Recently, attributes have been introduced to help object classification. Multi-task learning is an effective methodology to achieve this goal, which shares low-level features between attribute and object classifiers. ...
详细信息
Recently, attributes have been introduced to help object classification. Multi-task learning is an effective methodology to achieve this goal, which shares low-level features between attribute and object classifiers. Yet such a method neglects the constraints that attributes impose on classes which may fail to constrain the semantic relationship between the attribute and object classifiers. In this paper, we explicitly consider such attribute-object relationship, and correspondingly, we modify the multi-task learning model by adding attribute regularization. In this way, the learned model not only shares the low-level features, but also gets regularized according to the semantic constrains. Our method is verified on two challenging datasets (KTH and Olympic Sports), and the experimental results demonstrate that our method achieves better results than previous methods in human action recognition.
Cloud classification plays an essential role in a large number of applications. However, this issue is particularly challenging due to the extreme appearance variations under different atmospheric conditions. In this ...
详细信息
Cloud classification plays an essential role in a large number of applications. However, this issue is particularly challenging due to the extreme appearance variations under different atmospheric conditions. In this paper, a novel descriptor named illumination-invariant completed local ternary pattern (ICLTP) is proposed for cloud classification. The proposed descriptor effectively handles the illumination variations by introducing illumination invariant factor. Furthermore, the Quadratic-Chi metric, which is more suitable for comparing the difference between two histograms, is applied instead of Chi-Square metric. The experimental results demonstrate the superior performance of our strategy on two challenging cloud databases. Besides cloud classification, we further validate the proposed ICLTP operator on traditional texture classification, which show the good generalization ability.
In this paper, we propose a discriminative low-rank dictionary learning algorithm for sparse representation. Sparse representation seeks the sparsest coefficients to represent the test signal as linear combination of ...
详细信息
In this paper, we propose a discriminative low-rank dictionary learning algorithm for sparse representation. Sparse representation seeks the sparsest coefficients to represent the test signal as linear combination of the bases in an over-complete dictionary. Motivated by low-rank matrix recovery and completion, assume that the data from the same pattern are linearly correlated, if we stack these data points as column vectors of a dictionary, then the dictionary should be approximately low-rank. An objective function with sparse coefficients, class discrimination and rank minimization is proposed and optimized during dictionary learning. We have applied the algorithm for face recognition. Numerous experiments with improved performances over previous dictionary learning methods validate the effectiveness of the proposed algorithm.
In this paper, by employing an online algorithm based on policy iteration (PI), an adaptive optimal control problem for continuous-time (CT) nonlinear partially uncertain dynamic systems is investigated. In this propo...
详细信息
In this paper, by employing an online algorithm based on policy iteration (PI), an adaptive optimal control problem for continuous-time (CT) nonlinear partially uncertain dynamic systems is investigated. In this proposed algorithm, a discounted cost function is discussed, which is considered to be a more general case for optimal control problems. Two neural networks (NNs) are used to implement the algorithm, which aims at approximating the cost function and the control law, respectively. The uniform convergence to the optimal control is proven, and the stability of the system is guaranteed. An illustrating example is given.
Bus Rapid Transit (BRT) is an effective way to increase urban traffic capacity. But its operation and scheduling optimization are difficult. In this article, Parallel BRT Operation management System (PBOMS) is constru...
详细信息
Bus Rapid Transit (BRT) is an effective way to increase urban traffic capacity. But its operation and scheduling optimization are difficult. In this article, Parallel BRT Operation management System (PBOMS) is constructed based on ACP approach. It can detect the passenger's quantity on station platforms in real-time, traffic flow besides stations or at intersections, and the queuing length of vehicles on the road lines. It can provide short-term passenger and traffic saturation prediction in order to arrange transportation management more accurately to relieve the congestion. It can assess, improve and optimize the emergency management during holidays, public events, accidents and other emergency situations. It can improve the quality of real-time scheduling functions by using the measurement results detected from traffic videos, and so on. This system has been piloted in Guangzhou Zhongshan Avenue BRT, which was applied for BRT's monitoring, warning, forecasting, emergency management, real-time scheduling and other purposes, to improve Guangzhou BRT's smoothness, safety, efficiency and reliability.
Public traffic is required for the convenient travel, reducing traffic congestion and accidents, low-carbon, environmental protection, sustainable development, and traffic demand of giant sports and large business act...
详细信息
Public traffic is required for the convenient travel, reducing traffic congestion and accidents, low-carbon, environmental protection, sustainable development, and traffic demand of giant sports and large business activities, etc. For public transport demand of the 16th Asian Games and the 2010 Asian Para Games held in Guangzhou in 2010, based on ACP approach, Parallel Public Transport management And control System (PPTMS) for Guangzhou Asian Games had been developed to support management decision of public transport. This system can help public transport managers to improve and enhance significantly the level of public transport management in Guangzhou, from experience-based formulation and manual implementation to scientific computation-based formulation and automatic implementation with intelligent systems, to guarantee the traffic demand effectively during the two Games.
Traditional sparse coding has been successfully applied in texture and image classification in the past years. Yet such kind of method neglects the influence of the signs of coding coefficients, which may cause inform...
详细信息
ISBN:
(纸本)9781467322164
Traditional sparse coding has been successfully applied in texture and image classification in the past years. Yet such kind of method neglects the influence of the signs of coding coefficients, which may cause information loss in the sequential max pooling. In this paper, we propose a novel coding strategy for ground-based cloud classification, which is named soft-signed sparse coding. In our method, a constraint on the signs is explicitly added to the objective function of traditional sparse coding model, which can effectively regulate the ratio between the number of positive and negative non-zero coefficients. As a result, the proposed method can not only obtain low reconstruction error but also consider the influence of the signs of coding coefficients. The strategy is verified on two challenging cloud datasets, and the experimental results demonstrate the superior performance of our method compared with previous ones.
In this paper, we solve the H ∞ control problems for discrete-time affine nonlinear systems with known dynamics. An iterative heuristic dynamic programming algorithm is derived and the convergence analysis is provid...
In this paper, we solve the H ∞ control problems for discrete-time affine nonlinear systems with known dynamics. An iterative heuristic dynamic programming algorithm is derived and the convergence analysis is provided. Three neural networks are used to approximate the control policy, the disturbance policy, and the value function, respectively. A simulation example is presented to demonstrate the effectiveness of the proposed scheme.
In the literature of human action recognition, despite promising results have been obtained by the traditional bag-of-words model, the relationship among spatiotemporal points has rarely been considered. Furthermore, ...
详细信息
In the literature of human action recognition, despite promising results have been obtained by the traditional bag-of-words model, the relationship among spatiotemporal points has rarely been considered. Furthermore, serious quantization error also exists in this kind of strategy. In this paper, we propose a novel coding strategy named contextual Fisher kernels to overcome these limitations. We add a Gaussian function to represent contextual information into the generative model. In this way, our method explicitly considers the spatio-temporal contextual relationships between interest points and alleviates quantization error. Our method is verified on two challenging datasets (KTH and UCF sports), and the experimental results demonstrate that our method achieves better results than the state-of-the-art methods in human action recognition.
The Proportional - Integral - Derivative (PID) controllers are one of the most popular controllers used in industry because of their remarkable effectiveness, simplicity of implementation and broad applicability. PID ...
详细信息
暂无评论