The goal of street-to-aerial cross-view image geo-localization is to determine the location of the query street-view image by retrieving the aerial-view image from the same place.The drastic viewpoint and appearance g...The goal of street-to-aerial cross-view image geo-localization is to determine the location of the query street-view image by retrieving the aerial-view image from the same place.The drastic viewpoint and appearance gap between the aerial-view and the street-view images brings a huge challenge against this task.In this paper,we propose a novel multiscale attention encoder to capture the multiscale contextual information of the aerial/street-view images.To bridge the domain gap between these two view images,we first use an inverse polar transform to make the street-view images approximately aligned with the aerial-view images.Then,the explored multiscale attention encoder is applied to convert the image into feature representation with the guidance of the learnt multiscale information.Finally,we propose a novel global mining strategy to enable the network to pay more attention to hard negative exemplars.Experiments on standard benchmark datasets show that our approach obtains 81.39%top-1 recall rate on the CVUSA dataset and 71.52%on the CVACT dataset,achieving the state-of-the-art performance and outperforming most of the existing methods significantly.展开更多
Current studies have shown that the spatial-temporal graph convolutional network(STGCN)is effective for skeleton-based action recognition.However,for the existing STGCN-based methods,their temporal kernel size is usua...Current studies have shown that the spatial-temporal graph convolutional network(STGCN)is effective for skeleton-based action recognition.However,for the existing STGCN-based methods,their temporal kernel size is usually fixed over all layers,which makes them cannot fully exploit the temporal dependency between discontinuous frames and different sequence lengths.Besides,most of these methods use average pooling to obtain global graph feature from vertex features,resulting in losing much fine-grained information for action classification.To address these issues,in this work,the authors propose a novel spatial attentive and temporal dilated graph convolutional network(SATD-GCN).It contains two important components,that is,a spatial attention pooling module(SAP)and a temporal dilated graph convolution module(TDGC).Specifically,the SAP module can select the human body joints which are beneficial for action recognition by a self-attention mechanism and alleviates the influence of data redundancy and noise.The TDGC module can effectively extract the temporal features at different time scales,which is useful to improve the temporal perception field and enhance the robustness of the model to different motion speed and sequence length.Importantly,both the SAP module and the TDGC module can be easily integrated into the ST-GCN-based models,and significantly improve their performance.Extensive experiments on two large-scale benchmark datasets,that is,NTU-RGB+D and Kinetics-Skeleton,demonstrate that the authors’method achieves the state-of-the-art performance for skeleton-based action recognition.展开更多
Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related death worldwide.1 E2 ubiquitin conjugating enzymes (UBE2) are potential therapeutic targets in tumors arising from genomic instability and tu...Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related death worldwide.1 E2 ubiquitin conjugating enzymes (UBE2) are potential therapeutic targets in tumors arising from genomic instability and tumor microenvironment (TME).2,3 UBE2S, an important UBE2, has demonstrated strong oncogenic activities in various malignant cancers, including HCC. However, a comprehensive study regarding its role in HCC is still absent, and its association with immunology and drug response of HCC is still unclear. In this study, we conducted a pan-cancer analysis of UBE2S expression and prognosis, carried out enrichment analysis of UBE2S-associated genes, and analyzed association between UBE2S expression and HCC microenvironment, stemness and drug response. Collectively, our results demonstrated that UBE2S expression was significantly increased in multiple types of cancer, including HCC, and harbors prognostic values for HCC. Potential function of UBE2S involves modulation of ubiquitin mediated proteolysis and cell cycle progression. Furthermore, in HCC, UBE2S expression was positively correlated with TME infiltration, microsatellite instability (MSI), DNA methylation, stemness and drug response. These findings highlighted the possible pivotal roles of UBE2S in HCC prognosis, precision immunotherapy and drug response.展开更多
Mantle cell lymphoma(MCL)is an aggressive subtype of non-Hodgkin lymphoma(NHL)characterized by the overexpression of cyclin D1 and deregulated cell cycle.1 Ganetespib(STA-9090),a second-generation HSP90 inhibitor,dram...Mantle cell lymphoma(MCL)is an aggressive subtype of non-Hodgkin lymphoma(NHL)characterized by the overexpression of cyclin D1 and deregulated cell cycle.1 Ganetespib(STA-9090),a second-generation HSP90 inhibitor,dramatically disrupted oncogenic cellular processes resulting in the inhibition of client protein-derived tumors in preclinical studies.2 The synthetic lethal strategy using poly(ADP-ribose)polymerase(PARP)inhibitors(PARPis)has been reported as a powerful therapeutic intervention in MCL and their effectiveness can be increased by a deficiency in DNA damage repair(DDR),especially homologous recombination deficiency.3 Since we found earlier that transient ganetespib treatment can induce defects in DDR,we hypothesized that ganetespib treatment can possibly enhance the sensitivity of MCL cells to PARPis and HSP90 and PARP is can be demonstrated as promising combination therapies for MCL.展开更多
基金National Natural Science Foundation of China,Grant/Award Number:62106177supported by the Central University Basic Research Fund of China(No.2042020KF0016)supported by the supercomputing system in the Supercomputing Center of Wuhan University.
