-
Article
PTDS CenterTrack: pedestrian tracking in dense scenes with re-identification and feature enhancement
Multi-object tracking in dense scenes has always been a major difficulty in this field. Although some existing algorithms achieve excellent results in multi-object tracking, they fail to achieve good generaliz...
-
Chapter and Conference Paper
Image Captioning with Global Information Enhanced Image Representation
In recent years, significant progress has been made in image captioning using the encoder-decoder framework. However, most of these methods fail to exploit global information effectively. Global information pr...
-
Chapter and Conference Paper
Robust Target Detection and Localization for UAV Autonomous Landing with Partially Occluded Targets
This paper presents an approach for robust target detection and localization in the context of UAV autonomous landing with partially occluded targets. Since the performance of the autonomous landing system lar...
-
Chapter and Conference Paper
Class Incremental Learning Method for Hyperspectral Images Based on Real Data Playback Mechanism and Classification Network Optimization
In recent years, the hyperspectral image (HSI) classification has attracted great attention in the field of earth observation. With the expansion of application scenarios and the continuous improvement of appl...
-
Article
IgG4-related disease with kidney and lymph nodes involvement: a case-based review
IgG4-related disease (IgG4-RD), a rare immune-mediated chronic fibro-inflammatory condition, has various initial symptoms, thus posing diagnostic and therapeutic challenges. Here, we report a case of IgG4-RD i...
-
Article
Open AccessComprehensive single-cell transcriptomic and proteomic analysis reveals NK cell exhaustion and unique tumor cell evolutionary trajectory in non-keratinizing nasopharyngeal carcinoma
Nonkeratinizing nasopharyngeal carcinoma (NK-NPC) has a strong association with Epstein-Barr virus (EBV) infection. The role of NK cells and the tumor cell evolutionary trajectory in NK-NPC remain unclear. In ...
-
Article
Diffeomorphic matching with multiscale kernels based on sparse parameterization for cross-view target detection
We present a novel, robust target detection method to locate a target from a reference image (UAV image) according to a target image (remote sensing satellite image). Using sparse parameterization diffeomorphi...
-
Chapter and Conference Paper
Super Resolution of Unpaired MR Images Based on Domain Migration
High-resolution magnetic resonance imaging (MRI) is very important for doctors to judge the condition. At present, the depth learning method has been widely studied in the super-resolution reconstruction of MR...
-
Chapter and Conference Paper
Radar Waveform Gaming Configurable Framework Based on Deep Reinforcement Learning
Radar faces a variety of different jamming techniques, among which mainlobe jamming is difficult to deal with. Traditional experience-based passive anti-jamming methods are usually less effective when facing f...
-
Article
Shift work and nonalcoholic fatty liver disease incidence among Chinese rail workers: a 4-year longitudinal cohort study
Occupational harmful factors, such as shift work, are attracting increasing attention as a potential cause of nonalcoholic fatty liver disease (NAFLD). In this study, we aimed to identify the association betwe...
-
Article
Open AccessThree Novel Variants of CEP290 and CC2D2DA and a Link Between ZNF77 and SHH Signaling Pathway Are Found in Two Meckel-Gruber Syndrome Fetuses
Meckel-Gruber syndrome (MKS) is a rare lethal autosomal recessive inherited disorder. Missed diagnosis might happen in clinical works due to an unclear genotype–phenotype correlation. We analyzed two families ...
-
Chapter and Conference Paper
Small Object Detection Based on Multi-source Data Learning Fusion Network
Small object group detection is a difficult task in the field of object detection. In recent years, with the development of sensing technology and unmanned driving, there are more and more multi-source data in...
-
Chapter and Conference Paper
Channel Pruning and Quantization-Based Learning for Object Detection with Computing Source Limited Application
the rise of convolutional neural network (CNN) in the field of computer vision, more and more practical applications need to deploy CNN on mobile devices. However, due to the large amount of CNN computi...
-
Article
Long-term exposure to high particulate matter pollution and incident hypertension: a 12-year cohort study in northern China
Numerous cohort studies have reported the association of long-term exposure to particulate matter <10 μm in diameter (PM10) and hypertension in American and European countries. However, these results have been in...
-
Article
Open AccessA longitudinal sampling study of transcriptomic and epigenetic profiles in patients with thrombocytopenia syndrome
Severe fever with thrombocytopenia syndrome (SFTS) is a novel tick-borne infectious disease caused by a new type of SFTS virus (SFTSV). Here, a longitudinal sampling study is conducted to explore the differenc...
-
Article
Open AccessInhibition of autophagy by CRMP2-derived peptide ST2-104 (R9-CBD3) via a CaMKKβ/AMPK/mTOR pathway contributes to ischemic postconditioning-induced neuroprotection against cerebral ischemia-reperfusion injury
Cerebral ischemia, a common cerebrovascular disease, is characterized by functional deficits and apoptotic cell death. Autophagy, a type of programmed cell death, plays critical roles in controlling neuronal d...
-
Chapter and Conference Paper
SCHC: Incorporating Social Contagion and Hashtag Consistency for Topic-Oriented Social Summarization
The boom of social media platforms like Twitter brings the large scale short, noisy and redundant messages, making it difficult for people to obtain essential information. We study extractive topic-oriented so...
-
Chapter and Conference Paper
Exploiting Explicit and Inferred Implicit Personas for Multi-turn Dialogue Generation
Learning and utilizing personas in open-domain dialogue have become a hotspot in recent years. The existing methods that only use predefined explicit personas enhance the personality to some extent, however, t...
-
Article
Open AccessHighly efficient and air-stable Eu(II)-containing azacryptates ready for organic light-emitting diodes
Divalent europium 5d-4f transition has aroused great attention in many fields, in a way of do** Eu2+ ions into inorganic solids. However, molecular Eu2+ complexes with 5d-4f transition are thought to be too air...
-
Article
Lysionotin attenuates Staphylococcus aureus pathogenicity by inhibiting α-toxin expression
α-Toxin, one of the best known pore-forming proteins produced by Staphylococcus aureus (S. aureus), is a critical virulence factor in multiple infections. The necessity of α-toxin for S. aureus pathogenicity sugg...
