Clothing attribute recognition has become an essential technology,which enables users to automatically identify the characteristics of clothes and search for clothing images with similar attributes.However,existing me...Clothing attribute recognition has become an essential technology,which enables users to automatically identify the characteristics of clothes and search for clothing images with similar attributes.However,existing methods cannot recognize newly added attributes and may fail to capture region-level visual features.To address the aforementioned issues,a region-aware fashion contrastive language-image pre-training(RaF-CLIP)model was proposed.This model aligned cropped and segmented images with category and multiple fine-grained attribute texts,achieving the matching of fashion region and corresponding texts through contrastive learning.Clothing retrieval found suitable clothing based on the user-specified clothing categories and attributes,and to further improve the accuracy of retrieval,an attribute-guided composed network(AGCN)as an additional component on RaF-CLIP was introduced,specifically designed for composed image retrieval.This task aimed to modify the reference image based on textual expressions to retrieve the expected target.By adopting a transformer-based bidirectional attention and gating mechanism,it realized the fusion and selection of image features and attribute text features.Experimental results show that the proposed model achieves a mean precision of 0.6633 for attribute recognition tasks and a recall@10(recall@k is defined as the percentage of correct samples appearing in the top k retrieval results)of 39.18 for composed image retrieval task,satisfying user needs for freely searching for clothing through images and texts.展开更多
An attribute recognition model for safe thickness assessment between a concealed karst cave and a tunnel is established based on the attribute mathematic theory.The model can be applied to carrying out risk classifica...An attribute recognition model for safe thickness assessment between a concealed karst cave and a tunnel is established based on the attribute mathematic theory.The model can be applied to carrying out risk classification of the safe thickness between a concealed karst cave and a tunnel and to guarantee construction’s safety in tunnel engineering.Firstly,the assessment indicators and classification standard of safe thickness between a concealed karst cave and a tunnel are studied based on the perturbation method.Then some attribute measurement functions are constructed to compute the attribute measurement of each single index and synthetic attribute measurement.Finally,the identification and classification of risk assessment of safe thickness between a concealed karst cave and a tunnel are recognized by the confidence criterion.The results of two engineering application show that the evaluation results agree well with the site situations in construction.The results provide a good guidance for the tunnel construction.展开更多
In our study, entropy weight coefficients, based on Shannon entropy, were determined for an attribute recognition model to model the quality of groundwater sources. The model follows the theory previously proposed by ...In our study, entropy weight coefficients, based on Shannon entropy, were determined for an attribute recognition model to model the quality of groundwater sources. The model follows the theory previously proposed by Chen Q S. In the model, firstly, the author establishes the attribute space matrix and determines the weight based on Shannon entropy theory; secondly, calculates attribute measure; thirdly, evaluates that with confidence criterion and score criterion; finally, an application example is given. The results show that the water quality of the groundwater sources for the city comes up to the grade II or III standard. There is no pollution that obviously exceeds the standard and the water can meet people’s needs .The results from an evaluation of this model are in basic agreement with the observed situation and with a set pair analysis (SPA) model.展开更多
The attribute recognition model (ARM) has been widely used to make comprehensive assessment in many engineering fields, such as environment, ecology, and economy. However, large numbers of experiments indicate that th...The attribute recognition model (ARM) has been widely used to make comprehensive assessment in many engineering fields, such as environment, ecology, and economy. However, large numbers of experiments indicate that the value of weight vector has no relativity to its initial value but depends on the data of Quality Standard and actual samples. In the present study, the ARM is enhanced with the technique of data driving, which means some more groups of data from the Quality Standard are selected with the uniform random method to make the calculation of weight values more rational and more scientific. This improved attribute recognition model (IARM) is applied to a real case of assessment on seawater quality. The given example shows that the IARM has the merits of being simple in principle, easy to operate, and capable of producing objective results, and is therefore of use in evaluation problems in marine environment science.展开更多
