A Twofold Siamese Network for Real-Time Object Tracking

He, Anfeng; Luo, Chong; Tian, Xinmei; Zeng, Wenjun

doi:10.1109/cvpr.2018.00508

Cited by 562 publications

(349 citation statements)

References 40 publications

Supporting

Mentioning

348

Contrasting

Unclassified

Order By: Relevance

“…OTB-2013 [41] and OTB-2015 [42] are two popular visual tracking benchmark datasets. The RAR tracker is compared with recent real-time (≥ 25 fps) trackers including DaSiamPRN [51], SiamTri [52], SA Siam [53], SiamRPN [22], TRACA [54], EDCF [40], CACF [46], CFNet [21], SiamFC [20] and HCF [27] on these benchmarks. We exploit two evaluation metrics, i.e., distance precision (DP) and overlap success rate (OSR).…”

Section: Results On Otbmentioning

confidence: 99%

Learning reinforced attentional representation for end-to-end visual tracking

Gao

Zhang

Wang

et al. 2020

Information Sciences

View full text Add to dashboard Cite

Despite the fact that tremendous advances have been made by numerous recent tracking approaches in the last decade, how to achieve high-performance visual tracking is still an open problem. In this paper, we propose an end-to-end network model to learn reinforced attentional representation for accurate target object discrimination and localization. We utilize a novel hierarchical attentional module with long short-term memory and multi-layer perceptrons to leverage both inter-and intra-frame attention to effectively facilitate visual pattern emphasis. Moreover, we incorporate a contextual attentional correlation filter into the backbone network to make our model be trained in an end-to-end fashion. Our proposed approach not only takes full advantage of informative geometries and semantics, but also updates correlation filters online without the backbone network fine-tuning to enable adaptation of target appearance variations. Extensive experiments conducted on several popular benchmark datasets demonstrate the effectiveness and efficiency of our proposed approach while remaining computational efficiency.

show abstract

Section: Results On Otbmentioning

confidence: 99%

Learning reinforced attentional representation for end-to-end visual tracking

Gao

Zhang

Wang

et al. 2020

Information Sciences

View full text Add to dashboard Cite

show abstract

“…CFNet [40] improved SiamFC by adding a correlation layer to the target branch. SA-Siam [15] proposed two Siamese networks, the first network encodes the semantic information and the second network encodes the appearance model, which is different from our architecture that has only one Siamese network. SiamRPN [24] formulated the tracking problem as a local one-shot detection.…”

Section: Siamese-based Trackersmentioning

confidence: 96%

“…A↑ EAO↑ R↓ FPS ASMS [41] 0.494 0.169 0.623 25 SiamRPN [23] 0.586 0.383 0.276 160 SA Siam R [15] 0.566 0.337 0.258 50 FSAN [19] 0.554 0.256 0.356 30 CSRDCF [29] 0.491 0.256 0.356 13 SiamFC [4] 0.503 0.188 0.585 86 SAPKLTF [19] 0.488 0.171 0.613 25 DSiam [14] 0.215 0.196 0.646 25 ECO [7] 0.484 0.280 0.276 60 DomainSiam(proposed) 0.593 0.396 0.221 53 Table 3. Comparisons with state-of-the-art trackers on TrackingNet dataset in terms of the Precision (PRE), Normalized Precision (NPRE), and Success.…”

Section: Trackermentioning

confidence: 99%

DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking

Abdelpakey

Shehata

2019

Advances in Visual Computing

View full text Add to dashboard Cite

Visual object tracking is a fundamental task in the field of computer vision. Recently, Siamese trackers have achieved state-of-theart performance on recent benchmarks. However, Siamese trackers do not fully utilize semantic and objectness information from pre-trained networks that have been trained on the image classification task. Furthermore, the pre-trained Siamese architecture is sparsely activated by the category label which leads to unnecessary calculations and overfitting. In this paper, we propose to learn a Domain-Aware, that is fully utilizing semantic and objectness information while producing a class-agnostic using a ridge regression network. Moreover, to reduce the sparsity problem, we solve the ridge regression problem with a differentiable weighteddynamic loss function. Our tracker, dubbed DomainSiam, improves the feature learning in the training phase and generalization capability to other domains. Extensive experiments are performed on five tracking benchmarks including OTB2013 and OTB2015 for a validation set; as well as the VOT2017, VOT2018, LaSOT, TrackingNet, and GOT10k for a testing set. DomainSiam achieves a state-of-the-art performance on these benchmarks while running at 53 FPS.

show abstract

“…He et al [14] combines two branches (Semantic net and Appearance net) of Siamese network (SA-Siam) to improve the generalization capability of SiamFC. Two branches are individually trained, and then the two branches are combined to output the similarity score at testing.…”

Section: Siamese Network Based Trackersmentioning

confidence: 99%

Fast Visual Object Tracking using Ellipse Fitting for Rotated Bounding Boxes

Chen

Tsotsos

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

In this paper, we demonstrate a novel algorithm that uses ellipse fitting to estimate the bounding box rotation angle and size with the segmentation(mask) on the target for online and real-time visual object tracking. Our method, SiamMask E, improves the bounding box fitting procedure of the state-of-the-art object tracking algorithm SiamMask and still retains a fast-tracking frame rate (80 fps) on a system equipped with GPU (GeForce GTX 1080 Ti or higher). We tested our approach on the visual object tracking datasets (VOT2016, VOT2018, and VOT2019) that were labeled with rotated bounding boxes. By comparing with the original SiamMask, we achieved an improved Accuracy of 65.2% and 30.9% EAO on VOT2019, which is 5.6% and 2.6% higher than the original SiamMask.The implementation is available on GitHub: https://github.com/ baoxinchen/siammask_e.

show abstract

A Twofold Siamese Network for Real-Time Object Tracking

Cited by 562 publications

References 40 publications

Learning reinforced attentional representation for end-to-end visual tracking

Learning reinforced attentional representation for end-to-end visual tracking

DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking

Fast Visual Object Tracking using Ellipse Fitting for Rotated Bounding Boxes

Contact Info

Product

Resources

About