Printer Friendly

Commercial Video Evaluation via Low-Level Feature Extraction and Selection.

1. Introduction

As a major kind of commercial multimedia, commercial videos' popularity is concerned by related companies and producers. There are many factors which influenced the audiences' evaluation to the commercial videos, such as the actor/actress, director, and story. But it is too subjective if these factors are employed to evaluate the videos. It is because that these factors are not quantitative in the evaluation procedure. So, the importance of design a model to analysis the videos and calculate the evaluation of them should be realized by the researchers [1]. The article [2] proposed an objective video quality evaluation method based on motion and disparity information. The article [3] presented a video quality evaluation method based on Quaternion Singular Value Decomposition. But only a few video features were used in [2,3]. The video features should include many features such as color features, motion features, and shot features which might be very likely to influence the audiences' evaluation of the videos. However, the most influential feature set and the relationships between them and the video popularity are still not clear yet. For all the features extracted, we can select the most influential feature set through the feature selection methods according the commercial videos' evaluation data. Of cause, the feature dimension reduction methods could also be used here.

Different feature set might be selected by different feature selection or dimension reduction methods. The feature dimension reduction algorithms, such as PCA [4, 5], FDA [6], and KPCA [7, 8], would reduce the feature number, while feature selection algorithms would select the optimal feature set from all the original features. Compared with the dimension reduction algorithms, the feature selection maintains the physical meanings of the original features and this is more convenient for data and relationship between features and videos' popularity analysis [9].

The main idea of feature selection is selecting a few valuable features and removing the useless ones from all the features extracted. The methods, such as embedded methods, Relief [10], mRMR [11], and CFS [12, 13], are widely used now.

For the embedded methods, sparsity regularized feature selection methods were also widely used in some research area such as appearance modeling in visual tracking [14-16]. In these methods, [l.sub.1]-norm [17] (being called Lasso, presented by Tibshirani in 1996) and [l.sub.1,2]-norm based regularization models have been researched for selecting features with joint sparsity across different tasks [18]. These methods select features by adding a penalty term with weight to the objective function of the machine learning model, which restricts the weight of each feature of the model. Feature selection is done in the process of model training, and those features whose coefficients are trained to zero are considered as redundant features. Recently, [l.sub.p]-norm and [l.sub.2,p]-norm model based regularization methods have attracted more and more attention because they can obtain sparser solutions than the methods based on [l.sub.1]-norm and [l.sub.2,1]-norm [19]. The algorithms typically take a trade-off between a data-fitting loss function term and a sparsity term; therefore there inevitably exists residual in the loss function. However, little is known about such a residual's impact on the feature selection [20].

For other methods, only the correlation between feature and class was concerned in Relief algorithm but not the correlation between features. So, the selected feature set was not the optimal one [21]. For mRMR algorithm, both the correlation between features and feature-class were concerned to get the best feature set [22]. For the classifier, all the contributions of the features selected by mRMR were same, and the feature set was selected from the original features. The main idea of CFS is selecting the feature set with lower correlation between features and higher correlation between feature and class. After this procedure, the redundant features and the features which were not closely related to the class would be removed. The Pearson linear correlation coefficient was used in [21, 22] by Huanjing Wang and Ningqing Sun to calculate the correlation between features and feature-class. But only linear correlation coefficient could be measured in Pearson formula. For continuous data, discretization methods or kernel density estimation methods should be employed to solve the problem. This procedure would lead to probability estimation error.

So, the effectiveness of the correlation calculation is the key of successfulness of CFS. Currently, some correlation calculation methods were concerned by many researchers, and we should select the best one according to experiment results. Except Pearson Coefficient, some other correlation calculation methods are being used now. Spearman Rank Correlation Coefficient was used in the article of Marie Therese Puth [23] to descript the correlation of two vectors. The experiment result showed that the Spearman Rank Correlation Coefficient is better than Pearson Coefficient. In the research of Xiaoyuan Xu [24], the Spearman Rank Correlation Coefficient was employed to descript the correlation between features of wind speed. In the article of Jing Feng [25], a nonparametric method based on Spearman Rank Correlation Coefficient was proposed to measure the principle of storage degradation failure.

Spearman Rank Correlation Coefficient was not widely used in feature selection yet. In this paper, after extracting the commercial videos low-level features including color features, motion features, and shot features, a CFS-Spearman algorithm is presented and used to process the four datasets, including 'Cancer', 'Glass', 'Bank, and 'Credit', in the UCI machine learning database. The experiment results are compared with CFS and mRMR. The LibSVM classifier is utilized to test the effectiveness of CFS-Spearman. Then, the method in this paper is employed to select the low-level features of the commercial videos to predict the popularity of them. The results showed that the proposed method was better than CFS, mRMR, and Ip-norm based sparsity regularized feature selection.

2. Video Low-Level Features Extraction

2.1. Color Features. Color is an important feature of vision. The color feature set is combined with 10 features including means and variances of Brightness, Contrast, Saturation, Colorfulness, and Simplicity. Brightness is calculated by average the brightness of every pixel in every frame in HSV space. It is similar as Saturation calculation procedure. The Contrast could be expressed by the following formula:

[mathematical expression not reproducible] (1)

in which, r, g, and b represent red, green, and blue value of a pixel. Var is the variance calculation function [26].

Colorfulness is a parameter reflecting the combination of image's color. It is defined as

Cf = A + 0.3 B (2)

in which

A = [square rot of (var (r - g) + var ((r + g)/2 - b))] (3)

B = [square root of ([Mean [(r - g)].sup.2] + [{Mean [(r+g)/2 - b]}.sup.2])] (4)

Mean is the function to get the average the input value [27].

To attract the audiences' attention in the progress of movie making, the director and the cameraman always make the scenes simpler than the objects. The Simplicity is used to measure this character in some article. It is defined in [28] and the final Simplicity is the mean value of every frame.

2.2. Motion Features. Motion features reflect the changing rate of the scene or objects in the videos. It could be regarded as the moving speed between camera and the objects while shooting. In this article, the motion features are calculated as follows. Firstly, every frame is separated into 16 x 16 blocks. The pixel barycenter of every block is get, and then, the frame n and the frame n+1 are compared to obtain the barycenter changing rate of the corresponding blocks in the two neighbor frames. The motion feature mean is the mean value of pixel barycenter coordinate changing and the motion feature variance is the variance of it [29].

2.3. Shot Features. Shot features are also important for video evaluation. To get every shot in a video, the key frames, which are located at the edge of the shots, of the video should be selected firstly [30]. We compare the color histogram of every two neighbor frames to calculate the similarity of them. After key frame selection, the four features, "Shot length mean", "Shot number", "Shot length variance", and "Video length", are calculated.

