Improved Action-Decision Network for Visual Tracking With Meta-Learning

Huang, Detian; Kong, Lingke; Zhu, Jianqing; Zheng, Lixin

doi:10.1109/access.2019.2936551

Cited by 7 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to approaches using iterative bounding box refinements (in column Iter), such as TSAS [ 36 ] and ADNet, our model (Ours_MT_MD) achieves better/comparable results. Our ADNet-based tracker (ADNet_MT) achieves better/comparable results than those in [ 7 , 35 , 40 ], which also use iterative refinements.…”

Section: Resultsmentioning

confidence: 98%

See 1 more Smart Citation

Iterative Multiple Bounding-Box Refinements for Visual Tracking

Cruciata¹,

Presti²,

Cascia³

2022

J. Imaging

View full text Add to dashboard Cite

Single-object visual tracking aims at locating a target in each video frame by predicting the bounding box of the object. Recent approaches have adopted iterative procedures to gradually refine the bounding box and locate the target in the image. In such approaches, the deep model takes as input the image patch corresponding to the currently estimated target bounding box, and provides as output the probability associated with each of the possible bounding box refinements, generally defined as a discrete set of linear transformations of the bounding box center and size. At each iteration, only one transformation is applied, and supervised training of the model may introduce an inherent ambiguity by giving importance priority to some transformations over the others. This paper proposes a novel formulation of the problem of selecting the bounding box refinement. It introduces the concept of non-conflicting transformations and allows applying multiple refinements to the target bounding box at each iteration without introducing ambiguities during learning of the model parameters. Empirical results demonstrate that the proposed approach improves the iterative single refinement in terms of accuracy and precision of the tracking results.

show abstract

Section: Resultsmentioning

confidence: 98%

“…At test time, a supervised adaptation of the latest fully connected layers is performed to make the model more robust to appearance changes. ADNet was later improved in IADNet [ 35 ]. During training, a multi-domain learning strategy [ 4 ] is used.…”

Section: Related Workmentioning

confidence: 99%

Iterative Multiple Bounding-Box Refinements for Visual Tracking

Cruciata¹,

Presti²,

Cascia³

2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…However, the algorithm proposed can achieve better results in the category of a non-deep learning algorithm, but it can only be used when the target area has been provided, and it is not suitable for other cases. More positively, various kinds of deep neural network are now widely studied and have illustrated outstanding accuracy and efficiency in existing tracking benchmarks [47]- [50]. As is reported in literature [51], [52], a multi-mode framework based on a neural network is proposed, which can better capture effective targets.…”

Section: Analysis and Future Workmentioning

confidence: 99%

Robust Visual Tracking via a Collaborative Model Based on Locality-Constrained Sparse Coding

Fan

2020

IEEE Access

View full text Add to dashboard Cite

Target tracking is an important task in computer vision. Now many tracking algorithms have achieved great results. However, several challenges still hinder the development of tracking algorithms, such as abrupt motion, occlusion and so on. In order to use the feature information of the target more effectively and improve the accuracy and robustness of target tracking, a novel model is designed which is different from the previous discriminative component and generative component, and a novel discriminative-generative collaborative appearance model is presented to combine the two components in this paper. First, for the discriminative component, Locality-Constrained Sparse Coding Algorithm is proposed. In this algorithm, the objective function of the local feature of the target spatial information is determined by fusing the pyramid maximum pool and local feature histogram method. The objective function has three important parameters, which are solved by different optimization strategies. Second, for the generative component, the Histogram of Locality-Constrained Feature Algorithm is proposed. In this algorithm, the locality constraint is served to describe the spatial information of the target as a generative appearance model. Each image patch can be approximated by a linear combination of a local coordinate system formed by a dictionary whose elements are cluster centers that contain the most representative model of the target. Third, this paper designs a collaborative target tracking framework based on semi-supervised learning algorithm with locality constraint coding. The framework can quickly and robustly determine the feature information of the tracking region. The proposed algorithm is evaluated on the comprehensive test platform. The experimental results show that our method is more robust and efficient, and the precision and success rate of our algorithm are improved by 5.4% and 4.7%, respectively. INDEX TERMS Locality-constrained, collaborative model, visual tracking, Bayesian framework.

show abstract

Accurate visual tracking via reliable patch

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a novel visual tracking framework that intelligently discovers reliable patterns from a wide range of video to resist drift error for long-term tracking tasks. First, we design a Discrete Fourier Transform (DFT) based tracker which is able to exploit a large number of tracked samples while still ensures real-time performance. Second, we propose a clustering method with temporal constraints to explore and memorize consistent patterns from previous frames, named as "reliable memories". By virtue of this method, our tracker can utilize uncontaminated information to alleviate drifting issues. Experimental results show that our tracker performs favorably against other stateof-the-art methods on benchmark datasets. Furthermore, it is significantly competent in handling drifts and able to robustly track challenging long videos over 4000 frames, while most of others lose track at early frames.

show abstract

Improved Action-Decision Network for Visual Tracking With Meta-Learning

Cited by 7 publications

References 34 publications

Iterative Multiple Bounding-Box Refinements for Visual Tracking

Iterative Multiple Bounding-Box Refinements for Visual Tracking

Robust Visual Tracking via a Collaborative Model Based on Locality-Constrained Sparse Coding

Accurate visual tracking via reliable patch

Contact Info

Product

Resources

About