Abstract:Correlation filter (CF) based trackers have become quite popular in video tracking because of their impressive performance and high frame rates. A large amount of recent research focuses on the improvement of training model of correlation filter to get a tracker with better discriminative power. However, this only helps the tracker to discriminate the target object from background within a small neighborhood, which is not suitable for fast motion scenes. In this paper, we propose a new detection model to dig out the potential of the correlation filter to deal with the challenge of fast motion. The model performs detection operations on multiple small search areas within a large one. Thus, our tracker can accurately localize the target object in a larger search area. In addition, we also added space constraints to boost the tracking performance of the model. The extensive experimental results demonstrate that the proposed tracker outperforms several state-of-the-art trackers on the challenging benchmark dataset with 51 sequences.

Alert Name:
Alerting to:
Authentication email will be sent to your email address in 24 hours
Frequency:
Email Message Format:	Plain text Graphical(HTML)

Complete the form below and we will recommend the selected titles to your friends on your behalf. * Indicates a required field.
Your name*:
Your email address*:
Recipient's name*:
Recipient's email address*:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find the page(s) useful.

Your name:
Your email address:
Recipient's name:
Recipient's email address:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find this page useful.

Disclaimer: This message was sent to your friend using the "Send it to a friend" facility on the Sciencepaper Online’ WWW site, http://www.paper.edu.cn/en. The Sciencepaper Online is not responsible for the content of this email, and anything said in this email does not necessarily reflect the Sciencepaper Online's views.


	1. Kernel Correlation Filter Tracking based on Spatial Constraint
	LI Zhi-Yong,Chen Li
	Information Science and System Science 25 April 2018
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Correlation filter (CF) based trackers have become quite popular in video tracking because of their impressive performance and high frame rates. A large amount of recent research focuses on the improvement of training model of correlation filter to get a tracker with better discriminative power. However, this only helps the tracker to discriminate the target object from background within a small neighborhood, which is not suitable for fast motion scenes. In this paper, we propose a new detection model to dig out the potential of the correlation filter to deal with the challenge of fast motion. The model performs detection operations on multiple small search areas within a large one. Thus, our tracker can accurately localize the target object in a larger search area. In addition, we also added space constraints to boost the tracking performance of the model. The extensive experimental results demonstrate that the proposed tracker outperforms several state-of-the-art trackers on the challenging benchmark dataset with 51 sequences.
	TO cite this article:LI Zhi-Yong,Chen Li. Kernel Correlation Filter Tracking based on Spatial Constraint[OL].[25 April 2018] http://en.paper.edu.cn/en_releasepaper/content/4744779


	2. Pedestrian Detection Based on Ensemble Large Margin Distribution Machine
	Cheng Fanyong,Zhang Jing
	Information Science and System Science 04 March 2015
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:This paper studies the problem of robust classifier for visual pedestrian detection, based on HOG (Histograms of Oriented Gradient) descriptors. The average gradient image over the training positive examples is similar with the personal sketch and the variance represents poses in various complicated environments. Inspired by these, Large Margin Distribution Learning is investigated. It is found that the performance of LDM classifier with appropriate parameters is better than SVMs', nevertheless it is difficult to obtain optimal parameters. In order to improve robustness, ELDM (Ensemble Large Margin Distribution Machine) including maximizing the minimum margin and two margin distributions is proposed, which is the best in convex combination of SVMs and two LDMs with different parameter orders. The impact of parameters which are sensitive in the robustness of LDM is weakened by ELDM and ensemble parameters are obtained by the mesh grid optimization. Experimental results show that ELDM can obtain better results than existing classifiers for pedestrian detection in the classification performance and stability.
	TO cite this article:Cheng Fanyong,Zhang Jing. Pedestrian Detection Based on Ensemble Large Margin Distribution Machine[OL].[ 4 March 2015] http://en.paper.edu.cn/en_releasepaper/content/4633082