Then, the 16 features, including "Brightness mean", "Contrast mean", "Saturation mean", "Colorfulness mean", "Simplicity mean", "Brightness variance", "Contrast variance", "Saturation variance", "Colorfulness variance", "Simplicity variance", "Motion mean", "Motion variance", "Trailer length", "Shot number", "Shot length mean", and "Shot length variance", are get as shown in Figure 1.

3. Feature Selection Suing CFS

When the features are extracted, the relationship between features and video evaluation is still not so clear. It is because that some features influence video viewers' evaluation but others do not. We should select the most influential feature set of the videos' evaluation. Some feature selection methods might be introduced here.

3.1. mRMR. mRMR is a typical feature dimension reduction method which use mutual information to measure the correlation between two features and feature-class. The formulas are listed as follows:

[mathematical expression not reproducible] (5)

[mathematical expression not reproducible] (6)

in which S is the feature set, [absolute value of (S)] is the feature number, c is the class index, I([x.sub.i], c) is the mutual information between the ith feature and class c, and I([x.sub.i], [x.sub.j]) is the mutual information between the ith feature and the jth feature.

The mutual information between x and y here is defined as

I (x, y) = [integral][integral] p (x, y) log p(x, y)/p(x) p(y) dx dy (7)

Then, we get the criterion of feature selection as follows:

max (D - R) (8)

3.2. CFS Algorithm. CFS is a simple feature selection method. It calculates the correlation value between every two features and feature-class to select the features related to classes most closely. As shown in (9) and (10), this method tries to maximize the Ms.

Ms = k[[bar.r]]/[square root of (k + k (k - 1) [[bar.r]])] (9)

[mathematical expression not reproducible] (10)

In the formulas above, [M.sub.s] is a measure of feature set S with k features. [[bar.r].sub.xy] is the average correlation calculation method of x and y which are all features or feature and class. N is the number of samples. According to formula (10), in the feature set S, the value of [M.sub.s] will be bigger if the average correlation between features is minor and the average correlation between features and class is bigger. Then, the feature set is an optimized one. This algorithm is called Pearson Correlation Coefficient.

3.3. Spearman Rank Correlation Coefficient. Pearson Correlation Coefficient was employed in traditional CFS. But there are some other correlation calculation methods which could be tested. Spearman Rank Correlation Coefficient is one of them. It could be defined as follows:

[mathematical expression not reproducible] (11)

In the formula above, we firstly define the random variable X and Y with N samples as ([x.sub.i], [y.sub.i]). Then, let [R.sub.i] and [S.sub.i] be the ranks of [x.sub.i] and [y.sub.i] in the corresponding sample. [bar.R] and [bar.S] are the average ranks of the sample. The Spearman Rank Correlation Coefficient described the monotonic dependence of variables X and Y. The monotonic direction could be recognized by the sign of [r.sub.xy]. When Y creases with X creasing, the sign of [r.sub.xy] is positive, and it is negative conversely. Y will not change with X while the sign of [r.sub.xy] is 0.

The linear correlation coefficient is a widely used correlation measurement and it is easy to be calculated. When the random variables are elliptical distribution, the linear correlation coefficient could express the correlation between the variables. But the short points of it is that it is nonexistent when the variables' first- and second-order moments could not be get, its value should change when the variables distribution function changed, and after nonlinear strictly increasing, the linear relationships between variables would change [24]. It is most important that the relationship could not be expressed accurately while the variables do not distribute as elliptical distribution.

The Spearman Rank Correlation Coefficient is a nonparametric statistic method. Let the rank correlation coefficient of the two variables X and Y be r(X, Y), then

r(X, Y) = [rho]([F.sub.X] (X), [F.sub.Y] (Y)) (12)

in which [F.sub.(X)] and [F.sub.(Y)] are the cumulative probability of X and Y, respectively.

The two random variables' rank correlation coefficient is the linear correlation coefficient of the cumulative probability distribution function expressed as [F.sub.X](x) = P(X [less than or equal to] x). If the inverse function of it exists, the variable FX(X) distributed as uniform distribution in [0, 1] because of the following formula:

P ([F.sub.X] (x) [less than or equal to] r) = P(x [less than or equal to] [F.sup.-1.sub.X] (r)) = [F.sub.X] ([F.sup.-1.sub.X] (r)) = r r [member of] [0, 1] (13)

So the rank correlation coefficient is just an expression of relationship after transformation from the original variables to the variables in uniform distribution. Compared with linear correlation coefficient, the rank correlation coefficient's advantages are as follows: (1) always exist; (2) does not change with edge distribution; (3) does not change after strict nonlinear transform. So, it is chosen in this paper to measure the relationships between feature and feature or feature and class.

4. Experiment Analyzing for Feature Selection

To prove the effectiveness of CFS-Spearman feature selection method in this paper, the 4 datasets, including "Breast-cancer", "Glass", "Bank", and "Credit" in the UCI machine learning database, are used as the experiment data. The detailed information of the 4 datasets is listed in the Table 1. In the experiment procedure, CFS-Spearman feature selection method was employed to select the most important features and the SVM classification was used to test the selected feature sets. In the experiment, 1/10 of all the samples were selected randomly as the testing data and the others were used as the training data. This classification procedure was repeated for 10 times for every dataset. The mean values of the correctly classification rates were showed in the tables and figures to prove the effectiveness of the method in this paper.

The experiment results were got by Matlab and LibSVM tool box. The results of CFS-Spearman feature selection were also compared with the original CFS, mRMR, and lp-norm based sparsity regularized feature selection method as shown in the tables. In Tables 3 and 8, the weighted fonts are the correctly classification rate of CFS-Spearman higher than or equal to CFS, mRMR, and lp-norm. For lp-norm based sparsity regularized feature selection, we obtained the different settings of p [member of] [0.1, 0.3, 0.5, 0.7, 0.9] in every experiment. This parameter was selected by the classification results using SVM.

Table 2 showed the 8 features and classes of dataset "Breast-cancer". As shown in Table 3, the CFS-Spearman feature selection method, original CFS, mRMR, and lp-norm (p=0.9) were used to select the features in this dataset. From the results, it is obvious that the selected features were different in most feature sets. But if using features selected by CFS-Spearman, the correct classification rates were higher than or equal to other methods in all cases.

In the second experiment, the dataset is "Glass". We can estimate whether a piece of glass is "float glass" or not according to the chemical elements in it. These elements were listed in Table 4. Same as the second experiment, the third one is about one person might be a member of bank or not. The 9 features, like "Age", "Living area", "Income", and so on, were listed in Table 5. The last experiment was about "Credit degree". There were 14 features in this dataset as shown in Table 6.

The correct classification rates were shown in Figure 2. In the figure, (a) showed the classification results of dataset "Breast-cancer". The red curve is the correct classification rate of CFS in the cases of 1-feature, 2-features, to 7-features. The green curve was for mRMR and the blue one was for CFS-Spearman. The pink curve was for lp-norm (p=0.9). The results in this subfigure are same as the data in Table 3.

