Existing unsupervised person re-identification approaches fail to fully capture thefine-grained features of local regions,which can result in people with similar appearances and different identities being assigned the...Existing unsupervised person re-identification approaches fail to fully capture thefine-grained features of local regions,which can result in people with similar appearances and different identities being assigned the same label after clustering.The identity-independent information contained in different local regions leads to different levels of local noise.To address these challenges,joint training with local soft attention and dual cross-neighbor label smoothing(DCLS)is proposed in this study.First,the joint training is divided into global and local parts,whereby a soft attention mechanism is proposed for the local branch to accurately capture the subtle differences in local regions,which improves the ability of the re-identification model in identifying a person’s local significant features.Second,DCLS is designed to progressively mitigate label noise in different local regions.The DCLS uses global and local similarity metrics to semantically align the global and local regions of the person and further determines the proximity association between local regions through the cross information of neighboring regions,thereby achieving label smoothing of the global and local regions throughout the training process.In extensive experiments,the proposed method outperformed existing methods under unsupervised settings on several standard person re-identification datasets.展开更多
This paper proposes a star type multiport hybrid circuit breaker(Star-HCB)topology for protection of multiterminal DC transmission.Reliability and stability of high voltage DC(HVDC)grids are determined by their capabi...This paper proposes a star type multiport hybrid circuit breaker(Star-HCB)topology for protection of multiterminal DC transmission.Reliability and stability of high voltage DC(HVDC)grids are determined by their capabilities to withstand DC-side faults.In order to maintain reliability of HVDC grids,both ends of each line should be equipped with hybrid circuit breakers(HCB).This method will increase expenditure of the HVDC,especially the meshed topology.The n-port Star-HCB consists of ultra-fast mechanical disconnectors,load current switch and only one transferring branch which is formed by improved half-bridge sub-module.Compared with existing traditional hybrid circuit breakers and other multiport hybrid circuit breakers,the proposed topology can realize the same short-circuit blocking goal using fewer components.Detailed mathematical transient process calculation and timedomain simulation of the proposed Star-HCB are given to verify its superiority.展开更多
Small-cell lung cancer(SCLC)is a highly malignant cancer with characteristics of rapid growth,abundant angiogenesis,and early distant metastasis that accounts for about 15%of lung cancers.With the wide application of ...Small-cell lung cancer(SCLC)is a highly malignant cancer with characteristics of rapid growth,abundant angiogenesis,and early distant metastasis that accounts for about 15%of lung cancers.With the wide application of low-dose computed tomography screening in recent years,the incidence of early limited-stage SCLC has increased dramatically.展开更多
基金supported by the National Natural Science Foundation of China under Grant Nos.62076117 and 62166026the Jiangxi Key Laboratory of Smart City under Grant No.20192BCD40002Jiangxi Provincial Natural Science Foundation under Grant No.20224BAB212011.
文摘Existing unsupervised person re-identification approaches fail to fully capture thefine-grained features of local regions,which can result in people with similar appearances and different identities being assigned the same label after clustering.The identity-independent information contained in different local regions leads to different levels of local noise.To address these challenges,joint training with local soft attention and dual cross-neighbor label smoothing(DCLS)is proposed in this study.First,the joint training is divided into global and local parts,whereby a soft attention mechanism is proposed for the local branch to accurately capture the subtle differences in local regions,which improves the ability of the re-identification model in identifying a person’s local significant features.Second,DCLS is designed to progressively mitigate label noise in different local regions.The DCLS uses global and local similarity metrics to semantically align the global and local regions of the person and further determines the proximity association between local regions through the cross information of neighboring regions,thereby achieving label smoothing of the global and local regions throughout the training process.In extensive experiments,the proposed method outperformed existing methods under unsupervised settings on several standard person re-identification datasets.
基金supported by the Institute of Electrical Engineering,CAS under grant(E155610101,E155610201 and E155610301).
文摘This paper proposes a star type multiport hybrid circuit breaker(Star-HCB)topology for protection of multiterminal DC transmission.Reliability and stability of high voltage DC(HVDC)grids are determined by their capabilities to withstand DC-side faults.In order to maintain reliability of HVDC grids,both ends of each line should be equipped with hybrid circuit breakers(HCB).This method will increase expenditure of the HVDC,especially the meshed topology.The n-port Star-HCB consists of ultra-fast mechanical disconnectors,load current switch and only one transferring branch which is formed by improved half-bridge sub-module.Compared with existing traditional hybrid circuit breakers and other multiport hybrid circuit breakers,the proposed topology can realize the same short-circuit blocking goal using fewer components.Detailed mathematical transient process calculation and timedomain simulation of the proposed Star-HCB are given to verify its superiority.
文摘Small-cell lung cancer(SCLC)is a highly malignant cancer with characteristics of rapid growth,abundant angiogenesis,and early distant metastasis that accounts for about 15%of lung cancers.With the wide application of low-dose computed tomography screening in recent years,the incidence of early limited-stage SCLC has increased dramatically.
