-
Article
Global–local Bi-alignment for purer unsupervised domain adaptation
Unsupervised domain adaptation (UDA) aims to extract domain-invariant features. Existing UDA methods mainly utilize a convolutional neural network (CNN) or vision transformer (ViT) as feature extractor, which ...
-
Article
AAR:Attention Remodulation for Weakly Supervised Semantic Segmentation
Weakly Supervised Semantic Segmentation is a crucial task in computer vision. However, existing methods that utilize Class Activation Maps (CAMs) with classification tasks can only identify a small part of the...
-
Article
Complete joint global and local collaborative marginal fisher analysis
Marginal Fisher analysis (MFA) maintains the nearest neighbor structure according to the class information of samples, so it achieves good recognition results for image recognition task. However, MFA needs to ...
-
Article
SiamLight: lightweight networks for object tracking via attention mechanisms and pixel-level cross-correlation
Despite Siamese-based trackers have achieved great success in recent years, researchers have focused more on the accuracy of trackers than their complexity, which leads to their inapplicability in some scenari...
-
Article
Smarter peer learning for online knowledge distillation
Model distillation is an effective way to let a less-parameterized student model learn the knowledge of a large teacher model. It requires a well-trained and high-performance model in advance, which limits the...
-
Article
Open AccessMetabolome and transcriptome analyses reveal chlorophyll and anthocyanin metabolism pathway associated with cucumber fruit skin color
Fruit skin color play important role in commercial value of cucumber, which is mainly determined by the content and composition of chlorophyll and anthocyanins. Therefore, understanding the related genes and m...
-
Article
Transcriptome analysis in different chieh-qua cultivars provides new insights into drought-stress response
Drought, one of the crucial environmental constraints, seriously threats the quality and yield in chieh-qua. Therefore, cultivating drought-tolerant variety is greatly necessary for its normal growth under wat...
-
Chapter and Conference Paper
Two Dimensional Orthogonal Constrained Maximum Variance Map** for Face Recognition
Constrained maximum variance map** (CMVM) is one promising feature extraction technique for face recognition. However, CMVM suffers from the well-known small sample size (SSS) problem, where the number of sa...
-
Article
Genetic analysis and QTL map** of fruit-related traits in wax gourd (Benincasa hispida)
As an important fruit vegetable, fruit-related traits have become one of the breeding hotspots of wax gourd (Benincasa hispida). The fruit traits have an important role on the quality and yield of wax gourd, and ...
-
Chapter and Conference Paper
Null Space Diversity Fisher Discriminant Analysis for Face Recognition
The feature extraction algorithms, which attempt to project the original data contained in a lower dimensional feature space, have drawn much attention. In this paper, based on enhanced fisher discriminant cri...
-
Article
Open AccessHigh-density genetic map construction and gene map** of pericarp color in wax gourd using specific-locus amplified fragment (SLAF) sequencing
High-density map is a valuable tool for genetic and genomic analysis. Although wax gourd is a widely distributed vegetable of Cucurbitaceae and has important medicinal and health value, no genetic map has been co...
-
Article
The first Illumina-based de novo transcriptome sequencing and analysis of pumpkin (Cucurbita moschata Duch.) and SSR marker development
Pumpkin (Cucurbita moschata Duch.) is an important vegetable crop cultivated worldwide. In this study, the pumpkin transcriptome was sequenced by RNA-seq using the Illumina Hiseq 2000. A total of 52,849,316 clean...
-
Article
Transgenic expression of an insect diapause-specific peptide (DSP) in Arabidopsis resists phytopathogenic fungal attacks
Diapause-specific peptide (DSP) is an insect antimicrobial peptide, composed of 41 amino acid residues including six cysteines and isolated from diapausing adults of the leaf beetle Gastrophysa atrocyaneais. Rece...
-
Chapter and Conference Paper
Kernel Optimal Unsupervised Discriminant Projection and Its Application to Face Recognition
Kernel Optimal Unsupervised Discriminant Projection (KOUDP) is presented in this paper. The proposed method first maps the input data into a potentially much higher dimensional feature space by virtue of nonli...