Figure 2(b) showed the classification results of dataset "Glass" using different feature selection methods. Correct classification rates of CFS-Spearman algorithm in cases of 1-feature, 2-features, to 7-features were better than original CFS, mRMR, and Ip-norm (p=0.7). But if we select 8 features, the correct classification rate of CFS-Spearman algorithm was lower. When 4 features were selected, the correct classification rate was highest and the feature set included features 1, 3, 4, and 5 corresponding to Table 4.

As shown in Figure 2(c), for dataset "Bank", the correct classification rates of CFS-Spearman algorithm in cases of 1-feature, 2-features, to 8-features were better than or equal to original CFS, mRMR, and lp-norm (p=0.7). The correct classification rates were all 81.25%. Corresponding to Table 5, when we selected 2 features, the set is constructed by feature 1 and feature 6. When 4 features were selected, the set is combined with feature 1, feature 6, feature 7, and feature 8.

Figure 2(d) showed the classification results of dataset "Credit" using different feature selection methods. Correct classification rates of CFS-Spearman algorithm in cases of 1-feature, 2-features, to 13-features were better than or equal to original CFS, mRMR, and lp-norm (p=0.9). When more than 9 features were selected, the correct classification rate reached the highest value 84.2%, and the 9-features set included features 3, 5, 6, 7, 9, 11, 12, 13, and 14 corresponding to Table 4.

From Figure 2, in most cases, the correct classification rates increased with the increasing of feature number until one feature number and then decreased. So, if we want to make a classification with some features like those shown in Table 8, not all features are necessary. Some more important features should be selected by the appropriate feature selection method.

5. Videos Popularity Prediction

In this paper, the CFS-Spearman feature selection method was used in video low-level feature selecting for videos' popularity prediction. The low-level feature set included 16 features as expressed in the second part of this paper. There are 300 videos, which were downloaded from "Youtube", used in experiments. The 16 features were extracted for each video and the serial numbers of them were showed in Table 7.

To evaluate the popularity of them, the audiences' "Like/Dislike" votes numbers were employed to calculate the popularity degree as shown in

Score = LN/LN + DN x 5 (14)

in which LN is the vote number of "like" and DN is the vote number of "dislike" for a video. We set 4.7 as the threshold of classification for "good" videos and "bad" videos. It means that if the score of a video is higher than or equal to 4.7, it is a good video. Otherwise, it is regarded as bad one. All the extracted features were listed in Table 7. We used the four methods to select the features, and the selecting results were shown in Table 8. If the selected features were employed to classify the videos in to two classes, good and bad, the correct classification rates were listed in Table 8.

The SVM classification results showed that most correct classification rates of CFS-Spearman method were higher than that of the other two ones. And when the feature number is 3, the correct classification rates are the highest one which is 78%. And in this case, the features "Mean of contrast", "Variance of Simplicity", and "Variance of shot length" were selected as the most influential features. So, they could be used as the feature set to predict the popularity of commercial videos.

The correct classification rates curves were drawn in Figure 3.

The results in Table 8 were obtained by SVM using the selected feature set. Recently, some classification methods associated with deep learning received wide attention. CNN (convolution neural network) is a popular one within them. To compare the classification effectiveness, CNN was designed to test the prediction of the videos' popularity in this part using the selected 3 features. The design of CNN used in this paper was shown in Figure 4. Firstly, the selected feature set, including features 1, 3,4, 5,6, and 7, were employed as the original input data of CNN. It is because that other features, such as "Variance of motion" and "Variance of shot length", were just one scalar but not a vector or matrix.

In contrast with using SVM, the 6 features (features 1, 3, 4, 5, 6, and 7) were not the mean values of every frame in the whole video, but just uniformly selected 500 frames from a video and calculated the 6 features in every selected frame. Then, we get the input data whose size is 500x6 of CNN. The parameters in this framework were set as follows. The convolution and pooling procedure was repeated for 3 times. For the 6 features, there was no any relationship between each other. So, the convolution kernels' size was set as [m, 1]. The parameters were designed as follows.

For the first time, [m.sub.1]=51, [k.sub.1]=500, and there were 4 convolution layers in the procedure. Then, the size of feature map [C.sub.1] was 4@(450x6). After the first pooling processing with p=2, the size of feature map [S.sub.1] was 4@(225x6). For the second time, [m.sub.2]=76, [k.sub.2]=225, and there were 10 convolution layers. The size of feature map [C.sub.2] was 10@(150x6). The size of feature map [S.sub.1] was 10@(75x6). For the third time, [m.sub.3]=75, [k.sub.3]=75, and the size of feature map [S.sub.3] was 10@(1x6). We convert [S.sub.3] to a column shoes size which was (60x1). Then, the video's 3 features were transformed to a new feature set with 60 numbers. After Softmax classification, the results were obtained. The experiments were repeated for 10 times, as shown in Table 9, just like the experiments using SVM. The testing result showed that the mean correct classification rate was 61.6667, which was much lower than SVM using the 3 selected features. It is because that the 16 features were most scalars which were not suitable for CNN classification.

If we use the whole videos or some frames in them as the input data for CNN, according to the characteristic of CNN, it only pays attention to the differences between the input data in the convolution procedures or tries to get the edges in the images or videos. So, the features such as the 3 selected one, which were proved to be the influential features to the popularity of the videos, would not be calculated in the CNN framework.

6. Conclusions

This paper researched the low-level feature selection methods in commercial videos' popularity prediction. To select the more influential features in the feature set, the paper proposed a CFS-based method in which the Spearman Correlation Coefficient was employed to take place of original Pearson Correlation Coefficient. To test the method, the data in UCI machine learning database were used as the experiments data source. The widely used algorithm, mRMR, original CFS, lp-norm based sparsity regularized feature selection, and the method called CFS-Spearman algorithm presented in this paper were compared using the data. Four results showed that the method in this paper was better than the other ones.

Then, to select the influential low-level features for commercial videos, 300 videos were downloaded from Youtube. For each video, 16 features were extracted, and the videos were separated into two classes, "good" and "bad" according to their scores which were calculated through the "like/dislike" number voted by audiences. When the selected feature number is 3 by CFS-Spearman, the correct classification rates is the highest one which is 78%. The features called "Mean of contrast", "Variance of Simplicity", and "Variance of shot length" were selected as the most influential ones.

Finally, the SVM classification was compared with the popular classification method CNN. The results showed that because the 16 features were most scalars, the SVM was more suitable for this target.


See Table 10.

Data Availability

The data used to support the findings of this study are included within the article.

Conflicts of Interest

The authors declare that they have no conflicts of interest.


The research work of this paper was supported by the Science and Technology Development Program Fund of Science and Technology Department Jilin province, China (no. 20150414051GH).


[1] L. Xiang-yu, Research on No-reference Video Quality Assessment Method, Zhejiang University, 2012.