In order to solve emitter recognition problems in a practical reconnaissance environment, attribute mathematics is introduced. The basic concepts and theory of attribute set and attribute measure are described i n det...In order to solve emitter recognition problems in a practical reconnaissance environment, attribute mathematics is introduced. The basic concepts and theory of attribute set and attribute measure are described i n detail. A new attribute recognition method based on attribute measure is prese nted in this paper. Application example is given, which demonstrates this new me thod is accurate and effective. Moreover, computer simulation for recognizing th e emitter purpose is selected, and compared with classical statistical pattern r ecognition through simulation. The excellent experimental results demonstrate t hat this is a brand-new attribute recognition method as compared to existing st atistical pattern recognition techniques.展开更多
Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method ba...Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention(VALA), which utilizes view information to guide the recognition process to focus on specific attributes and attention mechanism to localize specific attribute-corresponding areas. Concretely, view information is leveraged by the view prediction branch to generate four view weights that represent the confidences for attributes from different views. View weights are then delivered back to compose specific view-attributes, which will participate and supervise deep feature extraction. In order to explore the spatial location of a view-attribute, regional attention is introduced to aggregate spatial information and encode inter-channel dependencies of the view feature. Subsequently, a fine attentive attribute-specific region is localized, and regional weights for the view-attribute from different spatial locations are gained by the regional attention. The final view-attribute recognition outcome is obtained by combining the view weights with the regional weights. Experiments on three wide datasets(richly annotated pedestrian(RAP), annotated pedestrian v2(RAPv2), and PA-100 K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.展开更多
Pedestrian attribute recognition is often considered as a multi-label image classification task. In order to make full use of attribute-related location information, a saliency guided self-attention network(SGSA-Net) ...Pedestrian attribute recognition is often considered as a multi-label image classification task. In order to make full use of attribute-related location information, a saliency guided self-attention network(SGSA-Net) was proposed to weakly supervise attribute localization, without annotations of attribute-related regions. Saliency priors were integrated into the spatial attention module(SAM). Meanwhile, channel-wise attention and spatial attention were introduced into the network. Moreover, a weighted binary cross-entropy loss(WCEL) function was employed to handle the imbalance of training data. Extensive experiments on richly annotated pedestrian(RAP) and pedestrian attribute(PETA) datasets demonstrated that SGSA-Net outperformed other state-of-the-art methods.展开更多
Water inrush is one of the most serious geological hazards in underground engineering construction.In order to effectively prevent and control the occurrence of water inrush,a new attribute interval recognition theory...Water inrush is one of the most serious geological hazards in underground engineering construction.In order to effectively prevent and control the occurrence of water inrush,a new attribute interval recognition theory and method is proposed to systematically evaluate the risk of water inrush in karst tunnels.Its innovation mainly includes that the value of evaluation index is an interval rather than a certain value;the single-index attribute evaluation model is improved non-linearly based on the idea of normal distribution;the synthetic attribute interval analysis method based on improved intuitionistic fuzzy theory is proposed.The TFN-AHP method is proposed to analyze the weight of evaluation index.By analyzing geological factors and engineering factors in tunnel zone,a multi-grade hierarchical index system for tunnel water inrush risk assessment is established.The proposed method is applied to ventilation incline of Xiakou tunnel,and its rationality and practicability is verified by comparison with field situation and evaluation results of other methods.In addition,the results evaluated by this method,which considers that water inrush is a complex non-linear system and the geological conditions have spatial variability,are more accurate and reliable.And it has good applicability in solving the problem of certain and uncertain problem.展开更多
Ulansuhai Lake is the important component part of irrigation and drainage system in Hetao irrigation region of Inner Mongolia.We applied the attribute recognition method in the summer water quality evaluation of Ulans...Ulansuhai Lake is the important component part of irrigation and drainage system in Hetao irrigation region of Inner Mongolia.We applied the attribute recognition method in the summer water quality evaluation of Ulansuhai Lake and divided according to the lake situation.The water quality in every area was analyzed,and the water quality situations in Ulansuhai Lake in 2006 and 2008 summer were gained.It provided the scientific basis for the effective utilization and the pollution treatment of Ulansuhai Lake.展开更多
