The Visual Object Tracking VOT2017 Challenge Results

Kristan, Matej; Leonardis, Aleš; Matas, Jiřı́; Felsberg, Michael; Pflugfelder, Roman; Zajc, Luka Čehovin; Vojíř, Tomáš; Hager, G; Lukežič, Alan; Eldesokey, Abdelrahman; Fernández, Gustavo J.; García-Martín, Álvaro; Muhič, Andrej; Petrosino, Alfredo; Memarmoghadam, Alireza; Vedaldi, Andrea; Manzanera, Antoine; Tran, Antoine; Alatan, A. Aydın; Mocanu, Bogdan; Chen, Boyu; Huang, Chang; Xu, Changsheng; Sun, Chong; Du, Dalong; Zhang, David; Du, Dawei; Mishra, Deepak; Gundogdu, Erhan; Velasco-Salido, Erik; Khan, Fahad Shahbaz; Battistone, Francesco; Subrahmanyam, Gorthi R. K. Sai; Bhat, Goutam; Huang, Guan; Bastos, Guilherme Sousa; Seetharaman, Guna; Zhang, Hongliang; Li, Houqiang; Lu, Huchuan; Drummond, Isabela; Valmadre, Jack; Jeong, Jae-chan; Cho, Jae-il; Lee, Jae-Yeong; Nosková, Jana; Zhu, Jianke; Gao, Jin; Liu, Jingyu; Kim, Ji Wan; Henriques, João F.; Martinez, José M.; Zhuang, Junfei; Xing, Junliang; Gao, Junyu; Chen, Kai; Palaniappan, Kannappan; Lebeda, Karel; Gao, Ke; Kitani, Kris M.; Zhang, Lei; Wang, Lijun; Yang, Lei; Wen, Longyin; Bertinetto, Luca; Poostchi, Mahdieh; Danelljan, Martin; Mueller, Matthias; Zhang, Mengdan; Yang, Ming–Hsuan; Xie, Nianhao; Wang, Ning; Mikšík, Ondřej; Moallem, Payman; M, Pallavi Venugopal; Senna, Pedro; Torr, Philip H. S.; Wang, Qiang; Yu, Qifeng; Huang, Qingming; Martín-Nieto, Rafael; Bowden, Richard; Liu, Risheng; Țapu, Ruxandra; Hadfield, Simon; Lyu, Siwei; Golodetz, Stuart; Choi, Sunglok; Zhang, Tianzhu; Zaharia, Titus; Santopietro, Vincenzo; Zou, Wei; Hu, Weiming; Tao, Wenbing; Li, Wenbo; Zhou, Wengang; Yu, Xianguo; Bian, Xiao; Li, Yang; Xing, Yifan; Fan, Yingruo; Zhu, Zheng; Zhang, Zhipeng; He, Zhiqun

doi:10.1109/iccvw.2017.230

Cited by 374 publications

(355 citation statements)

References 49 publications

Supporting

Mentioning

351

Contrasting

Unclassified

Order By: Relevance

“…This data augmentation technique facilitates the training of the LSTM network and improves the tracking performance. Extensive experiments on the OTB [11], TC-128 [15], UAV-123 [16] and VOT-2017 [17] benchmarks demonstrate the superior performance of the proposed method at the real-time speed compared with several state-of-the-art trackers. This exhibits great potentials of recurrent structures for visual tracking.…”

Section: Discussionmentioning

confidence: 93%

“…2 illustrates the pipeline of our tracking method. Experimental results on the OTB (both OTB-2013 and OTB-2015) [11], TC-128 [15], UAV-123 [16] and VOT-2017 [17] benchmarks demonstrate that our method achieves the state-of-the-art performance while operating at real-time speed, which exhibits great potentials of recurrent structures for visual object tracking.…”

Section: Introductionmentioning

confidence: 92%

See 1 more Smart Citation

Object-adaptive LSTM network for real-time visual tracking with adversarial data augmentation