文摘The goal of street-to-aerial cross-view image geo-localization is to determine the location of the query street-view image by retrieving the aerial-view image from the same place.The drastic viewpoint and appearance gap between the aerial-view and the street-view images brings a huge challenge against this task.In this paper,we propose a novel multiscale attention encoder to capture the multiscale contextual information of the aerial/street-view images.To bridge the domain gap between these two view images,we first use an inverse polar transform to make the street-view images approximately aligned with the aerial-view images.Then,the explored multiscale attention encoder is applied to convert the image into feature representation with the guidance of the learnt multiscale information.Finally,we propose a novel global mining strategy to enable the network to pay more attention to hard negative exemplars.Experiments on standard benchmark datasets show that our approach obtains 81.39%top-1 recall rate on the CVUSA dataset and 71.52%on the CVACT dataset,achieving the state-of-the-art performance and outperforming most of the existing methods significantly.
基金National Key Research and Development Program of China,Grant/Award Number:2018YFB1600600。
文摘Current studies have shown that the spatial-temporal graph convolutional network(STGCN)is effective for skeleton-based action recognition.However,for the existing STGCN-based methods,their temporal kernel size is usually fixed over all layers,which makes them cannot fully exploit the temporal dependency between discontinuous frames and different sequence lengths.Besides,most of these methods use average pooling to obtain global graph feature from vertex features,resulting in losing much fine-grained information for action classification.To address these issues,in this work,the authors propose a novel spatial attentive and temporal dilated graph convolutional network(SATD-GCN).It contains two important components,that is,a spatial attention pooling module(SAP)and a temporal dilated graph convolution module(TDGC).Specifically,the SAP module can select the human body joints which are beneficial for action recognition by a self-attention mechanism and alleviates the influence of data redundancy and noise.The TDGC module can effectively extract the temporal features at different time scales,which is useful to improve the temporal perception field and enhance the robustness of the model to different motion speed and sequence length.Importantly,both the SAP module and the TDGC module can be easily integrated into the ST-GCN-based models,and significantly improve their performance.Extensive experiments on two large-scale benchmark datasets,that is,NTU-RGB+D and Kinetics-Skeleton,demonstrate that the authors’method achieves the state-of-the-art performance for skeleton-based action recognition.
基金supported by the National Natural Science Foundation of China(No.81672582,31471294 and 31771521)the Training Project of Young Backbone Teachers of Jiangsu University and Student Scientific Research Project of Jiangsu University(No.19A367).
文摘Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related death worldwide.1 E2 ubiquitin conjugating enzymes (UBE2) are potential therapeutic targets in tumors arising from genomic instability and tumor microenvironment (TME).2,3 UBE2S, an important UBE2, has demonstrated strong oncogenic activities in various malignant cancers, including HCC. However, a comprehensive study regarding its role in HCC is still absent, and its association with immunology and drug response of HCC is still unclear. In this study, we conducted a pan-cancer analysis of UBE2S expression and prognosis, carried out enrichment analysis of UBE2S-associated genes, and analyzed association between UBE2S expression and HCC microenvironment, stemness and drug response. Collectively, our results demonstrated that UBE2S expression was significantly increased in multiple types of cancer, including HCC, and harbors prognostic values for HCC. Potential function of UBE2S involves modulation of ubiquitin mediated proteolysis and cell cycle progression. Furthermore, in HCC, UBE2S expression was positively correlated with TME infiltration, microsatellite instability (MSI), DNA methylation, stemness and drug response. These findings highlighted the possible pivotal roles of UBE2S in HCC prognosis, precision immunotherapy and drug response.
基金supported by the National Natural Science Foundation of China(No.81672582 to HL,31771521 to ZT,and 82200083 to CS),Top Talent of Innovative Research Team of Jiangsu Province,China(to HL and ZT)the Natural Science Foundation of Jiangsu Province,China(No.BK20200891 to CS)the Senior Talent Start-up Funds of Jiangsu University(China)(No.14JDG050 and 14JDG011 to HL and ZT).
文摘Mantle cell lymphoma(MCL)is an aggressive subtype of non-Hodgkin lymphoma(NHL)characterized by the overexpression of cyclin D1 and deregulated cell cycle.1 Ganetespib(STA-9090),a second-generation HSP90 inhibitor,dramatically disrupted oncogenic cellular processes resulting in the inhibition of client protein-derived tumors in preclinical studies.2 The synthetic lethal strategy using poly(ADP-ribose)polymerase(PARP)inhibitors(PARPis)has been reported as a powerful therapeutic intervention in MCL and their effectiveness can be increased by a deficiency in DNA damage repair(DDR),especially homologous recombination deficiency.3 Since we found earlier that transient ganetespib treatment can induce defects in DDR,we hypothesized that ganetespib treatment can possibly enhance the sensitivity of MCL cells to PARPis and HSP90 and PARP is can be demonstrated as promising combination therapies for MCL.
