-
Article
ULAF-Net: Ultra lightweight attention fusion network for real-time semantic segmentation
Real-time semantic segmentation, laying the foundation of mobile robots and autonomous driving, has attracted much attention in recent years. Currently, most deep models suffer high computational costs due to ...
-
Article
Exploring and exploiting hierarchical structures for large-scale classification
Classification and recognition tasks confronted by intelligent systems are becoming complicated as the sizes of samples, dimensionality and labels dramatically increase in the past few years. Learning machines...
-
Article
Open AccessAssociation between social capital and utilization of essential public health services among elderly migrants: a multilevel logistic study based on the 2017 China migrant dynamic survey (CMDS)
As the number of elderly migrants in China continues to grow, it is necessary to pay closer attention to their health and health services. Some studies have confirmed that social capital plays a significant ro...
-
Article
Transcriptome analysis and functional validation reveal the novel role of LhCYCL in axillary bud development in hybrid Liriodendron
Shoot branching significantly influences yield and timber quality in woody plants, with hybrid Liriodendron being particularly valuable due to its rapid growth. However, understanding of the mechanisms governing ...
-
Article
Integrated Heterogeneous Graph Attention Network for Incomplete Multi-modal Clustering
Incomplete multi-modal clustering (IMmC) is challenging due to the unexpected missing of some modalities in data. A key to this problem is to explore complementarity information among different samples with in...
-
Article
Unsupervised deep hashing with multiple similarity preservation for cross-modal image-text retrieval
Deep hashing cross-modal image-text retrieval has the advantage of low storage cost and high retrieval efficiency by map** different modal data into a Hamming space. However, the existing unsupervised deep h...
-
Article
Genomic survey, bioinformatics analysis, and expression profiles of TCP genes in Liriodendron chinense and functional characterization of LcTCP4
TEOSINTE-BRANCHED/CYCLOIDEA/PCF (TCP) proteins are plant-specific transcription factors (TFs) that play a pivotal role in leaf development by controlling cell proliferation and differentiation. In this study, ...
-
Article
Open AccessTargeting P2Y14R protects against necroptosis of intestinal epithelial cells through PKA/CREB/RIPK1 axis in ulcerative colitis
Purinergic signaling plays a causal role in the pathogenesis of inflammatory bowel disease. Among purinoceptors, only P2Y14R is positively correlated with inflammatory score in mucosal biopsies of ulcerative coli...
-
Article
Immunomodulatory macrophages and Treg in pulmonary hypertension
Pulmonary hypertension (PH) is a disease that affects the right ventricle and venous circulation. The need for improvement in the discovery of novel therapeutic targets and drugs focusing on the immunomodulato...
-
Chapter and Conference Paper
Weakly-Supervised Grounding for VQA with Dual Visual-Linguistic Interaction
Visual question answer (VQA) grounding, aimed at locating the visual evidence associated with the answers while answering questions, has attracted increasing research interest. To locate the evidence, most exi...
-
Article
Open AccessExtracellular vesicles in venous thromboembolism and pulmonary hypertension
Venous thromboembolism (VTE) is a multifactorial disease, and pulmonary hypertension (PH) is a serious condition characterized by pulmonary vascular remodeling leading with increased pulmonary vascular resista...
-
Article
Open AccessPathogenetic detection, retrospective and pathogenicity analysis of a fatal case of Vibrio vulnificus in Shenzhen, China
We report a 36-year-old male patient died of V. vulnificus-induced septicaemia and multiple organ failure syndrome after oyster consumption at a restaurant. We isolated and identified V. vulnificus vv16015 from t...
-
Article
AutoEncoder-Driven Multimodal Collaborative Learning for Medical Image Synthesis
Multimodal medical images have been widely applied in various clinical diagnoses and treatments. Due to the practical restrictions, certain modalities may be hard to acquire, resulting in incomplete data. Exis...
-
Article
Building hierarchical class structures for extreme multi-class learning
Class hierarchical structures play a significant role in large and complex tasks of machine learning. Existing studies on the construction of such structures follow a two-stage strategy. The category similarit...
-
Article
Open AccessCo-profiling reveals distinct patterns of genomic chromatin accessibility and gene expression in pulmonary hypertension caused by chronic hypoxia
Aberrant gene expression is a key mechanism underlying pulmonary hypertension (PH) development. The alterations of genomic chromatin accessibility and their relationship with the aberrant gene expressions in P...
-
Article
Dual-branch network with memory for video anomaly detection
Anomaly event detection is a video surveillance technology automatically analyzing video sequences without manual intervention by employing machine learning and computer vision technology. In the existing appr...
-
Article
A Model-based Design of the Water Membrane Evaporator for the Advanced Spacesuit
A spacesuit water membrane evaporator (SWME) based on the hollow fiber membrane bundle is regarded as a promising technology for the advanced thermal management system of the next-generation spacesuit. This pa...
-
Chapter and Conference Paper
Correction to: Lightweight Model Inference on Resource-Constrained Computing Nodes in Intelligent Surveillance Systems
-
Chapter and Conference Paper
MRSCN: A GNN-based Model for Mining Relationship Strength Changes Between Nodes in Dynamic Networks
The relationship strength between individuals in the network is an essential task in network analysis. However, existing measures of relationship strength are mostly artificially predefined, which can only ref...
-
Chapter and Conference Paper
Lightweight Model Inference on Resource-Constrained Computing Nodes in Intelligent Surveillance Systems
Intelligent Surveillance System (ISS) is an important application combining deep learning with IoT technologies. Meanwhile, multiple targets multiple camera tracking (MTMCT) has been widely recognized as a pro...
