Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and sha...Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and share such multimodal data.However,due to professional discrepancies among annotators and lax quality control,noisy labels might be introduced.Recent research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the DNNs.To address this challenging problem,we present a Multimodal Robust Meta Learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities simultaneously.Specifically,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network training.Besides,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy labels.We conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.展开更多
Driver state sensing technologies, such as vehicular systems, start to be widely considered by automotive manufacturers. To reduce the cost and minimize the intrusiveness towards driving, the majority of these systems...Driver state sensing technologies, such as vehicular systems, start to be widely considered by automotive manufacturers. To reduce the cost and minimize the intrusiveness towards driving, the majority of these systems rely on the in-cabin camera(s) and other optical sensors. With their great capabilities in detecting and intervening of driver distraction and inattention,these technologies may become key components in future vehicle safety and control systems. However, to the best of our knowledge,currently, there is no common standard available to objectively compare the performance of these technologies. Thus, it is imperative to develop one standardized process for evaluation purposes.In this paper, we propose one systematic and standardized evaluation process after successfully addressing three difficulties:1) defining and selecting the important influential individual and environmental factors, 2) countering the effects of individual differences and randomness in driver behaviors, and 3) building a reliable in-vehicle driver head motion tracking tool to collect ground-truth motion data. We have collected data on a large scale on a commercial driver state-sensing platform. For each subject, 30 to 40 minutes of head motion data was collected and included variables, such as lighting conditions, head/face features,and camera locations. The collected data was analyzed based on a proposed performance measure. The results show that the developed process can efficiently evaluate an individual camerabased driver state sensing product, which builds a common base for comparing the performance of different systems.展开更多
The purpose of this study is to analyze the household waste reduction effect of sorted collection of recyclable waste in Japan using a panel data analysis, which considers time-series and cross-section data simultaneo...The purpose of this study is to analyze the household waste reduction effect of sorted collection of recyclable waste in Japan using a panel data analysis, which considers time-series and cross-section data simultaneously. Also, the study shows the effect of the type of sorted items on the quantity of household waste disposed. We used the data attained from 103 cities recorded over three years, and applied the quantity of total waste disposed, the quantity of combustible waste, the quantity of other waste （waste excluding combustible and recyclable waste）, and the quantity of combustible plus other waste as objective variables, respectively, in the models. The result suggests that when the number of sorted items is increased marginally, the quantity of household waste decreases by about 0.5%-3.3% or 1.28-4.17 grams per capita per day. In addition, it is shown that sorting out white trays is effective in reducing the quantity of combustible waste. Sorting out paper containers and packages is also effective in reducing the quantity of other waste and combustible plus other waste.展开更多
在遥测垂线坐标仪、遥测引张线仪尚未普及,且其可靠性有待进一步完善的情况下,传统的垂线、引张线的人工观测仍占居主导地位。因传统方法的数据记录使内业数据处理工作量大大增加,采用基于Windows Mobile系统的PDA作为记录器,并利用Visu...在遥测垂线坐标仪、遥测引张线仪尚未普及,且其可靠性有待进一步完善的情况下,传统的垂线、引张线的人工观测仍占居主导地位。因传统方法的数据记录使内业数据处理工作量大大增加,采用基于Windows Mobile系统的PDA作为记录器,并利用Visual Studio 2008开发环境对其功能进行实现,取得了较好的运行效果,已试验性地运用于三峡工程安全监测项目中。阐述了垂线、引张线数据采集及处理系统的目标和主要功能,介绍了系统的设计目标、系统功能的实现以及系统的操作流程。展开更多
基金supported by STI 2030-Major Projects 2021ZD0200400National Natural Science Foundation of China(62276233 and 62072405)Key Research Project of Zhejiang Province(2023C01048).
文摘Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and share such multimodal data.However,due to professional discrepancies among annotators and lax quality control,noisy labels might be introduced.Recent research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the DNNs.To address this challenging problem,we present a Multimodal Robust Meta Learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities simultaneously.Specifically,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network training.Besides,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy labels.We conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.
基金supported by Ford Motor Company Research and Innovation Center
文摘Driver state sensing technologies, such as vehicular systems, start to be widely considered by automotive manufacturers. To reduce the cost and minimize the intrusiveness towards driving, the majority of these systems rely on the in-cabin camera(s) and other optical sensors. With their great capabilities in detecting and intervening of driver distraction and inattention,these technologies may become key components in future vehicle safety and control systems. However, to the best of our knowledge,currently, there is no common standard available to objectively compare the performance of these technologies. Thus, it is imperative to develop one standardized process for evaluation purposes.In this paper, we propose one systematic and standardized evaluation process after successfully addressing three difficulties:1) defining and selecting the important influential individual and environmental factors, 2) countering the effects of individual differences and randomness in driver behaviors, and 3) building a reliable in-vehicle driver head motion tracking tool to collect ground-truth motion data. We have collected data on a large scale on a commercial driver state-sensing platform. For each subject, 30 to 40 minutes of head motion data was collected and included variables, such as lighting conditions, head/face features,and camera locations. The collected data was analyzed based on a proposed performance measure. The results show that the developed process can efficiently evaluate an individual camerabased driver state sensing product, which builds a common base for comparing the performance of different systems.
文摘The purpose of this study is to analyze the household waste reduction effect of sorted collection of recyclable waste in Japan using a panel data analysis, which considers time-series and cross-section data simultaneously. Also, the study shows the effect of the type of sorted items on the quantity of household waste disposed. We used the data attained from 103 cities recorded over three years, and applied the quantity of total waste disposed, the quantity of combustible waste, the quantity of other waste （waste excluding combustible and recyclable waste）, and the quantity of combustible plus other waste as objective variables, respectively, in the models. The result suggests that when the number of sorted items is increased marginally, the quantity of household waste decreases by about 0.5%-3.3% or 1.28-4.17 grams per capita per day. In addition, it is shown that sorting out white trays is effective in reducing the quantity of combustible waste. Sorting out paper containers and packages is also effective in reducing the quantity of other waste and combustible plus other waste.
文摘在遥测垂线坐标仪、遥测引张线仪尚未普及,且其可靠性有待进一步完善的情况下,传统的垂线、引张线的人工观测仍占居主导地位。因传统方法的数据记录使内业数据处理工作量大大增加,采用基于Windows Mobile系统的PDA作为记录器,并利用Visual Studio 2008开发环境对其功能进行实现,取得了较好的运行效果,已试验性地运用于三峡工程安全监测项目中。阐述了垂线、引张线数据采集及处理系统的目标和主要功能,介绍了系统的设计目标、系统功能的实现以及系统的操作流程。
