Face forgery detection is drawing ever-increasing attention in the academic community owing to security concerns.Despite the considerable progress in existing methods,we note that:Previous works overlooked finegrain f...Face forgery detection is drawing ever-increasing attention in the academic community owing to security concerns.Despite the considerable progress in existing methods,we note that:Previous works overlooked finegrain forgery cues with high transferability.Such cues positively impact the model’s accuracy and generalizability.Moreover,single-modality often causes overfitting of the model,and Red-Green-Blue(RGB)modal-only is not conducive to extracting the more detailed forgery traces.We propose a novel framework for fine-grain forgery cues mining with fusion modality to cope with these issues.First,we propose two functional modules to reveal and locate the deeper forged features.Our method locates deeper forgery cues through a dual-modality progressive fusion module and a noise adaptive enhancement module,which can excavate the association between dualmodal space and channels and enhance the learning of subtle noise features.A sensitive patch branch is introduced on this foundation to enhance the mining of subtle forgery traces under fusion modality.The experimental results demonstrate that our proposed framework can desirably explore the differences between authentic and forged images with supervised learning.Comprehensive evaluations of several mainstream datasets show that our method outperforms the state-of-the-art detection methods with remarkable detection ability and generalizability.展开更多
Nowadays,it is extremely urgent for the software engineering education to cultivate the knowledge and ability of database talents in the era of big data.To this end,this paper proposes a talent training teaching modal...Nowadays,it is extremely urgent for the software engineering education to cultivate the knowledge and ability of database talents in the era of big data.To this end,this paper proposes a talent training teaching modality that integrates knowledge,ability,practice,and innovation(KAPI)for Database System Course.The teaching modality contains three parts:top-level design,course learning process,and course assurance and evaluation.The top-level design sorts out the core knowledge of the course and determines a mixed online and offline teaching platform.The course learning process emphasizes the correspondence transformation relationship between core knowledge points and ability enhancement,and the course is practiced in the form of experimental projects to finally enhance students’innovation consciousness and ability.The assurance and evaluation of the course are based on the outcome-based education(OBE)orientation,which realizes the objective evaluation of students’learning process and final performance.The teaching results of the course in the past 2 years show that the KAPI-based teaching modality has achieved better results.Meanwhile,students are satisfied with the evaluation of the modality.The teaching modality in this paper helps to stimulate students’initiatives,and improve their knowledge vision and practical ability,and thus helps to cultivate innovative and high-quality engineering talents required by the emerging engineering education.展开更多
桥梁健康监测数据的挖掘和分析工作只有在整体数据质量符合基本要求的有效数据基础上进行,才能保障如模态参数识别、损伤识别和状态评估等后续工作的准确性。因此,基于量化改进的探索性分析方法(Exploratory Data Analysis,EDA)和相关...桥梁健康监测数据的挖掘和分析工作只有在整体数据质量符合基本要求的有效数据基础上进行,才能保障如模态参数识别、损伤识别和状态评估等后续工作的准确性。因此,基于量化改进的探索性分析方法(Exploratory Data Analysis,EDA)和相关性分析从数据完整性、准确性和一致性的角度建立了桥梁健康监测静、动态数据的质量评估方法。对某大跨度斜拉桥健康监测系统的静、动态数据进行质量评估,通过对比分析了不同评估质量的温度数据、静挠度数据和不同评估质量的主梁竖向加速度动力信号的模态参数识别的稳定图,验证了所提方法的正确性。结果表明,所提评估方法能够快速有效地判断数据质量的好坏,进而确保桥梁结构的服役性能评估和预测的准确性,有利于提高健康监测数据的可用性和效能。展开更多
基金This study is supported by the Fundamental Research Funds for the Central Universities of PPSUC under Grant 2022JKF02009.
文摘Face forgery detection is drawing ever-increasing attention in the academic community owing to security concerns.Despite the considerable progress in existing methods,we note that:Previous works overlooked finegrain forgery cues with high transferability.Such cues positively impact the model’s accuracy and generalizability.Moreover,single-modality often causes overfitting of the model,and Red-Green-Blue(RGB)modal-only is not conducive to extracting the more detailed forgery traces.We propose a novel framework for fine-grain forgery cues mining with fusion modality to cope with these issues.First,we propose two functional modules to reveal and locate the deeper forged features.Our method locates deeper forgery cues through a dual-modality progressive fusion module and a noise adaptive enhancement module,which can excavate the association between dualmodal space and channels and enhance the learning of subtle noise features.A sensitive patch branch is introduced on this foundation to enhance the mining of subtle forgery traces under fusion modality.The experimental results demonstrate that our proposed framework can desirably explore the differences between authentic and forged images with supervised learning.Comprehensive evaluations of several mainstream datasets show that our method outperforms the state-of-the-art detection methods with remarkable detection ability and generalizability.
基金the support from the General Program of the Educational Teaching Reform Research Project of Northwestern Polytechnical University(Grant No.2023JGY35)the Guangdong Basic and Applied Basic Research Foundation(Grant No.2022A1515110252)+1 种基金the Double First-class Construction Foundation(Grant No.22GH010616)the Northwestern Polytechnical University of Graduate Student Quality Improvement Program(Grant No.22GZ210101)。
文摘Nowadays,it is extremely urgent for the software engineering education to cultivate the knowledge and ability of database talents in the era of big data.To this end,this paper proposes a talent training teaching modality that integrates knowledge,ability,practice,and innovation(KAPI)for Database System Course.The teaching modality contains three parts:top-level design,course learning process,and course assurance and evaluation.The top-level design sorts out the core knowledge of the course and determines a mixed online and offline teaching platform.The course learning process emphasizes the correspondence transformation relationship between core knowledge points and ability enhancement,and the course is practiced in the form of experimental projects to finally enhance students’innovation consciousness and ability.The assurance and evaluation of the course are based on the outcome-based education(OBE)orientation,which realizes the objective evaluation of students’learning process and final performance.The teaching results of the course in the past 2 years show that the KAPI-based teaching modality has achieved better results.Meanwhile,students are satisfied with the evaluation of the modality.The teaching modality in this paper helps to stimulate students’initiatives,and improve their knowledge vision and practical ability,and thus helps to cultivate innovative and high-quality engineering talents required by the emerging engineering education.
文摘桥梁健康监测数据的挖掘和分析工作只有在整体数据质量符合基本要求的有效数据基础上进行,才能保障如模态参数识别、损伤识别和状态评估等后续工作的准确性。因此,基于量化改进的探索性分析方法(Exploratory Data Analysis,EDA)和相关性分析从数据完整性、准确性和一致性的角度建立了桥梁健康监测静、动态数据的质量评估方法。对某大跨度斜拉桥健康监测系统的静、动态数据进行质量评估,通过对比分析了不同评估质量的温度数据、静挠度数据和不同评估质量的主梁竖向加速度动力信号的模态参数识别的稳定图,验证了所提方法的正确性。结果表明,所提评估方法能够快速有效地判断数据质量的好坏,进而确保桥梁结构的服役性能评估和预测的准确性,有利于提高健康监测数据的可用性和效能。