[2] C.-Y. Ma, S.-M. Li, R.-Z. Ma, D. Zhu, and X.-X. Guo, "Objective assessment of stereo video quality based on motion and disparity information," Journal of Optoelectronics Laser, vol. 24, no. 10, pp. 2002-2009, 2013.

[3] F.-Q. Zhang, J.-L. Li, G. Li, J.-J. Man, and G. Chen, "Video quality assessment based on quaternion singular value decomposition," Acta Electronica Sinica, vol. 39, no. 1, pp. 219-223, 2011.

[4] S. Huang, D. Yang, G. Yongxin, and X. Zhang, "Combined supervised information with PCA via discriminative component selection," Information Processing Letters, vol. 115, no. 11, pp. 812-816, 2015.

[5] A. Vinay, C. Kumar A, G. Shenoy R et al., "ORB-PCA based feature extraction technique for face recognition," Procedia Computer Science, vol. 58, pp. 614-621, 2015.

[6] E. V. Patridge, P. C. Gareiss, M. S. Kinch, and D. W. Hoyer, "An analysis of original research contributions toward FDA-approved drugs," Drug Discovery Therapy, vol. 20, no. 10, pp. 1182-1187, 2015.

[7] S. A. Vinay, V. S. Shekhar, K. N. B. Murthy et al., "Face recognition using gabor wavelet features with PCA and KPCAA comparative study," Procedia Computer Science, vol. 57, pp. 650-659, 2015.

[8] Z. Xiao-guang, S. Zheng, X. Gui-yun et al., "A feature selection algorithm combining within-class variance with correlation measure," Journal of Harbin Institute of Technology, vol. 3, no. 03, pp. 132-136, 2011.

[9] Z. Dechuan and Z. Zhihua, "A correlation projection score-based feature selection algorithm," Journal of Frontiers of Computer Science and Technology, vol. 1, no. 2, pp. 138-145, 2007

[10] S. Dalai, B. Chatterjee, D. Dey, S. Chakravorti, and K. Bhattacharya, "Rough-set-based feature selection and classification for power quality sensing device employing correlation techniques," IEEE Sensors Journal, vol. 13, no. 2, pp. 563-573, 2013.

[11] H.-H. Hsu and C.-W. Hsieh, "Feature selection via correlation coefficient clustering," Journal of Software , vol. 5, no. 12, pp. 1371-1377, 2010.

[12] P. Moradi and M. Rostami, "A graph theoretic approach for unsupervised feature selection," Engineering Applications of Artificial Intelligence, vol. 44, pp. 33-45, 2015.

[13] Z. Li, J. Liu, Y. Yang, X. Zhou, and H. Lu, "Clustering-guided sparse structural learning for unsupervised feature selection," IEEE Transactions on Knowledge and Data Engineering, vol. 26, no. 9, pp. 2138-2150, 2014.

[14] X. Lan, A. J. Ma, and P. C. Yuen, "Multi-cue visual tracking using robust feature-level fusion based on joint sparse representation," in Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR '14), pp. 1194-1201, Columbus, OH, USA, June 2014.

[15] X. Lan, A. J. Ma, P. C. Yuen, and R. Chellappa, "Joint sparse representation and robust feature-level fusion for multi-cue visual tracking," IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 5826-5841, 2015.

[16] X. Lan, S. Zhang, P. C. Yuen, and R. Chellappa, "Learning common and feature-specific patterns: a novel multiple-sparse-representation-based tracker," IEEE Transactions on Image Processing, vol. 27, no. 4, pp. 2022-2037, 2018.

[17] R. Tibshirani, "Regression shrinkage and selection via the lasso," Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 58, no. 1, pp. 267-288, 1996.

[18] S. Xiang, F. Nie, G. Meng, C. Pan, and C. Zhang, "Discriminative least squares regression for multiclass classification and feature selection," IEEE Transactions on Neural Networks and Learning Systems, vol. 23, no. 11, pp. 1738-1754, 2012.

[19] D. Kong and C. Ding, "Non-convex feature learning via [l.sub.p,[infinity]] operator," in Proceedings of the National Conference on Artificial Intelligence, pp. 1918-1924, July 2014.

[20] H. Peng and Y. Fan, "Direct sparsity optimization based feature selection for multi-class classification," in Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI '16), pp. 1918-1924, July 2016.

[21] H. Wang, T. M. Khoshgoftaar, and A. Napolitano, "Stability of filter- and wrapper-based software metric selection techniques," in Proceedings of the 15th IEEE International Conference on Information Reuse and Integration (IEEE IRI '14), pp. 309-314, Redwod City, Calif, USA, August 2014.

[22] S. Ningqing, "A network intrusion detection system based on neural networks and the cfs-based feature selection," Computer Engineering & Science, vol. 32, no. 6, pp. 37-39, 2010.

[23] M.-T. Puth, M. Neuhauser, and G. D. Ruxton, "Effective use of Spearman's and Kendall's correlation coefficients for association between two measured traits," Animal Behaviour, vol. 105, pp. 77-84, 2015.

[24] X. Xu, Z. Yan, D. Feng, Y. Wang, and L. Cao, "Probabilistic load flow calculation based on rank correlation coefficient of input random variables," Automation of Electric Power Systems, vol. 38, no. 12, pp. 54-61, 2014.

[25] J. Feng, "Consistent test of accelerated storage degradation failure mechanism based on rank correlation coefficient," Journal of Aerospace Power, vol. 26, no. 11, pp. 2439-2444, 2011.

[26] M. J. Swain and D. H. Ballard, "Color indexing," International Journal of Computer Vision, vol. 7, no. 1, pp. 11-32, 1991.

[27] S. Hasler and S. Susstrunk, "Measuring colorfulness in real images," vol. 5007, pp. 87-95, 2003.

[28] J. S. Pedro and S. Siersdorfer, "Ranking and classifying attractiveness of photos in folksonomies," in Proceedings of the 18th International World Wide Web Conference (WWW '09), pp. 771780, Madrid, Spain, April 2009.

[29] L. Yiwen and T. Xiaoou, "Photo and video quality evaluation: focusing on the subject," in Proceedings of the European Conference on Computer Vision, part 3, pp. 386-399, Marseille, France, October 2008.

[30] S. K. Kuanar, R. Panda, and A. S. Chowdhury, "Video key frame extraction through dynamic Delaunay clustering with a structural constraint," Journal of Visual Communication and Image Representation, vol. 24, no. 7, pp. 1212-1227, 2013.

Xiangmin Lun, (1,2) Mingxuan Wang, (2) Zhenglin Yu (iD), (1) and Yimin Hou (iD) (2)

(1) College of Mechanical and Electric Engineering, Changchun University of Science and Technology, Changchun, China

(2) School of Automation Engineering, Northeast Electric Power University, Jilin, China

Correspondence should be addressed to Zhenglin Yu;

Received 1 August 2018; Revised 21 September 2018; Accepted 24 September 2018; Published 10 October 2018

Academic Editor: Alexander Loui

Caption: Figure 1: Video features extraction procedure.