Yan

Chen

et al. 2020

Neurocomputing

View full text Add to dashboard Cite

In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking methods exhibit excellent performance while their speeds are heavily limited by the expensive computation for massive proposal feature extraction. In contrast, matching-based tracking methods (such as Siamese networks) possess remarkable speed superiority.However, the absence of online updating renders these methods unadaptable to significant object appearance variations. In this paper, we propose a novel real-time visual tracking method, which adopts an object-adaptive LSTM network to effectively capture the video sequential dependencies and adaptively learn the object appearance variations. For high computational efficiency, we also present a fast proposal selection strategy, which utilizes the matching-based tracking method to pre-estimate dense proposals and selects high-quality ones to feed to the LSTM network for classification. This strategy efficiently filters out some irrelevant proposals and avoids the redundant computation for feature extraction, which enables our method to operate faster than conventional classification-based tracking methods. In addition, to handle the problems of sample inadequacy and class imbalance during online tracking, we adopt a data augmentation technique based on the Generative Adversarial Network (GAN) to facilitate the training of the LSTM network. Extensive experiments on four visual tracking benchmarks demonstrate the state-of-the-art performance of our method in terms of both tracking accuracy and speed, which exhibits great potentials of recurrent structures for visual tracking.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 92%

Object-adaptive LSTM network for real-time visual tracking with adversarial data augmentation

Yan

Chen

et al. 2020

Neurocomputing

View full text Add to dashboard Cite

show abstract

“…Our tracker is implemented in Python with the Pytorch framework, which runs at 80fps with an intel i7 3.2GHz CPU with 32G memory and a Nvidia 1080ti GPU with 11G memory. We compare our tracker with many state-of-theart trackers with real-time performance (i.e., their speeds are faster than 25fps) on recent benchmarks, including OTB-2015 [38], TC-128 [25], VOT-2017 [21] and LaSOT [12].…”

Section: Methodsmentioning

confidence: 99%

GradNet: Gradient-Guided Network for Visual Object Tracking

Chen

Ouyang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

279

118

View full text Add to dashboard Cite

The fully-convolutional siamese network based on template matching has shown great potentials in visual tracking. During testing, the template is fixed with the initial target feature and the performance totally relies on the general matching ability of the siamese network. However, this manner cannot capture the temporal variations of targets or background clutter. In this work, we propose a novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations. To be specific, the algorithm can utilize the information from the gradient to update the template in the current frame. In addition, a template generalization training method is proposed to better use gradient information and avoid overfitting. To our knowledge, this work is the first attempt to exploit the information in the gradient for template update in siamese-based trackers. Extensive experiments on recent benchmarks demonstrate that our method achieves better performance than other state-of-the-art trackers. The source codes are available at

show abstract

“…We employ the expected average overlap (EAO), Accuracy and Robustness to evaluate the baseline and real-time performance. We compare our ACFT with the trackers of top performance in [23], i.e., LSART (CVPR2018), CFWCR (ICCV17), CFCF (TPAMI18), ECO (CVPR17), CSRDCF++ (CVPR17), ECO_HC (CVPR17), SiamFC (ECCV16).…”

Section: Datasets and Evaluation Metricsmentioning

confidence: 99%

“…For VOT2017, we report the Baseline and the Real-time [23] results in Table 3. In the Baseline metric, ACFT achieves a comparable performance to the top trackers, with 0.317, 0.522 and 0.238 in terms of EAO, Accuracy and Robustness, respectively.…”

Section: Component Analysismentioning

confidence: 99%

An accelerated correlation filter tracker

Xu¹,

Feng²,

Wu³

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

Recent visual object tracking methods have witnessed a continuous improvement in the state-of-the-art with the development of efficient discriminative correlation filters (DCF) and robust deep neural network features. Despite the outstanding performance achieved by the above combination, existing advanced trackers suffer from the burden of high computational complexity of the deep feature extraction and online model learning. We propose an accelerated ADMM optimisation method obtained by adding a momentum to the optimisation sequence iterates, and by relaxing the impact of the error between DCF parameters and their norm. The proposed optimisation method is applied to an innovative formulation of the DCF design, which seeks the most discriminative spatially regularised feature channels. A further speed up is achieved by an adaptive initialisation of the filter optimisation process. The significantly increased convergence of the DCF filter is demonstrated by establishing the optimisation process equivalence with a continuous dynamical system for which the convergence properties can readily be derived. The experimental results obtained on several well-known benchmarking datasets demonstrate the efficiency and robustness of the proposed ACFT method, with a tracking accuracy comparable to the start-of-the-art trackers.

show abstract

The Visual Object Tracking VOT2017 Challenge Results

Cited by 374 publications

References 49 publications

Object-adaptive LSTM network for real-time visual tracking with adversarial data augmentation

Object-adaptive LSTM network for real-time visual tracking with adversarial data augmentation

GradNet: Gradient-Guided Network for Visual Object Tracking

An accelerated correlation filter tracker

Contact Info

Product

Resources

About