Background Gesture recognition has attracted significant attention because of its wide range of potential applications.Although multi-modal gesture recognition has made significant progress in recent years,a popular m...Background Gesture recognition has attracted significant attention because of its wide range of potential applications.Although multi-modal gesture recognition has made significant progress in recent years,a popular method still is simply fusing prediction scores at the end of each branch,which often ignores complementary features among different modalities in the early stage and does not fuse the complementary features into a more discriminative feature.Methods This paper proposes an Adaptive Cross-modal Weighting(ACmW)scheme to exploit complementarity features from RGB-D data in this study.The scheme learns relations among different modalities by combining the features of different data streams.The proposed ACmW module contains two key functions:(1)fusing complementary features from multiple streams through an adaptive one-dimensional convolution;and(2)modeling the correlation of multi-stream complementary features in the time dimension.Through the effective combination of these two functional modules,the proposed ACmW can automatically analyze the relationship between the complementary features from different streams,and can fuse them in the spatial and temporal dimensions.Results Extensive experiments validate the effectiveness of the proposed method,and show that our method outperforms state-of-the-art methods on IsoGD and NVGesture.展开更多
Dear Editor,Bread wheat(Triticum aestivum L.)is a globally important cereal providing~20% of the calories and proteins for>4.5billion people.Plant architecture,including morphologies of leaves,spikes,stems,and root...Dear Editor,Bread wheat(Triticum aestivum L.)is a globally important cereal providing~20% of the calories and proteins for>4.5billion people.Plant architecture,including morphologies of leaves,spikes,stems,and roots,has great impact on plant development and productivity,and thus has been extensively investigated in various plant species(Jiang et al.,2023;Zhang et al.,2017).展开更多
In advanced hepatocellular carcinoma(HCC)tissues,M2-like tumor-associated macrophages(TAMs)are in the majority and promotes HCC progression.Contrary to the pro-tumor effect of M2-like TAMs,M1-like TAMs account for a s...In advanced hepatocellular carcinoma(HCC)tissues,M2-like tumor-associated macrophages(TAMs)are in the majority and promotes HCC progression.Contrary to the pro-tumor effect of M2-like TAMs,M1-like TAMs account for a small proportion and have anti-tumor effects.Since TAMs can switch from one type to another,reprogramming TAMs may be an important treatment for HCC therapy.However,the mechanisms of phenotypic switch and reprogramming TAMs are still obscure.In this study,we analyzed differential genes in normal macrophages and TAMs,and found that loss of MANF in TAMs accompanied by high levels of downstream genes negatively regulated by MANF.MANF reprogrammed TAMs into M1 phenotype.Meanwhile,loss of MANF promoted HCC progression in HCC patients and mice HCC model,especially tumor neovascularization.Additionally,macrophages with MANF supplement suppressed HCC progression in mice,suggesting MANF supplement in macrophage was an effective treatment for HCC.Mechanistically,MANF enhanced the HSF1-HSP70-1 interaction,restricted HSF1 in the cytoplasm of macrophages,and decreased both mRNA and protein levels of HSP70-1,which in turn led to reprogramming TAMs,and suppressing neovascularization of HCC.Our study contributes to the exploration the mechanism of TAMs reprogramming,which may provide insights for future therapeutic exploitation of HCC neovascularization.展开更多
基金the Chinese National Natural Science Foundation Projects(61961160704,61876179)the Key Project of the General Logistics Department(ASW17C001)the Science and Technology Development Fund of Macao(0010/2019/AFJ,0025/2019/AKP).
文摘Background Gesture recognition has attracted significant attention because of its wide range of potential applications.Although multi-modal gesture recognition has made significant progress in recent years,a popular method still is simply fusing prediction scores at the end of each branch,which often ignores complementary features among different modalities in the early stage and does not fuse the complementary features into a more discriminative feature.Methods This paper proposes an Adaptive Cross-modal Weighting(ACmW)scheme to exploit complementarity features from RGB-D data in this study.The scheme learns relations among different modalities by combining the features of different data streams.The proposed ACmW module contains two key functions:(1)fusing complementary features from multiple streams through an adaptive one-dimensional convolution;and(2)modeling the correlation of multi-stream complementary features in the time dimension.Through the effective combination of these two functional modules,the proposed ACmW can automatically analyze the relationship between the complementary features from different streams,and can fuse them in the spatial and temporal dimensions.Results Extensive experiments validate the effectiveness of the proposed method,and show that our method outperforms state-of-the-art methods on IsoGD and NVGesture.
基金supported by the Key R&D Program of Shandong Province(ZR202211070163,2023LZGC022)the Provincial Natural Science Foundation of Shandong(ZR2021MC056,ZR2021ZD30)+1 种基金the National Key Research and Development Program of China(2022YFD1201300)the Young Taishan Scholars Program of Shandong Province。
文摘Dear Editor,Bread wheat(Triticum aestivum L.)is a globally important cereal providing~20% of the calories and proteins for>4.5billion people.Plant architecture,including morphologies of leaves,spikes,stems,and roots,has great impact on plant development and productivity,and thus has been extensively investigated in various plant species(Jiang et al.,2023;Zhang et al.,2017).
基金funded by support programs for Jun Liu,including the National Natural Science Foundation of China(82073862)Excellent Youth Talent Program of Anhui Province Natural Science Foundation(2108085Y27,China)funded by Anhui Province Natural Science Foundation(2208085MH284,China)for Xiangpeng Hu,and funded by the National Natural Science Foundation of China(U21A20345)for Yuxian Shen。
文摘In advanced hepatocellular carcinoma(HCC)tissues,M2-like tumor-associated macrophages(TAMs)are in the majority and promotes HCC progression.Contrary to the pro-tumor effect of M2-like TAMs,M1-like TAMs account for a small proportion and have anti-tumor effects.Since TAMs can switch from one type to another,reprogramming TAMs may be an important treatment for HCC therapy.However,the mechanisms of phenotypic switch and reprogramming TAMs are still obscure.In this study,we analyzed differential genes in normal macrophages and TAMs,and found that loss of MANF in TAMs accompanied by high levels of downstream genes negatively regulated by MANF.MANF reprogrammed TAMs into M1 phenotype.Meanwhile,loss of MANF promoted HCC progression in HCC patients and mice HCC model,especially tumor neovascularization.Additionally,macrophages with MANF supplement suppressed HCC progression in mice,suggesting MANF supplement in macrophage was an effective treatment for HCC.Mechanistically,MANF enhanced the HSF1-HSP70-1 interaction,restricted HSF1 in the cytoplasm of macrophages,and decreased both mRNA and protein levels of HSP70-1,which in turn led to reprogramming TAMs,and suppressing neovascularization of HCC.Our study contributes to the exploration the mechanism of TAMs reprogramming,which may provide insights for future therapeutic exploitation of HCC neovascularization.