基金National Natural Science Foundation of China(No.61971121)。
文摘Clothing attribute recognition has become an essential technology,which enables users to automatically identify the characteristics of clothes and search for clothing images with similar attributes.However,existing methods cannot recognize newly added attributes and may fail to capture region-level visual features.To address the aforementioned issues,a region-aware fashion contrastive language-image pre-training(RaF-CLIP)model was proposed.This model aligned cropped and segmented images with category and multiple fine-grained attribute texts,achieving the matching of fashion region and corresponding texts through contrastive learning.Clothing retrieval found suitable clothing based on the user-specified clothing categories and attributes,and to further improve the accuracy of retrieval,an attribute-guided composed network(AGCN)as an additional component on RaF-CLIP was introduced,specifically designed for composed image retrieval.This task aimed to modify the reference image based on textual expressions to retrieve the expected target.By adopting a transformer-based bidirectional attention and gating mechanism,it realized the fusion and selection of image features and attribute text features.Experimental results show that the proposed model achieves a mean precision of 0.6633 for attribute recognition tasks and a recall@10(recall@k is defined as the percentage of correct samples appearing in the top k retrieval results)of 39.18 for composed image retrieval task,satisfying user needs for freely searching for clothing through images and texts.
基金Projects(51509147,51879153) supported by the National Natural Science Foundation of ChinaProjects(2017JC002,2017JC001) supported by the Fundamental Research Funds of Shandong University,China
文摘An attribute recognition model for safe thickness assessment between a concealed karst cave and a tunnel is established based on the attribute mathematic theory.The model can be applied to carrying out risk classification of the safe thickness between a concealed karst cave and a tunnel and to guarantee construction’s safety in tunnel engineering.Firstly,the assessment indicators and classification standard of safe thickness between a concealed karst cave and a tunnel are studied based on the perturbation method.Then some attribute measurement functions are constructed to compute the attribute measurement of each single index and synthetic attribute measurement.Finally,the identification and classification of risk assessment of safe thickness between a concealed karst cave and a tunnel are recognized by the confidence criterion.The results of two engineering application show that the evaluation results agree well with the site situations in construction.The results provide a good guidance for the tunnel construction.
文摘In our study, entropy weight coefficients, based on Shannon entropy, were determined for an attribute recognition model to model the quality of groundwater sources. The model follows the theory previously proposed by Chen Q S. In the model, firstly, the author establishes the attribute space matrix and determines the weight based on Shannon entropy theory; secondly, calculates attribute measure; thirdly, evaluates that with confidence criterion and score criterion; finally, an application example is given. The results show that the water quality of the groundwater sources for the city comes up to the grade II or III standard. There is no pollution that obviously exceeds the standard and the water can meet people’s needs .The results from an evaluation of this model are in basic agreement with the observed situation and with a set pair analysis (SPA) model.
基金The authors would like to acknowledge the funding support of the National Natural Science Foundation of China （50579009, 70471090） the National 10 th Five Year Scientific Project of China for Tackling the Key Problems （2004BA608B-02 - 02） and the Excellence Youth Teacher Sustentation Fund Program of the Ministry of Education of China （Department of Education and Personnel [2002] 350）.
文摘The attribute recognition model (ARM) has been widely used to make comprehensive assessment in many engineering fields, such as environment, ecology, and economy. However, large numbers of experiments indicate that the value of weight vector has no relativity to its initial value but depends on the data of Quality Standard and actual samples. In the present study, the ARM is enhanced with the technique of data driving, which means some more groups of data from the Quality Standard are selected with the uniform random method to make the calculation of weight values more rational and more scientific. This improved attribute recognition model (IARM) is applied to a real case of assessment on seawater quality. The given example shows that the IARM has the merits of being simple in principle, easy to operate, and capable of producing objective results, and is therefore of use in evaluation problems in marine environment science.
