Deepfake Video Detection Based on Improved CapsNet and Temporal–Spatial Features

Rapid development of deepfake technology led to the spread of forged audios and videos across network platforms,presenting risks for numerous countries,societies,and individuals,and posing a serious threat to cyberspace security.To address the problem of insufficient extraction of spatial features and the fact that temporal features are not considered in the deepfake video detection,we propose a detection method based on improved CapsNet and temporal–spatial features(iCapsNet–TSF).First,the dynamic routing algorithm of CapsNet is improved using weight initialization and updating.Then,the optical flow algorithm is used to extract interframe temporal features of the videos to form a dataset of temporal–spatial features.Finally,the iCapsNet model is employed to fully learn the temporal–spatial features of facial videos,and the results are fused.Experimental results show that the detection accuracy of iCapsNet–TSF reaches 94.07%,98.83%,and 98.50%on the Celeb-DF,FaceSwap,and Deepfakes datasets,respectively,displaying a better performance than most existing mainstream algorithms.The iCapsNet–TSF method combines the capsule network and the optical flow algorithm,providing a novel strategy for the deepfake detection,which is of great significance to the prevention of deepfake attacks and the preservation of cyberspace security.

Temporal and Spatial Variation and Distribution Characteristics of Maximum and Minimum Temperature from 1971 to 2008 in Tibet

Based on temperature data of meteorological stations from 1971 to 2008 in Tibet,the temporal and spatial variation of maximum andminimum temperature in Tibet was analyzed.The results showed that both maximum temperature andminimum temperature increased distinctly,the warming amplitude of winter was the highest among the four seasons,and next came spring.The increment ofminimum temperature was visibly over that of maximum temperature,particularlyminimum temperature in winter with significant increment.For spatial variation,maximum temperature in most stations increased except particular stations,while theminimum temperature in all stations rose.In addition,the space variation law ofminimum temperature,being more obvious thanminimum temperature,increased from southeast to northwest with different spatial changes in various seasons.From decadal variation,both maximum andminimum temperature appeared increase from 1970s to the first eight years in the 21st century,and the rise ofminimum temperature was significant greater than maximum temperature.The increase of maximum andminimum temperature was the highest from 2001 to 2008,whereas the lowest in 1970s.

CLIMATOLOGICAL VARIATION FEATURES OF TYPHOON PRECIPITATION INFLUENCING FUJIAN FOR THE PAST 46 YEARS

The results of an analysis of the temporal and spatial distribution of typhoon precipitation influencing Fujian from 1960 to 2005 show that typhoon precipitation in Fujian province occurs from May to November, with the most in August. There has been a decreasing trend since 1960. Typhoon precipitation gradually decreases from the coastal region to the northwestern mainland of Fujian and the maximum typhoon precipitation occurs in the northeast and the south of Fujian. Typhoon torrential rain is one of the extreme rainfall events in Fujian. High frequencies of typhoon torrential rain occur in the coastal and southwest regions of the province. With the impact of Fujian＇s terrain, typhoon precipitation occurs more easily to the east of the mountains than to the west. Atmospheric circulation at 500 hPa over Asia and sea surface temperature anomalies of the equatorial eastern Pacific are analyzed, with the finding that they are closely connected with the anomaly of typhoon precipitation influencing Fujian, possibly mainly by modulating the northbound track of typhoons via changing the atmosphere circulation to lead to the anomaly of typhoon precipitation over the province

ANTARCTIC SEA ICE AND THE POLAR VORTEX INDEX:TEMPORAL AND SPATIAL CHARACTERISTICS AND THEIR RELATIONSHIP

The cluster analysis method has been used to divide the Antarctic sea ice variation field into 5 sectors.Then,for each of these sectors,the corresponding indexes of vortex area and vortex intensity on the 500 hPa level have been calcu- lated.These data were used to analyse the temporal and spatial characteristics of both Antarctic sea ice and the vortex index variations and their relationship.Our results show that substantial differences are presented in the climatic pattern and interannual variations of the sea ice data and vortex index in different sectors.The maximum sea ice extent varia- tions appear in sector 1 and sector 4.Oscillation periods of 2—2.5 and 5—7 years exist in the variations of sea ice extent and vortex index in most sectors.A positive trend is only found in sector 1 sea ice extent while the other sectors show negative trends.The average extent of the Antarctic sea ice as a whole has retreated at a rate of 1.6 latitudes per 100 years.The vortex areas for all sectors have decreased.Nevertheless,the vortex intensities in 3 sectors have increased.The relationship between sea ice and vortex characters in each sector is obvious,but a little complex.Sectors 1 and 5,which are located in the Southeast Pacific and South Atlantic,are the most sensitive areas in terms of sea ice/atmosphere interaction.

Trends of Temperature Extremes in Summer and Winter during 1971–2013 in China

The diurnal temperature range(DTR) has decreased dramatically in recent decades, but it is not yet obvious whether the extreme values of DTR have also reduced. Based on the daily maximum and minimum temperature data of 653 stations in China, a set of monthly indices of warm extremes, cold extremes, and DTR extremes in summer(June, July, August) and winter(December, January, February) were studied for spatial and temporal features during the period 1971–2013. Results show that the incidence of warm extremes has been increasing in most parts of China, while the opposite trend was found in the cold extremes for summer and winter months. Both increasing and decreasing trends of monthly DTR extremes were identified in China for both seasons. For high DTR extremes, decreasing trends were identified in northern China for both seasons, but increasing trends were found only in southern China in summer, while in winter, they were found in central China. Monthly low DTR extreme indices demonstrated consistent positive trends in summer and winter, while significant increases(P < 0.05) were identified for only a few stations.

Facial expression recognition based on bidirectional gated recurrent units within deep residual network

Purpose-recent years,facial expression recognition has been widely used in human machine interaction,clinical medicine and safe driving.However,there is a limitation that conventional recurrent neural networks can only learn the time-series characteristics of expressions based on one-way propagation information.Design/methodology/approach-To solve such limitation,this paper proposes a novel model based on bidirectional gated recurrent unit networks(Bi-GRUs)with two-way propagations,and the theory of identity mapping residuals is adopted to effectively prevent the problem of gradient disappearance caused by the depth of the introduced network.Since the Inception-V3 network model for spatial feature extraction has too many parameters,it is prone to overfitting during training.This paper proposes a novel facial expression recognition model to add two reduction modules to reduce parameters,so as to obtain an Inception-W network with better generalization.Findings-Finally,the proposed model is pretrained to determine the best settings and selections.Then,the pretrained model is experimented on two facial expression data sets of CKþand Oulu-CASIA,and the recognition performance and efficiency are compared with the existing methods.The highest recognition rate is 99.6%,which shows that the method has good recognition accuracy in a certain range.Originality/value-By using the proposed model for the applications of facial expression,the high recognition accuracy and robust recognition results with lower time consumption will help to build more sophisticated applications in real world.