In the field of satellite imagery, remote sensing image captioning(RSIC) is a hot topic with the challenge of overfitting and difficulty of image and text alignment. To address these issues, this paper proposes a visi...In the field of satellite imagery, remote sensing image captioning(RSIC) is a hot topic with the challenge of overfitting and difficulty of image and text alignment. To address these issues, this paper proposes a vision-language aligning paradigm for RSIC to jointly represent vision and language. First, a new RSIC dataset DIOR-Captions is built for augmenting object detection in optical remote(DIOR) sensing images dataset with manually annotated Chinese and English contents. Second, a Vision-Language aligning model with Cross-modal Attention(VLCA) is presented to generate accurate and abundant bilingual descriptions for remote sensing images. Third, a crossmodal learning network is introduced to address the problem of visual-lingual alignment. Notably, VLCA is also applied to end-toend Chinese captions generation by using the pre-training language model of Chinese. The experiments are carried out with various baselines to validate VLCA on the proposed dataset. The results demonstrate that the proposed algorithm is more descriptive and informative than existing algorithms in producing captions.展开更多
目的比较改良早期预警评分(modified early warning score,MEWS)与急性生理和慢性健康评分系统(acute physiological and chronic health evaluation-Ⅱ,APACHE-Ⅱ)在评估急诊内科患者病情的效果。方法 2014年1-3月,采用方便抽样法选取...目的比较改良早期预警评分(modified early warning score,MEWS)与急性生理和慢性健康评分系统(acute physiological and chronic health evaluation-Ⅱ,APACHE-Ⅱ)在评估急诊内科患者病情的效果。方法 2014年1-3月,采用方便抽样法选取乌鲁木齐市某三级甲等综合医院急诊内科患者640例为研究对象,对其进行MEWS评分以及入院24h后APACHE-Ⅱ评分,比较两种评分病情评估预测指标灵敏度、特异度、阳性预测值、阴性预测值、受试者ROC曲线。结果MEWS评分与APACHE-Ⅱ评分病情评估预测价值中等,MEWS评分ROC曲线下面积为0.648,最佳截断值是4分,灵敏度0.567,特异度0.708,阳性预测值71.68%,阴性预测值55.38%;APACHE-Ⅱ评分ROC曲线下面积为0.680,最佳截断值是14分,灵敏度61.16%,特异度66.79%,阳性预测值61.16%,阴性预测值66.79%;两种评分ROC曲线下面积比较,差异无统计学意义(P>0.05)。结论 MEWS评分可用于评估少数民族地区急诊内科患者病情,其操作简单便捷,可实现对患者病情的快速、动态监测,可与APACHE-Ⅱ评分进行联合应用。展开更多
基金supported by the National Natural Science Foundation of China (61702528,61806212)。
文摘In the field of satellite imagery, remote sensing image captioning(RSIC) is a hot topic with the challenge of overfitting and difficulty of image and text alignment. To address these issues, this paper proposes a vision-language aligning paradigm for RSIC to jointly represent vision and language. First, a new RSIC dataset DIOR-Captions is built for augmenting object detection in optical remote(DIOR) sensing images dataset with manually annotated Chinese and English contents. Second, a Vision-Language aligning model with Cross-modal Attention(VLCA) is presented to generate accurate and abundant bilingual descriptions for remote sensing images. Third, a crossmodal learning network is introduced to address the problem of visual-lingual alignment. Notably, VLCA is also applied to end-toend Chinese captions generation by using the pre-training language model of Chinese. The experiments are carried out with various baselines to validate VLCA on the proposed dataset. The results demonstrate that the proposed algorithm is more descriptive and informative than existing algorithms in producing captions.
文摘目的比较改良早期预警评分(modified early warning score,MEWS)与急性生理和慢性健康评分系统(acute physiological and chronic health evaluation-Ⅱ,APACHE-Ⅱ)在评估急诊内科患者病情的效果。方法 2014年1-3月,采用方便抽样法选取乌鲁木齐市某三级甲等综合医院急诊内科患者640例为研究对象,对其进行MEWS评分以及入院24h后APACHE-Ⅱ评分,比较两种评分病情评估预测指标灵敏度、特异度、阳性预测值、阴性预测值、受试者ROC曲线。结果MEWS评分与APACHE-Ⅱ评分病情评估预测价值中等,MEWS评分ROC曲线下面积为0.648,最佳截断值是4分,灵敏度0.567,特异度0.708,阳性预测值71.68%,阴性预测值55.38%;APACHE-Ⅱ评分ROC曲线下面积为0.680,最佳截断值是14分,灵敏度61.16%,特异度66.79%,阳性预测值61.16%,阴性预测值66.79%;两种评分ROC曲线下面积比较,差异无统计学意义(P>0.05)。结论 MEWS评分可用于评估少数民族地区急诊内科患者病情,其操作简单便捷,可实现对患者病情的快速、动态监测,可与APACHE-Ⅱ评分进行联合应用。