Saved Papers

Saved Papers


	3. Quantum teleportation and state sharing via a generalized seven-qubit Brown state
	Kang Shuang-Yong,Chen Xiu-Bo,Yang Yi-Xian
	Information Science and System Science 06 January 2014
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:In this paper, a novel scheme is investigated for quantum teleportation (QT) and quantum state sharing (QSTS). The generalized seven-qubit Brown state $\|B_{7} angle$ is used as information carrier. Firstly, for an arbitrary single-qubit state, we perfectly present a QT protocol and three QSTS ones, which is among three participants via $\|B_{7} angle$. Then we make an overall comparison among three QSTS protocols and present an almost even distribution principle of particles. Secondly, for two- and three- qubit cases, based on the almost even distribution principle we design several QT and QSTS protocols.%Finally, we mainly consider our scheme's security against dishonest participant attacks.Furthermore, for an arbitrary $N$-qubit state, there is a conjecture that QT and QSTS can be designed by using the generalized $(2N+1)$-qubit Brown state $\|B_{2N+1} angle$ in Eq.(3) ($Ngeq2$) in theoretical aspects.
	TO cite this article:Kang Shuang-Yong,Chen Xiu-Bo,Yang Yi-Xian. Quantum teleportation and state sharing via a generalized seven-qubit Brown state[OL].[ 6 January 2014] http://en.paper.edu.cn/en_releasepaper/content/4574567


	4. Recurrence networks from multivariate signals for uncovering dynamic transitions of horizontal oil-water stratified flows
	Gao Zhongke,Zhang Xinwang,Jin Ningde,Donner Reik V.,Marwan Norbert,Kurths Jürgen
	Information Science and System Science 07 August 2013
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Characterizing the mechanism of drop formation at the interface of horizontal oil-water stratified flows is a fundamental problem eliciting a great deal of attention from different disciplines. We experimentally and theoretically investigate the formation and transition of horizontal oil-water stratified flows. We design a new multi-sector conductance sensor and measure multivariate signals from two different stratified flow patterns. Using the Adaptive Optimal Kernel Time-Frequency Representation (AOK TFR) we first characterize flow behavior from the energy and frequency point of view. Then, we infer multivariate recurrence networks from experimental data and investigate the cross-transitivity for each constructed network. We find that the cross-transitivity from recurrence network analysis allows quantitatively uncovering the flow behavior when the stratified flow evolves from stable state to unstable state and recovers deeper insights into the mechanism governing the formation of drops at the interface of stratified flows, a task that existing method based on AOK TFR fails to work. These interesting and significant findings present a first step towards an improved understanding of the dynamic mechanism leading to the transition of horizontal oil-water stratified flows from a complex network perspective
	TO cite this article:Gao Zhongke,Zhang Xinwang,Jin Ningde, et al. Recurrence networks from multivariate signals for uncovering dynamic transitions of horizontal oil-water stratified flows[J].


	5. Multivariate recurrence network analysis for characterizing horizontal oil-water two-phase flow
	Gao Zhongke,Zhang Xinwang,Jin Ningde,Marwan Norbert,Kurths Jürgen
	Information Science and System Science 25 July 2013
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Characterizing complex patterns arising from horizontal oil-water two-phase flows is a contemporary and challenging problem of paramount importance. We design a new multi-sector conductance sensor and systematically carry out horizontal oil-water two-phase flow experiments for measuring multivariate signals of different flow patterns. We then infer multivariate recurrence networks from these experimental data and investigate local cross-network properties for each constructed network. Our results demonstrate that local cross-clustering coefficient from a multivariate recurrence network is very sensitive to transitions among different flow patterns and recovers quantitative insights into the flow behavior underlying horizontal oil-water flows. These properties render multivariate recurrence networks particularly powerful for investigating a horizontal oil-water two-phase flow system and its complex interacting components from a network perspective.
	TO cite this article:Gao Zhongke,Zhang Xinwang,Jin Ningde, et al. Multivariate recurrence network analysis for characterizing horizontal oil-water two-phase flow[J].


