Currently, in the field of video tracking, the typical Siamese network based algorithms only locate the center point of target, which results in poor locating performance on fast-deformation objects. Therefore, a real-time video tracking algorithm based on Siamese detection network called Siamese-FC Region-convolutional neural network (SiamRFC) was proposed. SiamRFC can directly predict the center position of the target, thus dealing with the rapid deformation. Firstly, the position of the center point of the target was obtained by judging the similarity. Then, the idea of object detection was used to return the optimal position by selecting a series of candidate boxes. Experimental results show that SiamRFC has good performance on the VOT2015|16|17 test sets.

To solve the problem that traditional video emotional analysis methods can not work effectively and the results are not easy to explain, a video shot emotional analysis approach based on time-sync comments was proposed, as a basis for the recommendation of video shots. First, a formal description of video shots recommendation based on emotion analysis was studied. Then, after analyzing the classification of time sync comments based on Latent Dirichlet Allocation (LDA) topic model, the emotional vector of the words in time-sync comments were evaluated. Meanwhile, the emotion relationships among the video shots were analyzed for video shots recommendation. The recommendation precision of the proposed method was 28.9% higher than that of the method based on Term Frequency-Inverse Document Frequency (TF-IDF), and 43.8% higher than that of traditional LDA model. The experimental results show that the proposed model is effective in analyzing the complex emotion of different kinds of text information.

Concerning the problem that Stack Auto-encoder (SA) easily traps to overfitting, which may reduce the accuracy of spam classification, a modified SA method based on dynamic dropout was proposed. Firstly, the specificity of the spam classification was analyzed, and the dropout algorithm was employed in SA to handle overfitting. Then according to the fault of dropout algorithm that making some nodes be in the stall state for a long time, an improved algorithm of dropout was proposed. The static dropout rate was replaced by dynamic dropout rate which decreased with training steps using dynamic function. Finally, the dynamic dropout algorithm was used to improve the pretraining model of SA. The simulation results show that compared with Support Vector Machine (SVM) and Back Propagation (BP) neural network, the average accuracy of the modified SA is 97.66%. And the Matthews correlation coefficient of every dataset is higher than 89%. Matthews correlation coefficient of the modified SA on every dataset is 3.27%, 1.68%, 2.16%, 1.51%, 1.58% and 1.07% higher than that of the conventional SA separately. The experimental results show that the modified SA using dynamic dropout has higher accuracy and better robustness.