Siamese Box Adaptive Network for Visual Tracking

By Zedu Chen, Bineng Zhong, Guorong Li, Shengping Zhang, Rongrong Ji. Computer Vision and Pattern Recognition, 2020

856 citations recorded by the source corpus.

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 configurations. To address this issue, we propose a simple yet effective visual tracking framework (named Siamese Box Adaptive Network, SiamBAN) by exploiting the expressive power of the fully convolutional network (FCN). SiamBAN views the visual tracking problem as a parallel classification and regression problem, and thus directly classifies objects and regresses their bounding boxes in a unified FCN. The no-prior box design avoids hyper-parameters associated with the candidate boxes, making SiamBAN more flexible and general. Extensive experiments on visual tracking benchmarks including VOT2018, VOT2019, OTB100, NFS, UAV123, and LaSOT demonstrate that SiamBAN achieves state-of-the-art performance and runs at 40 FPS, confirming its effectiveness and efficiency. The code will be available at https://github.com/hqucv/siamban.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cce1fecc800d2782da638f3060d5b2e887739f74

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

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”
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.”
Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark (2021, neutral): “41 SiamBAN [5] BBox 0.”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “5GHz CPU, RTX 2080Ti GPU Python PyTorch 70 BB CSA [191] ResNet-50 GOT-10k DAF Intel I9 CPU, 64GB RAM, RTX 2080Ti GPU Python PyTorch 100 CM SiamAttn [197] ResNet-50 COCO, YouTube-VOS, LaSOT, TrackingNet DAF N/A, RTX 2080Ti GPU Python PyTorch 33 BB, SGM SiamBAN [198] ResNet-50 ILSVRC-VID, YTBB, COCO, ”
Is First Person Vision Challenging for Object Tracking? (2020, positive): “Trackers based on siamese networks [8, 91, 36, 15, 48, 80, 90, 92] emerge as the fastest trackers, thanks to their non-reliance of online adaptation mechanisms.”
Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking (2022, methodology): “Siamese network is a representative paradigm in visual object tracking [2, 25, 24, 9, 45, 43], which usually consists of a Siamese backbone for feature extraction, an interactive head (e.”
Graph Attention Tracking (2020, positive): “A number of anchor-free trackers, such as SiamFC++ [33], SiamCAR [10], SiamBAN [3] and Ocean [36] are proposed, which achieve state-of-the-art tracking performance.”
ODTrack: Online Dense Temporal Token Learning for Visual Tracking (2024, methodology): “Traditional feature matching/- fusion methods(Chen et al. 2020; Zhang et al. 2020; Guo et al. 2021; Xie et al. 2022) focus on the appearance similar-The ity of object, without considering the property that tracking instance rely on continuous cross-frame associations.”