Two supramolecular complexes [Zn（tacd）2]（C6H8O4）·6H2O（1） and [Cu（tacd）2]Cl2·4H2O（2） were synthesized and characterized by elemental analysis, IR spectra, TGA and single-crystal X-ray diffraction an...Two supramolecular complexes [Zn（tacd）2]（C6H8O4）·6H2O（1） and [Cu（tacd）2]Cl2·4H2O（2） were synthesized and characterized by elemental analysis, IR spectra, TGA and single-crystal X-ray diffraction analysis. The crystal structure showed that the metal ions in complexes 1 and 2 had similar coordination circumstance. But for the complex 2, it formed a novel two-dimensional supramolecular network with 12-membered rings and four-membered rings via hydrogen bond interaction. The thermal gravimetric analyses indicated that the two complexes had similar steps of weight-loss. On the basis of experiment, the two complexes were calculated by DFT-B3LYP/6-31G（d） in Gaussian 03. The results of calculation are in good agreement with the experiment.展开更多
针对遥感图像中小目标数量众多且背景复杂所导致的识别精度低的问题,提出了一种改进的遥感图像小目标检测方法。该方法基于改进的YOLOv7网络模型,将双级路由注意力机制加入至下采样阶段以构建针对小目标的特征提取模块MP-ATT(max poolin...针对遥感图像中小目标数量众多且背景复杂所导致的识别精度低的问题,提出了一种改进的遥感图像小目标检测方法。该方法基于改进的YOLOv7网络模型,将双级路由注意力机制加入至下采样阶段以构建针对小目标的特征提取模块MP-ATT(max pooling-attention),使得模型更加关注小目标的特征,提高小目标检测精度。为了加强对小目标的细节感知能力,使用DCNv3(deformable convolution network v3)替换骨干网络中的二维卷积,以此构建新的层聚合模块ELAN-D。为网络设计新的小目标检测层以获取更精细的特征信息,从而提升模型的鲁棒性。同时使用MPDIoU(minimum point distance based IoU)替换原模型中的CIoU来优化损失函数,以适应遥感图像的尺度变化。实验表明,所提出的方法在DOTA-v1.0数据集上取得了良好效果,准确率、召回率和平均准确率(mean average precision,mAP)相比原模型分别提升了0.4、4.0、2.3个百分点,证明了该方法能够有效提升遥感图像中小目标的检测效果。展开更多
基金Project supported by the National Natural Science Foundation of China （No. 20271041） and S haanxi Natural Science Foundation （No. 2002B04）.Acknowledgments We are grateful for Prof. Wen Zhenyi, who supplied the Gaussian 03 software for us. We also thank Prof. Ng Seik Weng at University of Malaya for the solution of the crystal structure of complex 1.
文摘Two supramolecular complexes [Zn（tacd）2]（C6H8O4）·6H2O（1） and [Cu（tacd）2]Cl2·4H2O（2） were synthesized and characterized by elemental analysis, IR spectra, TGA and single-crystal X-ray diffraction analysis. The crystal structure showed that the metal ions in complexes 1 and 2 had similar coordination circumstance. But for the complex 2, it formed a novel two-dimensional supramolecular network with 12-membered rings and four-membered rings via hydrogen bond interaction. The thermal gravimetric analyses indicated that the two complexes had similar steps of weight-loss. On the basis of experiment, the two complexes were calculated by DFT-B3LYP/6-31G（d） in Gaussian 03. The results of calculation are in good agreement with the experiment.
文摘针对遥感图像中小目标数量众多且背景复杂所导致的识别精度低的问题,提出了一种改进的遥感图像小目标检测方法。该方法基于改进的YOLOv7网络模型,将双级路由注意力机制加入至下采样阶段以构建针对小目标的特征提取模块MP-ATT(max pooling-attention),使得模型更加关注小目标的特征,提高小目标检测精度。为了加强对小目标的细节感知能力,使用DCNv3(deformable convolution network v3)替换骨干网络中的二维卷积,以此构建新的层聚合模块ELAN-D。为网络设计新的小目标检测层以获取更精细的特征信息,从而提升模型的鲁棒性。同时使用MPDIoU(minimum point distance based IoU)替换原模型中的CIoU来优化损失函数,以适应遥感图像的尺度变化。实验表明,所提出的方法在DOTA-v1.0数据集上取得了良好效果,准确率、召回率和平均准确率(mean average precision,mAP)相比原模型分别提升了0.4、4.0、2.3个百分点,证明了该方法能够有效提升遥感图像中小目标的检测效果。