Caption: Figure 2: Correct classification rates of different datasets using the 3 methods. (a) Correct classification rates for dataset "Breast-cancer". (b) Correct classification rates for dataset "Glass". (c) Correct classification rates for dataset "Bank". (d) Correct classification rates for dataset "Credit".

Caption: Figure 3: Correct classification rate using video features by different methods.

Caption: Figure 4: The designed CNN for video popularity prediction.
Table 1: The 4 datasets in UCI database.

                Sample   Feature    Class
Data set         Number   number    number

Breast-cancer     206        8        2
Glass             144        9        2
bank               30        9        2
Credit            998       14        2

Table 2: The 8 features and classes of dataset "Breast-cancer".


 1        2            3             4             5           6

Age   Menopause   Tumour size   Tumour node   Canceration    Tumour
                                                degree      position

         Features                 Class

 1       7            8

Age    Tumour    Radiotherapy   Benign or
      quadrant      or not      malignant

Table 3: Classification results using features selected by
different methods.

               CFS-Spearman                     CFS

                        Correct                      Correct
Feature              Classification               Classification
number    Features      rate (%)      Features       Rate (%)

k=l         (5)         70.1389          (5)         70.1389
k=2        (4-5)           75           (4,8)        71.5278
k=3       (1.4-5)       79.1667        (4-5,7)       76.3889
k=4       (1.3-5)          75         (4-5,7-8)      74.3056
k=5       (1.3-6)          75         (1,3-5,8)      74.3056
k=6       (1-5,8)       75.6944      (13-5,7-8)      75.6944
k=7      (1-5,7-8)      73.6111       (1-5,7-8)      73.6111

                   mRMR                   lp-norm (p=0.9)

                        Correct                      Correct
Feature              Classification               Classification
number    Features      rate (%)      Features       rate (%)

k=l         (5)         70.1389          (5)         70.1389
k=2        (2,5)        74.3056         (2,5)        74.3056
k=3       (2,4-5)          75          (2,4-5)          75
k=4       (2,4-6)       73.6111       (2,4-5,7)      74.3056
k=5      (2,4-6,8)      74.3056      (2,4-5,7-8)     74.3056
k=6       (2,4-8)       71.5278      (1-2,4-5,7-8    72.9167
k=7      (1-2,4-8)      75.6944       (1-5,7-8)      71.5278

Table 4: The 9 features and classes of dataset "Glass".


   1        2          3          4           5          6

Iridium   Sodium   Magnesium  Aluminium    Silicon   Potassium

             Features               Class

   1         7        8       9

Iridium   Calcium   Barium   Iron   Float
                                    or not

Table 5: The 9 features and classes of dataset "Bank".


 1      2        3         4         5          6         7

Age  Living    Income   Marital   Children   Have a    Deposit
       area             status     umber       Car
                                             or not

       Features             Class

 1       8          9

Age   Account    Mortgage    Bank
      exchange             member
                            or not

Table 6: The 14 features and classes of dataset "Credit".


1              2         3        4          5             6

Keeping     Credit    Purpose   Limit   Instalment     Personal
Time        record                        promise     information

8              9        10       11         12            13

Property      Age     Housing    Job      Family         Cell
rights                                    number         phone

     Features           Class

1               7

Keeping     Residence  Credit
Time                    degree

8              14

Property    Foreign    Credit
rights       worker     degree
             or not

Table 7: Extracted video features and classes.

1                  2             3              4             5

Mean of       Variance of     Mean of        Mean of       Mean of
motion          motion       brightness     contrast      saturation

9                 10             11            12             13

Variance of   Variance of   Variance of    Variance of   Mean of shot
contrast      saturation    colorfulness   simplicity       length

1                  6              7             8          Class

Mean of         Mean of        Mean of     Variance of    Good(l)
motion        colorfulness   simplicity     brightness    Bad(0)

9                  14            15             16

Variance of   Variance of    Shot number   Video length   Good(1)
contrast      shot length                                 Bad(0)

Table 8: Experiment results for video popularity prediction
using different methods.

                 CFS-Spearman                      CFS

Feature                     classificat-ion
number      Feature set         rate (%)        Feature set

k=l             (14)            56.6667             (5)
k=2            (4.14)           69.3333            (5,14)
k=3          (4,12,14)             78            (5,13-14)
k=4         (4,7,12,14)         75.3333          (5,13-15)
k=5           (2-5,7)           77.3333          (5,12-15)
k=6          (2-5,7,14)            76            (5,12-16)
k=7          (1-5,7,14)            76           (5-6,12-16)
k=8         (1-5,7-8,14)        74.6667        (5-6,10,12-14)
k=9           (1-8,14)          74.6 667        (5-6,10-16)
k=10        (1-8,13-14)         74.6 667         (5-6,9-16)
k=11        (1-8,13-15)         74.6 667         (4-6,9-16)
k=12        (1-8,12-15)         74.6 667        (1,4-6,9-16)
k=13        (1-8,12-16)            76           (1,4-7,9-16)
k=14       (1-8,10-14,16)          72             (1,4-16)
k=15        (1-8,10-16)         75.3333           (1,3-16)

                 CFS                         mRMR

               Correct                                   Correct
Feature    classificat-ion                           classificat-ion
number         rate (%)           Feature set            rate (%)

k=l            56.6667                (12)               50.6667
k=2            59.3333               (4,12)              63.3333
k=3            56.6667             (4,12,16)                76
k=4            68.6667            (4,9,12,16)            73.3333
k=5            69.3333           (4,6,9,12,16)           74.6667
k=6            75.3333          (2,4,6,9,12,16)          74.6667
k=7            74.6667         (2,4,6,9,12,15-16)           76
k=8            74.6667         (2,4-6,9,12,15-16)           76
k=9            74.6667          (2-6,9,12,15-16)         74.6667
k=10           74.6667        (2-6,9-10,12,15-16)        74.6667
k=11           74.6667        (2-7,9-10,12,15-16)        74.6667
k=12           74.6667          (2-7,9-12,15-16)         74.6667
k=13           74.6667          (1-7,9-12,15-16)         74.6667
k=14              76              (1-12,15-16)              74
k=15           75.3333            (1-12,14-16)           75.3333

                      lp-norm (p=0.9)

Feature                           classificat-ion
number         Feature set            rate (%)

k=l                (14)               56.6667
k=2               (5,14)              59.3333
k=3             (4,12,14)             64.6667
k=4            (4,9,12,14)               72
k=5           (4,5,9,12,14)           74.3333
k=6          (2,4,5,9,12,14)          74.6667
k=7         (1,2,4,5,9,12,14)            76
k=8         (1,2,4-6,9,12,14)         74.6667
k=9        (1,2,4-6,9,12,14-15)       74.6667
k=10         (1-6,9,12,14-15)         74.6667
k=11         (1-6,9,12,14-16)            72
k=12        (1-6,8,9,12,14-16)           72
k=13          (1-9,12,14-16)             72
k=14        (1-9,11-12,14-16)         71.6667
k=15           (1-12,14-16)           75.3333

Table 9: The classification results using CNN.

