Vehicle re-identification is one of the core technologies of intelligent transportation systems, and it is crucial for the construction of smart cities. With the rapid development of deep learning, vehicle re-identification technologies have made significant progress in recent years. Therefore, making a comprehensive survey about the vehicle re-identification methods based on deep learning is quite indispensable. There are mainly five types of deep learning-based methods designed for vehicle re-identification, i.e. methods based on local features, methods based on representation learning, methods based on metric learning, methods based on unsupervised learning, and methods based on attention mechanism. The major contributions of our survey come from three aspects. First, we give a comprehensive review of the current five types of deep learning-based methods for vehicle re-identification, and we further compare them from characteristics, advantages, and disadvantages. Second, we sort out vehicle public datasets and compare them from multiple dimensions. Third, we further discuss the challenges and possible research directions of vehicle re-identification in the future based on our survey. INDEX TERMS Deep learning, intelligent transportation system, vehicle re-identification, vehicle public datasets.
A new three-dimensional bimetallic tellurite, BaV2TeO8, was synthesized by the hydrothermal reaction of Ba(OH)2, TeO2 and V2O5, and characterized by single-crystal X-ray diffraction. The three-dimensional framework is built up from anionic [V2TeO8]n(2n-) layers parallel to (101) and connected via Ba-O bonds. The anionic layers are formed by three types of polyhedra, namely VO5 tetragonal pyramids, VO(4) tetrahedra and TeO(4+2) 'folded square' polyhedra.
BackgroundAlthough the functional damage of the diabetic pancreas can affect the postoperative recovery of pancreatic cancer patients, there is no significant difference in the prognosis of pancreatic cancer patients with a history of diabetes and ordinary pancreatic cancer patients. There is still no practical theory to explain this phenomenon.Materials and MethodThe mRNA expression profile data of 141 cases and 51 cases with clinical data of diabetes status were obtained from the TCGA database and the GEO database, respectively. The CRA001160 data set was obtained in the TISCH database. The Seurat was used to process single-cell expression profile sequencing data. The Cibersortx was used to construct a feature matrix of single-cell sequencing data and to deconvolve Bulk-RNAseq data to obtain each pancreatic cancer patients’ tumour invasion score. TIDE was used to assess the immune escape potential of the tumour. MiRNet was used to construct the miRNA-mRNA regulatory network.ResultCompared with regular pancreatic cancer patients, the immune-related signal transduction pathways in diabetic pancreatic cancer patients are in an activated state. In patients with diabetic pancreatic cancer, the infiltration score of CD8+ T cells is high, and the infiltration score of corresponding malignant tumour cells is low. The Bayesian classifier can distinguish diabetic pancreatic cancer patients from non-diabetic pancreatic cancer patients based on 10 signature genes. The miRNA-mRNA regulatory network suggests that regulation by miRNA can influence mRNA expression and thus prognostic survival of pancreatic cancer patients.ConclusionThe activation of inflammatory-related signalling pathways in diabetic pancreatic cancer patients increases the immune infiltration of CD8+ T cells in cancer patients and reduces the development of malignant tumour tissues. The expression of 10 signature genes allowed the diagnosis of diabetic and non-diabetic pancreatic cancer patients. The miRNA-mRNA regulatory network may be the main cause of the differences in the tumour inflammatory microenvironment between the two groups of patients. These findings help us further understand the immune microenvironment of patients with diabetic pancreatic cancer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.