文摘In order to solve emitter recognition problems in a practical reconnaissance environment, attribute mathematics is introduced. The basic concepts and theory of attribute set and attribute measure are described i n detail. A new attribute recognition method based on attribute measure is prese nted in this paper. Application example is given, which demonstrates this new me thod is accurate and effective. Moreover, computer simulation for recognizing th e emitter purpose is selected, and compared with classical statistical pattern r ecognition through simulation. The excellent experimental results demonstrate t hat this is a brand-new attribute recognition method as compared to existing st atistical pattern recognition techniques.
基金supported by National Key R&D Program of China(No.2018YFB1308000)Natural Science Foundation of Zhejiang province(No.LY21F 030018)。
文摘Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention(VALA), which utilizes view information to guide the recognition process to focus on specific attributes and attention mechanism to localize specific attribute-corresponding areas. Concretely, view information is leveraged by the view prediction branch to generate four view weights that represent the confidences for attributes from different views. View weights are then delivered back to compose specific view-attributes, which will participate and supervise deep feature extraction. In order to explore the spatial location of a view-attribute, regional attention is introduced to aggregate spatial information and encode inter-channel dependencies of the view feature. Subsequently, a fine attentive attribute-specific region is localized, and regional weights for the view-attribute from different spatial locations are gained by the regional attention. The final view-attribute recognition outcome is obtained by combining the view weights with the regional weights. Experiments on three wide datasets(richly annotated pedestrian(RAP), annotated pedestrian v2(RAPv2), and PA-100 K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.
基金supported by the National Natural Science Foundation of China (41874173)。
文摘Pedestrian attribute recognition is often considered as a multi-label image classification task. In order to make full use of attribute-related location information, a saliency guided self-attention network(SGSA-Net) was proposed to weakly supervise attribute localization, without annotations of attribute-related regions. Saliency priors were integrated into the spatial attention module(SAM). Meanwhile, channel-wise attention and spatial attention were introduced into the network. Moreover, a weighted binary cross-entropy loss(WCEL) function was employed to handle the imbalance of training data. Extensive experiments on richly annotated pedestrian(RAP) and pedestrian attribute(PETA) datasets demonstrated that SGSA-Net outperformed other state-of-the-art methods.
基金Project(51722904)supported by the National Science Fund for Excellent Young Scholars,ChinaProject(51679131)supported by the National Natural Science Foundation of China+2 种基金Project(2019JZZY010601)supported by the Shandong Provincial Key Research and Development Program(Major Scientific and Technological Innovation Project),ChinaProject(KJ1712304)supported by the Science and Technology Research Program of Chongqing Municipal Education Commission,ChinaProject(2016XJQN13)supported by the Yangtze Normal University Research Project,China
文摘Water inrush is one of the most serious geological hazards in underground engineering construction.In order to effectively prevent and control the occurrence of water inrush,a new attribute interval recognition theory and method is proposed to systematically evaluate the risk of water inrush in karst tunnels.Its innovation mainly includes that the value of evaluation index is an interval rather than a certain value;the single-index attribute evaluation model is improved non-linearly based on the idea of normal distribution;the synthetic attribute interval analysis method based on improved intuitionistic fuzzy theory is proposed.The TFN-AHP method is proposed to analyze the weight of evaluation index.By analyzing geological factors and engineering factors in tunnel zone,a multi-grade hierarchical index system for tunnel water inrush risk assessment is established.The proposed method is applied to ventilation incline of Xiakou tunnel,and its rationality and practicability is verified by comparison with field situation and evaluation results of other methods.In addition,the results evaluated by this method,which considers that water inrush is a complex non-linear system and the geological conditions have spatial variability,are more accurate and reliable.And it has good applicability in solving the problem of certain and uncertain problem.
基金Supported by National Natural Science Fund(50969005)
文摘Ulansuhai Lake is the important component part of irrigation and drainage system in Hetao irrigation region of Inner Mongolia.We applied the attribute recognition method in the summer water quality evaluation of Ulansuhai Lake and divided according to the lake situation.The water quality in every area was analyzed,and the water quality situations in Ulansuhai Lake in 2006 and 2008 summer were gained.It provided the scientific basis for the effective utilization and the pollution treatment of Ulansuhai Lake.