                 Correct classification rate (%)

1       2      3       4         5         6         7         8

70   63.3333   60   66.6667   56.6667   63.3333   53.3333   56.6667

   rate (%)

1    9      10       Mean

70   60   66.6667   61.6667

Table 10

No.                                 NAME

1                      Chairman of the Board Trailer
2               "Daniel der Zauberer" (official trailer) HQ
3                    Dinoshark (2011)--Official Trailer
4                       From Justin To Kelly Trailer
5                           Gigli (2003) Trailer
6                      Growth--Official Trailer [HD]
7               House ofThe Dead--Official HD Movie Trailer
8                     House OfThe Dead Trailer (2003)
9                  A Fox's Tale (Kis Vuk) English Trailer
10                       Jack and Jill Trailer 2011
11               Kaboom Movie Trailer 2011 Official Trailer
12           Manborg (2012)--Official Trailer--Horror Movies HD
13                   Mars Needs Moms Movie Trailer (HD)
14            Mega Python VS Gatoroid (2011)--Official Trailer
15               Melissa Molinaro--The Hillz (2004) Trailer
16                   Outpost 31--2013 OFFICIAL Trailer
17             Back to the Future 4 Official Trailer HD 720p
18                          piranhaconda trailer
19                    Quantum Apocalypse 2010 Trailer
20         the Animals (2012)--Official Trailer--Horror Movies HD
21                    RoboCop 2013 Trailer (official)
22                          Sand Sharks Trailer
23                Sharktopus (2010)--Official Trailer [HD]
24                   Son of The Mask 2005 High Quality
25                     Son of the Mask Movie Trailer
26         Superbabies: Baby Geniuses 2 (2004) Trailer [Official]
27                          SURF SCHOOL Trailer
28                   Bad ass (2012) Official Trailer HD
29                   The Double (2011) Movie Trailer HD
30                    The Fifth Element (1997) Trailer
31                      The Final Sacrifice Trailer
32                The Hottie and The Nottie Movie Trailer
33          The Human Centipede--Official Movie Trailer 2010 [HD]
34           The Legend of the Psychotic Forest Ranger (2012)--
                              Official Trailer
35             Bad Kids Go to Hell Official Trailer 2 (2012)
36                   Titanic: The Legend Goes On Trailer
37                    Tony Blair Witch Project--Trailer
38            Trailer--NOOBZ--Official Movie Trailer HD (2012)
39            Transformers 4: The Return of Megatron Trailer HD
40                  Yes Sir! Trailer (Official Version)
41                 YOUNG ADULT Trailer 2011 Official [HD]
42                         Zombie Nation Trailer
43          Battlefield America--Official Exclusive Trailer [HD]
44                          Ben Arthur--Trailer
45          Book of Shadows Blair Witch 2 [a steFANedit] TRAILER
46          All Superheroes Must Die Official Trailer #1 (2013)--
                               Jason Trost Mo
47         New Year's Eve Movie CLIP #2--This is Not a Training
                               Bra! (2011) H
48     World Of Heroes--Exclusive Superbowl XLIV TV Spot--TRUE 720 HD
49                 Re-Kill Official Trailer (2011 Movie)
50          "Snow Doesn't Melt Forever ..." (official trailer)
51                   District 13: Ultimatum' Trailer HD
52                Cosmopolis (2012)--Official Trailer [HD]
53                   Four (2012)--Official Trailer [HD]
54                Dark Tide (2012)--Official Trailer [HD]
55              Griff the Invisible (2010)Movie Trailer--HD
56                   Zone Of The Dead--Official Trailer
57       The Wicked Official Teaser Trailer (2012) Horror Movie HD
58                   The Troll Hunter--Official Trailer
59                        American Hustle Trailer
60         Hammer of the Gods Official Trailer #1 (2013)--Viking
                                  Movie HD
61                             Tiptoes (2003)
62                  Superbabies: Baby Geniuses 2 (2004)
63                           Sharktopus (2010)
64                          Disaster Movie (2008)
65                           Vampire Dog (2012)
66                        Super Mario Bros (1993)
67                        Empire Of The Apes (2013)
68                            CMe Dance (2009)
69                        Santa With Muscles (1996)
70                             Quigley (2003)
71                     Dinocroc Vs Supergator (2010)
72                     The Hottie & The Nottie (2008)
73                           Hobgoblins (1988)
74                           Samurai Cop (1989)
75                     Butterfinger The 13th (2011)
76                          Transmorphers (2007)
77                               LOL (2012)
78                   Anaconda 4: Trail Of Blood (2009)
79                     Mega Python Vs Gatoroid (2011)
80                          A Talking Cat (2013)
81                       Battlefield America (2012)
82                   Mega Shark Vs Giant Octopus (2009)
83                 Abraham Lincoln: Vampire Hunter (2012)
84                            Old Dogs (2009)
85                           Rottweiler (2004)
86                     I Hate Valentine's Day (2009)
87                            The Room (2003)
88                       Age Of The Hobbits (2012)
89                           Leprechaun (1993)
90                1 ROBOCOP--Official Trailer (2014) [HQ]
91            White House Down--Official Trailer (2013) [HD]
                            Channing Tatum, Jam
92       Scary Movie 5 Official TRAILER #1 (2013)--Charlie Sheen,
                                 Ashley Tis
93        Spiders 3D Official Trailer #1 (2013)--Science Fiction
                                  Movie HD
94              Evil Dead Trailer 2013 Movie--Official [HD]
95         SHARKNADO--Official Asylum Trailer--TOO VIOLENT FOR TV
96       Bad Milo Official Trailer #1 (2013)--Ken Marino Comedy HD
97          Hell Baby Official Trailer #1 (2013)--Horror Comedy
                                  Movie HD
98                    DIANA OFFICIAL TRAILER 2013 (HD)
99         Killing Season Official Trailer #1 (2013)--Robert De
                             Niro, John Travolt
100              Iron Sky Official Theatrical Trailer [HD]
101          Adore Official Trailer #1 (2013)--Robin Wright,
                            Naomi Watts Movie H

