At present,convolutional neural networks(CNNs)and transformers surpass humans in many situations(such as face recognition and object classification),but do not work well in identifying fibers in textile surface images...At present,convolutional neural networks(CNNs)and transformers surpass humans in many situations(such as face recognition and object classification),but do not work well in identifying fibers in textile surface images.Hence,this paper proposes an architecture named FiberCT which takes advantages of the feature extraction capability of CNNs and the long-range modeling capability of transformer decoders to adaptively extract multiple types of fiber features.Firstly,the convolution module extracts fiber features from the input textile surface images.Secondly,these features are sent into the transformer decoder module where label embeddings are compared with the features of each type of fibers through multi-head cross-attention and the desired features are pooled adaptively.Finally,an asymmetric loss further purifies the extracted fiber representations.Experiments show that FiberCT can more effectively extract the representations of various types of fibers and improve fiber identification accuracy than state-of-the-art multi-label classification approaches.展开更多
The earliest paper currencies in existence in China were handcrafted during the Yuan dynasty.These currencies were scientifically excavated from different ruins or tombs,whereas scientific analyses of the papers are r...The earliest paper currencies in existence in China were handcrafted during the Yuan dynasty.These currencies were scientifically excavated from different ruins or tombs,whereas scientific analyses of the papers are rare.This study used optical and scanning electron microscopy to examine the fibers collected in Yuan dynasty paper currencies in conjunction with the Herzberg staining method.Despite differences in circulation period,paper fibers in both Zhi Yuan Tong Xing Bao Chao(two Guan)and Zhong Tong Yuan Bao Jiao Chao(one Guan and 500 Wen,issued in Zhi Zheng period)were identified as similar papermaking materials,bast fibers of mulberry bark.The results indicate that mulberry bark,a durable papermaking material used since ancient times,was mainly utilized as a raw material in these Yuan dynasty paper currency.This fiber identification work solved the critical problem of papermaking material in the Yuan dynasty paper currency and provided important information for conserving these precious cultural relics.展开更多
One of the impediments in the genetic improvement of cotton fiber is the paucity of information about genes associated with fiber development.Availability of chromosome arm substitution line CS-
Actin cytoskeleton plays an important role in cell morphogenesis in plants as demonstrated by pharmacological,biochemical,and genetic studies.The actin cytoskeleton may be involved in
Twenty-eight candidate genes provided by other sub-projects were used to produce transgenic cotton plants.There were over 1000 individuals,and some of them were generation T2 or T3.All
Upland cotton (Gossypium hirsutum L.) is an allotetraploid species originated from interspecific hybridization between AA-genome diploid (G. arboretum) and DD-genome diploid (G. raimondii) (Wendel et al., 1992...Upland cotton (Gossypium hirsutum L.) is an allotetraploid species originated from interspecific hybridization between AA-genome diploid (G. arboretum) and DD-genome diploid (G. raimondii) (Wendel et al., 1992). Cotton fibers are single-celled trichomes that emerge from the ovule epidermal cells. Indexed by the number of days post-anthesis (dpa), fiber morphogenesis includes four distinct but overlapping steps: initiation (0-3 dpa), elongation (3-20 dpa), secondary cell wall thickening (15-45 dpa) and maturation (40-60 dpa) (Yang et al., 2008, Du et al., 2013). The efficiency and duration of each morphogenesis stage is important to the quality attributes of the mature fiber. Cell elongation is critical for fiber length, whereas secondary cell wall thickening is important for fiber fineness and strength (Meinert and Delmer, 1977).展开更多
基金National Natural Science Foundation of China(No.61972081)Fundamental Research Funds for the Central Universities,China(No.2232023Y-01)Natural Science Foundation of Shanghai,China(No.22ZR1400200)。
文摘At present,convolutional neural networks(CNNs)and transformers surpass humans in many situations(such as face recognition and object classification),but do not work well in identifying fibers in textile surface images.Hence,this paper proposes an architecture named FiberCT which takes advantages of the feature extraction capability of CNNs and the long-range modeling capability of transformer decoders to adaptively extract multiple types of fiber features.Firstly,the convolution module extracts fiber features from the input textile surface images.Secondly,these features are sent into the transformer decoder module where label embeddings are compared with the features of each type of fibers through multi-head cross-attention and the desired features are pooled adaptively.Finally,an asymmetric loss further purifies the extracted fiber representations.Experiments show that FiberCT can more effectively extract the representations of various types of fibers and improve fiber identification accuracy than state-of-the-art multi-label classification approaches.
文摘The earliest paper currencies in existence in China were handcrafted during the Yuan dynasty.These currencies were scientifically excavated from different ruins or tombs,whereas scientific analyses of the papers are rare.This study used optical and scanning electron microscopy to examine the fibers collected in Yuan dynasty paper currencies in conjunction with the Herzberg staining method.Despite differences in circulation period,paper fibers in both Zhi Yuan Tong Xing Bao Chao(two Guan)and Zhong Tong Yuan Bao Jiao Chao(one Guan and 500 Wen,issued in Zhi Zheng period)were identified as similar papermaking materials,bast fibers of mulberry bark.The results indicate that mulberry bark,a durable papermaking material used since ancient times,was mainly utilized as a raw material in these Yuan dynasty paper currency.This fiber identification work solved the critical problem of papermaking material in the Yuan dynasty paper currency and provided important information for conserving these precious cultural relics.
文摘One of the impediments in the genetic improvement of cotton fiber is the paucity of information about genes associated with fiber development.Availability of chromosome arm substitution line CS-
文摘Actin cytoskeleton plays an important role in cell morphogenesis in plants as demonstrated by pharmacological,biochemical,and genetic studies.The actin cytoskeleton may be involved in
文摘Twenty-eight candidate genes provided by other sub-projects were used to produce transgenic cotton plants.There were over 1000 individuals,and some of them were generation T2 or T3.All
基金supported by the grants from the State Key Basic Research and Development Plan (No. 2010CB126003)the National Transgenic Animals and Plants Research Project (Nos. 2011ZX08005-003 and 2011ZX08009-003)
文摘Upland cotton (Gossypium hirsutum L.) is an allotetraploid species originated from interspecific hybridization between AA-genome diploid (G. arboretum) and DD-genome diploid (G. raimondii) (Wendel et al., 1992). Cotton fibers are single-celled trichomes that emerge from the ovule epidermal cells. Indexed by the number of days post-anthesis (dpa), fiber morphogenesis includes four distinct but overlapping steps: initiation (0-3 dpa), elongation (3-20 dpa), secondary cell wall thickening (15-45 dpa) and maturation (40-60 dpa) (Yang et al., 2008, Du et al., 2013). The efficiency and duration of each morphogenesis stage is important to the quality attributes of the mature fiber. Cell elongation is critical for fiber length, whereas secondary cell wall thickening is important for fiber fineness and strength (Meinert and Delmer, 1977).