P2T: Part-to-Target Tracking via Deep Regression Learning

Gao, Junyu; Zhang, Tianzhu; Yang, Xiaoshan; Xu, Changsheng

doi:10.1109/tip.2018.2813166

Cited by 47 publications

(22 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the above sections we have carried out many experiments on the unconstrained face databases to demonstrate the effectiveness of our proposed method compared to the traditional subspace learning algorithms, such as LPP [22], NPE [23], SPP [33] and DSNPE [39] etc. However, as we all know, in recent years Deep Learning (DL) technology has already attracted widespread attentions due to its superior performance in many practical applications, such as face recognition [6,7], object tracking [60,61], image restoration [62,63], pose estimation [64,65], etc. Hence, in this section we also further compare the performance between DL-based algorithms and our proposed DSGE method, and analyze the advantages of using DSGE algorithm in the unconstrained face recognition.…”

Section: Comparison With Deep Learning Algorithmsmentioning

confidence: 99%

Discriminative Sparsity Graph Embedding for Unconstrained Face Recognition

2019

View full text Add to dashboard Cite

In this paper, we propose a new dimensionality reduction method named Discriminative Sparsity Graph Embedding (DSGE) which considers the local structure information and the global distribution information simultaneously. Firstly, we adopt the intra-class compactness constraint to automatically construct the intrinsic adjacent graph, which enhances the reconstruction relationship between the given sample and the non-neighbor samples with the same class. Meanwhile, the inter-class compactness constraint is exploited to construct the penalty adjacent graph, which reduces the reconstruction influence between the given sample and the pseudo-neighbor samples with the different classes. Then, the global distribution constraints are introduced to the projection objective function for seeking the optimal subspace which compacts intra-classes samples and alienates inter-classes samples at the same time. Extensive experiments are carried out on AR, Extended Yale B, LFW and PubFig databases which are four representative face datasets, and the corresponding experimental results illustrate the effectiveness of our proposed method.

show abstract

Section: Comparison With Deep Learning Algorithmsmentioning

confidence: 99%

Discriminative Sparsity Graph Embedding for Unconstrained Face Recognition

2019

View full text Add to dashboard Cite

show abstract

“…Targets in multi-target tracking tasks can be pedestrians [18], vehicles on the road [19], [20], players on the soccer field [21], groups of animals [22], or even different parts of a single target [23]. In this paper, we mainly focus on pedestrian tracking for the following reasons: first, pedestrian is a typical non-rigid object, which is an ideal example of multiobject tracking; second, pedestrian targets are relatively rich in scenes, the problems encountered are more comprehensive and complex; third, pedestrian tracking are closer to human daily life, and have great application value.…”

Section: Related Workmentioning

confidence: 99%

Fast Online Multi-Pedestrian Tracking via Integrating Motion Model and Deep Appearance Model

Luo

et al. 2019

IEEE Access

View full text Add to dashboard Cite

In recent years, multi-object tracking has attracted more and more attention, both in academia and engineering, but most of the recent works do not pay attention to the speed of the algorithm and only pursue the accuracy. In this paper, we propose an online multi-pedestrian tracking algorithm, taking into account both the accuracy and the speed. First, the motion models of the targets are established by the Kalman filter. At the same time, the appearance models of the targets are extracted by the convolutional neural network. Moreover, a data association algorithm is proposed, which integrates the motion information, including scale, intersection-over-union, and distance, and the appearance information, including the current appearance model and the long-term appearance model. With the data association algorithm, the matching between detections and tracklets is realized, and the goal of tracking by detection is achieved. We compare the proposed algorithm with other algorithms on the MOT15 benchmark and the MOT16 benchmark. The experiment results show that the algorithm has high accuracy and good real-time performance. INDEX TERMS Online, pedestrian detection, multi-object tracking, re-identifying, Kalman filter, data association.

show abstract

“…Recently, deep learning has become a significant part of information science research [1]- [4]. And deep learning has achieved outstanding performance in many fields, such as image classification [5]- [7], action recognition [8], [9], image captioning [10], and target localization [11]- [13]. The performance of a deep neural network is mainly determined by the structure of its model and its corresponding optimization algorithm.…”

Section: Introductionmentioning

confidence: 99%

Effective Neural Network Training With a New Weighting Mechanism-Based Optimization Algorithm

Fu-xian

2019

IEEE Access

View full text Add to dashboard Cite

First-order gradient-based optimization algorithms have been of core practical importance in the field of deep learning. In this paper, we propose a new weighting mechanism-based first-order gradient descent optimization algorithm, namely NWM-Adam, to resolve the undesirable convergence behavior of some optimization algorithms which employ fixed sized window of past gradients to scale the gradient updates and improve the performance of Adam and AMSGrad. The NWM-Adam is developed on the basis of the idea, i.e., placing more memory of the past gradients than the recent gradients. Furthermore, it can easily adjust the degree to which how much the past gradients weigh in the estimation. In order to empirically test the performance of our proposed NWM-Adam optimization algorithm, we compare it with other popular optimization algorithms in three well-known machine learning models, i.e., logistic regression, multi-layer fully connected neural networks, and deep convolutional neural networks. The experimental results show that the NWM-Adam can outperform other optimization algorithms. INDEX TERMS Deep learning, optimization algorithm, learning rate, neural network training.

show abstract

P2T: Part-to-Target Tracking via Deep Regression Learning

Cited by 47 publications

References 55 publications

Discriminative Sparsity Graph Embedding for Unconstrained Face Recognition

Discriminative Sparsity Graph Embedding for Unconstrained Face Recognition

Fast Online Multi-Pedestrian Tracking via Integrating Motion Model and Deep Appearance Model

Effective Neural Network Training With a New Weighting Mechanism-Based Optimization Algorithm

Contact Info

Product

Resources

About