102                           Lincoln Trailer
103     Behind the Candelabra Trailer (Matt Damon--Michael Douglas)
104     Assault on Wall Street Official Trailer #1 (2013)--Dominic
                                Purcell, Eri
105          Chennai Express--Official Trailer 2013--Shah Rukh
                              Khan--Deepika P
106      Rapture-Palooza Official Trailer #2 (2013)--Anna Kendrick
                                  Movie HD
107      *The Smurfs 2* Official Trailer #1 Starring Neil Patrick
                             Harris (2013) [HD]
108     Temptation Official Trailer #1 (2013)--Tyler Perry Movie HD
109             The Tree of Life Movie Trailer Official (HD)
110                          3 Geezers! Trailer
111      The Stranger Within Exclusive Official Trailer #1 (2013)
                               HD william bal
112         Jug Face Official Trailer 1 (2013)--Horror Movie HD
113                         ATLANTIC RIM trailer
114            Twilight Breaking Dawn Part 2 Official Trailer
115             Zero Dark Thirty--Official Trailer #2 (HD)
116         NTR Jr Ramayya Vasthavayya--Theatrical Trailer--Jr
                                NTR, Samatha
117         Shuddh Desi Romance--Official Theatrical Trailer--
118       The Demented Official Trailer 1 (2013)--Horror Movie HD
119               Albatross Official Trailer #1 (2012) HD
120        House of Pleasures Official Trailer #1--L'Apollonide
                              Movie (2011) HD
121        Official Call of Duty : Ghosts Single Player Campaign
122    Magic Magic Official Trailer #1 (2013)--Michael CeraMovie HD
123          Wadjda Offical Trailer (2013)--Haifaa Al Mansour
124        The Colony Official International Trailer #1 (2013)--
                             Laurence Fishburn
125                          Eden Movie Trailer
126            Thanks For Sharing Official Trailer #1 (2013)
127                 Trailer: Robo Cop TRAILER 1 (2014)
128                   Need for Speed Official Trailer
129                     NEED FOR SPEED Movie Trailer
130           Trailer: Her TRAILER 1 (2013)--Joaquin Phoenix,
                               Scarlett Johan
131                        PARADISE Movie Trailer
132      Jobs Official Trailer #1 (2013)--Ashton Kutcher Movie HD
133           The To Do List Trailer 2013 Movie--Official [HD]
134      Ender's Game Official Trailer #2 (2013)--Asa Butterfield,
135      Scary Movie 5 Official TRAILER #1 (2013)--Charlie Sheen,
136                     BOUNTY KILLER Movie Trailer
137              ANOTHER EARTH trailer 2011 official movie
138     Behind the Candelabra Trailer (Matt Damon--Michael Douglas)
139      Empire State Official Trailer #1 (2013)--Dwayne Johnson,
                                 Liam Hems
140         Haunter Official Trailer #1 (2013)--Abigail Breslin
                                  Movie HD
141    Baggage Claim Trailer 2013 Paula Patton Movie--Official [HD]
142                 Special Forces Movie Trailer (2012)
143                    WINNIE MANDELA Movie Trailer
144                    7500--Official Movie Trailer
145      Biryani official teaser--Karthi, Hansika, Venkat Prabhu,
                                 Yuvan, Pre
146                     Date Movie--Trailer (2006)
147                    Emperor Movie Trailer (2013)
148      Squirrels Teaser Trailer (2014)--Squirrel Horror Movie HD
149                   BA PASS Official Movie Trailer
150       Bangaru Kodi Petta--Telugu Movie Trailer--Swathi Reddy
                                 & Navdeep
151         Ainthu Ainthu Ainthu Movie Trailer--Nikhils Channel
152              Michael Bay's THE LAST SHIP Series Trailer
153                Monsters Movie Trailer Official (HD)
154             The Tree of Life Movie Trailer Official (HD)
155      Fired Trailer--Bollywood Adult Horror Movie--Rahul Bose,
                                Militza Rad
156        Battle of the Year Trailer 2013 Movie--Official [HD]
157           jOBS Movie CLIP (2013)--Ashton Kutcher Movie HD
158                         Vamps Movie Trailer
159         Naked As We Came (2012) Movie Trailer (Gay Themed)
160             Evil Dead Trailer 2013 Movie--Official [HD]
161       NABAR--New Punjabi Movie--Official Theatrical Trailer--
                                Latest Punj
162         Raja Huli Promo Kannada--Yash, Meghana Raj--Latest
                                 Kannada Mo
163                   Lucky (2011)--Movie Trailer--HD
164     Samrajyam 2 Son Of Alexander Malayalam Movie Trailer--Unni Muk
165      Metro Official Trailer #2 (2013)--Russian Disaster Movie HD
166   Once Upon A Time In Shanghai Official Movie Trailer 2013 in HD
167        Directors special Kannada movie Latest Trailer--Guru
                                Prasad, Ara
168   Spring Breakers Trailer 2013 Selena Gomez Movie--Official [HD]
169                  The Assassins Movie Trailer (2013)
170                SHELL (film 2013) official UK trailer
171                New Moon Movie Trailer--Official (HD)
172                   Prom Movie Trailer Official (HD)
173                  Youth of Christ-The Movie Trailer
174                 Universal Soldier 4 Red Band Trailer
175                        Sahara--Movie Trailer
176                     Hardwired movie Trailer 2009
177                      Official Watchmen Trailer
178                         Casino Royale teaser
179                   The official Cloverfield trailer
180         Terminator 4 Salvation teaser trailer 2009 official
181     Battle Los Angeles--Official Movie Trailer #1 (2011) US--HD
182                Mission: Impossible Trailer HQ (1996)
183          Marvel's The Avengers Super Bowl XLVI Commercial
184             Iron Man 3 Trailer UK--Official Marvel--HD
185            Sleepless In Seattle: Recut as a horror movie
186           X-Men: First Class Movie Trailer Official (HD)
187        Harry Potter and The Deathly Hallows Part 2 Trailer
                               Official (HD)
188                            Bubble Trailer
189            House of The Dead--Official HD Movie Trailer
190                    Paranormal Activity 2' Trailer
191         Pirates of the Caribbean 3--At World's End Trailer
192                 District 9--Official Trailer 2 [HD]
193                  The Departed--Trailer--(2006)--HQ
194                          Iron Man 2 Trailer
195                         THE CRAZIES--Trailer
196                   The Dark Knight HD 1080p Trailer
197                       'Inception' Trailer 2 HD
198           The Dark Knight Rises--Official Trailer #3 [HD]
199                  The Hobbit: An Unexpected Journey
200     World War Z Official Trailer #1 (2013)--Brad Pitt Movie HD
201               Independence Day--Official  Trailer [HD]
202                 Prometheus--Official Full HD Trailer
203    Transformers 3 Dark of the Moon Teaser Trailer--Official (HD)
204         Rise of the Planet of the Apes--HD Trailer 2--(2011)
205            Harry Potter and the Sorcerer's Stone Trailer
206         RESIDENT EVIL 5 Retribution Trailer 2--2012 Movie--
                               Official [HD]
207            TOTAL RECALL Trailer 2012 Movie--Official [HD]
208            Trailer: GREAT GATSBY Trailer (2012) Movie HD
209           THE LUCKY ONE Trailer 2012 Movie--Official [HD]
210                TED Movie Trailer 2012--Official [HD]
211     FLIGHT Trailer 2012 Denzel Washington Movie--Official [HD]
212   Killing Them Softly Trailer 2012 Brad Pitt Movie--Official [HD]
213                          Jarhead Trailer HD
214               Stand Up Guys Official Trailer #1 (2012)
215                Trailer: Pitch Perfect Trailer (2012)
216             Seven Psychopaths Official Trailer #1 (2012)
217            RUBY SPARKS Trailer 2012 Movie--Official [HD]
218              Wreck-It Ralph Official Trailer #1 (2012)
219           Trailer: Hit And Run Official Trailer #1 (2012)
220     The Amazing Spider-Man New Trailer 2 Official 2012 [1080 HD]
221       The Lone Ranger Official Trailer #2 (2012)--Johnny Depp
                                  Movie HD
222     THE CAMPAIGN Trailer 2012--Will Ferrell movie--Official [HD]
223        Pitch Perfect Trailer Clip--2012 Movie--Official [HD]
224                        Hitchcock Trailer 2012
225          Forrest Gump Trailer (Movie release: July 6, 1994)
226            Trailer: The Butterfly Room TRAILER 1 (2012)
227              Best New Movie Trailers--February 2012 HD
228               The Imposter--Official Trailer HD (2012)
229                   Iron Man 2 Trailer 2 (OFFICIAL)
230                          500 Days of Summer
231        Pirates of the Caribbean: On Strange Tides--Trailer 1
232                         SOURCE CODE--Trailer
233            Official SALT Trailer--In Theaters 7/23/2010
234                           FANTASTICMR. FOX
235                         John Carter Trailer
236                    JUST WRIGHT--Official trailer
237                         Bad Teacher- Trailer
238                    Supernatural Comedy Trailer HD
239                          Predators Trailer
240                         GASLAND Trailer 2010
241          I Spit On Your Grave (2010)--Official Trailer [HD]
242                 The Social Network Official Trailer
243                 New Beastly Movie Trailer--Official
244               "Shutter Island"--Official Trailer [HD]
245                         Carriers Trailer(HD)
246                  The Crazies--Official Trailer [HD]
247                 "Brothers"--Official Trailer [HQ HD]
248                      SURROGATES--Bruce Willis
249                   Julie & Julia--Official Trailer
250                  LITERAL Tron Legacy Trailer Parody
251                The Hurt Locker--Official Trailer [HD]
252                8 Mile Official Trailer #1--(2002) HD
253                Road To Perdition Trailer (2002) [HD]
254              A Walk To Remember Official Trailer (HD)
255                      Spider Man--Trailer [2002]
256                   Immortals--Official Trailer [HD]
257             The Tree of Life Movie Trailer Official (HD)
258         What's Your Number? Official Movie Trailer 2011 HD
259           The Darkest Hour Trailer 2011 Movie Official HD
260            The Bucket List Official Trailer #1--(2007) HD
261                     Halloween 2007 Trailer (HD)
262                      ANOTHER EARTH trailer 2011
263                 John Carter Fan Trailer 2 "Heritage"
264                     REC 2--Official Trailer [HD]
265       GONE Trailer 2012--Amanda Seyfried Movie--Official [HD]
266             The Human Experience--Official Trailer [HD]
267               Paranormal Activity 4 Trailer # Extended
268                Casino Royale--Official  Trailer [HD]
269                   Serenity (2005) Trailer 1080p HD
270        Harry Potter and the Goblet of Fire--Official Trailer
                              [2005][720p HD]
271                      Motorstorm E3 2005 trailer
272           The Bourne Supremacy--Official HD Trailer [2004]
273                   Being Flynn Official Trailer #1
274                         Puss in Boots (2011)
275                     I'll Be Seeing You (2004) HD
276         Iron Man 3 Official Trailer (2013) Marvel Movie HD
277              A Haunted House Official Trailer #1 (2013)
278              Now You See Me Official Trailer #1 (2013)
279                Pacific Rim Official Trailer #1 (2013)
280        The Place Beyond the Pines Official Trailer #1 (2013)
281                 The Tower Official Trailer #1 (2013)
282        Star Trek Into Darkness (NEW) Official Trailer (2013)
283                  Die Hard 5 Official Trailer (2013)
284              Identity Thief Trailer 2012 Official [HD]
285                   Red 2 Official Trailer #1 (2013)
286    Safe Haven Trailer 2013 Movie Nicholas Sparks--Official [HD]
287                 The Heat Official Trailer #1 (2013)
288       Anchorman 2: The Legend Continues Official Teaser (2013)
289            The Host Trailer #2--2013 Movie--Official [HD]
290     Jack the Giant Killer Trailer 2012 Official 2013 Movie [HD]
291   [720p] Official Rurouni Kenshin Action Movie Promo Trailer 2012
292                    TRON: LEGACY Official Trailer
293                    Trailer: Man of Steel Teaser
294          Trailer: Oz the Great and Powerful TRAILER (2013)
295   End Of Watch Official Trailer #1 (2012) Jake Gyllenhaal Movie HD
296                  Dark Shadows Trailer (Tim Burton)
297    The Man With The Iron Fists Trailer 2012 Movie--Official [HD]
298                  The Dark Knight Rises trailer 2012
299                   SKYFALL--Official Teaser Trailer
300                   MEN IN BLACK 3--Official Trailer

