Recent advances in artificial intelligence and the availability of large-scale benchmarks have made deepfake video generation and manipulation easier.Therefore,developing reliable and robust deepfake video detection m...Recent advances in artificial intelligence and the availability of large-scale benchmarks have made deepfake video generation and manipulation easier.Therefore,developing reliable and robust deepfake video detection mechanisms is paramount.This research introduces a novel real-time deepfake video detection framework by analyzing gaze and blink patterns,addressing the spatial-temporal challenges unique to gaze and blink anomalies using the TimeSformer and hybrid Transformer-CNN models.The TimeSformer architecture leverages spatial-temporal attention mechanisms to capture fine-grained blinking intervals and gaze direction anomalies.Compared to state-of-the-art traditional convolutional models like MesoNet and EfficientNet,which primarily focus on global facial features,our approach emphasizes localized eye-region analysis,significantly enhancing detection accuracy.We evaluate our framework on four standard datasets:FaceForensics,CelebDF-V2,DFDC,and FakeAVCeleb.The proposed framework results reveal higher accuracy,with the TimeSformer model achieving accuracies of 97.5%,96.3%,95.8%,and 97.1%,and with the hybrid Transformer-CNN model demonstrating accuracies of 92.8%,91.5%,90.9%,and 93.2%,on FaceForensics,CelebDF-V2,DFDC,and FakeAVCeleb datasets,respectively,showing robustness in distinguishing manipulated from authentic videos.Our research provides a robust state-of-the-art framework for real-time deepfake video detection.This novel study significantly contributes to video forensics,presenting scalable and accurate real-world application solutions.展开更多
We are evaluating dryland cotton production in Martin County, Texas, measuring cotton lint yield per unit of rainfall. Our goal is to collect rainfall data per 250 - 400 ha. Upon selection of a rainfall gauge, we real...We are evaluating dryland cotton production in Martin County, Texas, measuring cotton lint yield per unit of rainfall. Our goal is to collect rainfall data per 250 - 400 ha. Upon selection of a rainfall gauge, we realized that the cost of using, for example, a tipping bucket-type rain gauge would be too expensive and thus searched for an alternative method. We selected an all-in-one commercially available weather station;hereafter, referred to as a Personal Weather Station (PWS) that is both wireless and solar powered. Our objective was to evaluate average measurements of rainfall obtained with the PWS and to compare these to measurements obtained with an automatic weather station (AWS). For this purpose, we installed four PWS deployed within 20 m of the Plant Stress and Water Conservation Meteorological Tower that was used as our AWS, located at USDA-ARS Cropping Systems Research Laboratory, Lubbock, TX. In addition, we measured and compared hourly average values of short-wave irradiance (R<sub>g</sub>), air temperature (T<sub>air</sub>) and relative humidity (RH), and wind speed (WS), and calculated values of dewpoint temperature (T<sub>dew</sub>). This comparison was done over a 242-day period (1 October 2022-31 May 2023) and results indicated that there was no statistical difference in measurements of rainfall between the PWS and AWS. Hourly average values of R<sub>g</sub> measured with the PWS and AWS agreed on clear days, but PWS measurements were higher on cloudy days. There was no statistical difference between PWS and AWS hourly average measurements of T<sub>air</sub>, RH, and calculated T<sub>dew</sub>. Hourly average measurements of R<sub>g</sub> and WS were more variable. We concluded that the PWS we selected will provide adequate values of rainfall and other weather variables to meet our goal of evaluating dryland cotton lint yield per unit rainfall.展开更多
文摘Recent advances in artificial intelligence and the availability of large-scale benchmarks have made deepfake video generation and manipulation easier.Therefore,developing reliable and robust deepfake video detection mechanisms is paramount.This research introduces a novel real-time deepfake video detection framework by analyzing gaze and blink patterns,addressing the spatial-temporal challenges unique to gaze and blink anomalies using the TimeSformer and hybrid Transformer-CNN models.The TimeSformer architecture leverages spatial-temporal attention mechanisms to capture fine-grained blinking intervals and gaze direction anomalies.Compared to state-of-the-art traditional convolutional models like MesoNet and EfficientNet,which primarily focus on global facial features,our approach emphasizes localized eye-region analysis,significantly enhancing detection accuracy.We evaluate our framework on four standard datasets:FaceForensics,CelebDF-V2,DFDC,and FakeAVCeleb.The proposed framework results reveal higher accuracy,with the TimeSformer model achieving accuracies of 97.5%,96.3%,95.8%,and 97.1%,and with the hybrid Transformer-CNN model demonstrating accuracies of 92.8%,91.5%,90.9%,and 93.2%,on FaceForensics,CelebDF-V2,DFDC,and FakeAVCeleb datasets,respectively,showing robustness in distinguishing manipulated from authentic videos.Our research provides a robust state-of-the-art framework for real-time deepfake video detection.This novel study significantly contributes to video forensics,presenting scalable and accurate real-world application solutions.
文摘We are evaluating dryland cotton production in Martin County, Texas, measuring cotton lint yield per unit of rainfall. Our goal is to collect rainfall data per 250 - 400 ha. Upon selection of a rainfall gauge, we realized that the cost of using, for example, a tipping bucket-type rain gauge would be too expensive and thus searched for an alternative method. We selected an all-in-one commercially available weather station;hereafter, referred to as a Personal Weather Station (PWS) that is both wireless and solar powered. Our objective was to evaluate average measurements of rainfall obtained with the PWS and to compare these to measurements obtained with an automatic weather station (AWS). For this purpose, we installed four PWS deployed within 20 m of the Plant Stress and Water Conservation Meteorological Tower that was used as our AWS, located at USDA-ARS Cropping Systems Research Laboratory, Lubbock, TX. In addition, we measured and compared hourly average values of short-wave irradiance (R<sub>g</sub>), air temperature (T<sub>air</sub>) and relative humidity (RH), and wind speed (WS), and calculated values of dewpoint temperature (T<sub>dew</sub>). This comparison was done over a 242-day period (1 October 2022-31 May 2023) and results indicated that there was no statistical difference in measurements of rainfall between the PWS and AWS. Hourly average values of R<sub>g</sub> measured with the PWS and AWS agreed on clear days, but PWS measurements were higher on cloudy days. There was no statistical difference between PWS and AWS hourly average measurements of T<sub>air</sub>, RH, and calculated T<sub>dew</sub>. Hourly average measurements of R<sub>g</sub> and WS were more variable. We concluded that the PWS we selected will provide adequate values of rainfall and other weather variables to meet our goal of evaluating dryland cotton lint yield per unit rainfall.
