [48], KYS [3], DCFST [49], SiamFC++ [44], PrDiMP [10], CGACD [13], Sia-mAttn [46], MAML [40], D3S [26], SiamCAR [16], and SiamBAN [5]) and six representative trackers prese”
- Graph Attention Tracking (2020, neutral): “We evaluate SiamGAT on GOT-10k and compare it with state-of-the-art trackers including SiamCAR [10], Ocean [36], SiamFC++ [33], D3S [1], SiamRPN++ [15], SPM [29], SiamRPN [16] and other baselines.”
- Learning Spatio-Temporal Transformer for Visual Tracking (2021, methodology): “Previous Siamese trackers [25, 51, 14, 6] only exploit the spatial information for tracking, while online methods [54, 57, 9, 3] use historical predictions for model updates.”
- Change Detection on Remote Sensing Images Using Dual-Branch Multilevel Intertemporal Network (2023, background): “From early fully connected networks (FCNs) [13], [14], to typical convolutional neural networks (CNNs) [15], [16], recurrent neural networks (RNNs) [17], as well as graph convolutional networks (GCNs) [18], [19], [20], [21], and then to the recently rising star transformer [22], most…”
- Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark (2021, neutral): “405 015 SiamCAR [16] CVPR-2020 ResNet-50 7 3 Local 52@GPU 0.”
- FCOS: A Simple and Strong Anchor-Free Object Detector (2020, positive): “More importantly, due to its simple design, FCOS can be easily extended to solve other instance-level recognition tasks with minimal modification, as already evidenced by instance segmentation [21], [22], [23], [24], keypoint detection [25], text spotting [26], and tracking [27], [28].”