No.                      LINK

2 4
13 Ezk
19 hU
28 Wd6XtSmWI
30 k
37 MJmqA
55 AdqeDeo
57 NBb1ps
64 2BSUqg
65 j2fC4c
                _embedded&v=3k rel LhOk
                _embedded&v=vYrlYGe YT4
100 IndUbcxc
106 N1zsqo
109 0
115 JNz5Vbg
120 Dgbj E5c
122 AlgW6Lw
126 OkBBzdew
130 tpw0
146 Vb-Q3Q
153 coo
154 0
155 yeLPc4
158 8
180 8
187 kDb-pRCds
227 rzjmN7so
228 o
231 9A-cUEJc
253 dNY
257 0
290 84U
300 L24
COPYRIGHT 2018 Hindawi Limited
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2018 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Title Annotation:Research Article
Author:Lun, Xiangmin; Wang, Mingxuan; Yu, Zhenglin; Hou, Yimin
Publication:Advances in Multimedia
Article Type:Report
Date:Jan 1, 2018
Previous Article:Advanced Visual Analyses for Smart and Autonomous Vehicles.
Next Article:Temporal Activity Path Based Character Correction in Heterogeneous Social Networks via Multimedia Sources.

Terms of use | Privacy policy | Copyright © 2021 Farlex, Inc. | Feedback | For webmasters |