	6. A Continuous-time Recurrent Neural Network for Real-time Support Vector Regression
	Liu Qingshan
	Information Science and System Science 24 September 2012
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:This paper presents a continuous-time recurrent neural network described by differential equations for real-time support vector regression (SVR). The SVR is first formulated as a convex quadratic programming problem, and then a continuous-time recurrent neural network with one-layer structure is designed for training the support vector machine. Furthermore, simulation results on an illustrative example are given to demonstrate the effectiveness and performance of the proposed neural network.
	TO cite this article:Liu Qingshan. A Continuous-time Recurrent Neural Network for Real-time Support Vector Regression[OL].[24 September 2012] http://en.paper.edu.cn/en_releasepaper/content/4489716


	7. A discrete-time recurrent neural network with global exponential stability for constrained linear variational inequalities
	LIU Qingshan
	Information Science and System Science 11 January 2012
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:In this paper, a discrete-time recurrent neural networks with global exponential stability are proposed for solving constrained linear variational inequalities problems. Compared with the existing neural networks for linear variational inequalities, the proposed neural network in this paper has lower model complexity with only one-layer structure. The global exponential stability of the neural network can be guaranteed under some mild conditions. Simulation results show the performance and characteristic of the proposed neural network.
	TO cite this article:LIU Qingshan. A discrete-time recurrent neural network with global exponential stability for constrained linear variational inequalities[OL].[11 January 2012] http://en.paper.edu.cn/en_releasepaper/content/4459837


	8. Tissue P systems with cell separation: attacking the partition problem
	Zhang Xingyi,Wang Shuo,Niu Yunyun,Pan Linqiang
	Information Science and System Science 11 January 2011
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Tissue P systems are distributed parallel and non-deterministic computing models in the framework of membrane computing, which are inspired by intercellular communication and cooperation between neurons. Recently, cell separation is introduced into tissue P systems, which enables systems to generate an exponential workspace in a polynomial time. In this work, the computational power of tissue P systems with cell separation is investigated. Specifically, a uniform family of tissue P systems with cell separation is constructed for efficiently solving a well-known NP-complete problem, the partition problem.
	TO cite this article:Zhang Xingyi,Wang Shuo,Niu Yunyun, et al. Tissue P systems with cell separation: attacking the partition problem[OL].[11 January 2011] http://en.paper.edu.cn/en_releasepaper/content/4405857


	9. Discrete Particle Swarm Optimization for Terminal Assignment Problems
	WANG Jiahai,CAI Yiqiao
	Information Science and System Science 19 August 2010
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:This paper presents a novel discrete particle swarm optimization (PSO) based on estimation of distribution (EDA), named DPSO-EDA, for terminal assignment problem (TEAP). EDAs sample new solutions from a probability model which characterizes the distribution of promising solutions in the search space at each generation. The DPSO-EDA incorporates the global statistical information collected from personal best solutions of all particles into the PSO, and therefore each particle has comprehensive learning and search ability. Simulation results on several problem instances show that the DPSO-EDA is better than previous methods.
	TO cite this article:WANG Jiahai,CAI Yiqiao. Discrete Particle Swarm Optimization for Terminal Assignment Problems[OL].[19 August 2010] http://en.paper.edu.cn/en_releasepaper/content/4382268


	10. A fictitious play approach for minimizing the total weighted tardiness in a job shop
	Gu Hanyu ,Tao Jiping ,Xi Yugeng
	Information Science and System Science 30 April 2010
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:A noncooperative game model is established for the job shop scheduling problem of minimizing total weighted tardiness. Fictitious play is used to compute the Nash-equilibrium (NE). Then by exploiting the equivalence of the NE of the proposed game model and the optimal solutions of the Lagrangian dual problem and its linear programming dual problem, $\\alpha$-point idea is applied to construct feasible schedules. Furthermore a simple local search method is designed to further improve the schedule performance. Numerical results on classical benchmark instances demonstrate the effectiveness of the proposed algorithm.
	TO cite this article:Gu Hanyu ,Tao Jiping ,Xi Yugeng . A fictitious play approach for minimizing the total weighted tardiness in a job shop[OL].[30 April 2010] http://en.paper.edu.cn/en_releasepaper/content/42513

	Check out RSS, or use RSS reader to subscribe this item