Zhenwei He
YOU?
Author Swipe
View article: Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance
Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance Open
Single-domain generalization for object detection (S-DGOD) seeks to transfer learned representations from a single source domain to unseen target domains. While recent approaches have primarily focused on achieving feature invariance, they…
View article: Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptation
Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptation Open
Unsupervised domain adaptation (UDA) is a critical problem for transfer learning, which aims to transfer the semantic information from labeled source domain to unlabeled target domain. Recent advancements in UDA models have demonstrated si…
View article: Natural products as the therapeutic strategies for addiction
Natural products as the therapeutic strategies for addiction Open
World Drug Report 2023 concluded that 296 million people abused drugs, 39.5 million became addiction and 494,000 died as a direct or indirect result of addiction. Addiction has become a growing problem that affects individuals, their famil…
View article: Learning Causal Features for Incremental Object Detection
Learning Causal Features for Incremental Object Detection Open
Object detection limits its recognizable categories during the training phase, in which it can not cover all objects of interest for users. To satisfy the practical necessity, the incremental learning ability of the detector becomes a crit…
View article: Short-term wind power prediction model based on improved ACA-GRU neural network
Short-term wind power prediction model based on improved ACA-GRU neural network Open
To improve the accuracy of wind power forecasting, the improved ACA (Ant Colony Algorithm) is used to optimize the GRU (Gated Recurrent Unit) model. First, the original power generation data is normalized; Second, the GRU neural network mo…
View article: Development and validation of nomograms predicting postoperative survival in patients with chromophobe renal cell carcinoma
Development and validation of nomograms predicting postoperative survival in patients with chromophobe renal cell carcinoma Open
Objective The purpose of o ur study is to construct and validate nomograms that effectively predict postoperative overall survival and cancer-specific survival for patients with chromophobe renal cell carcinoma (chRCC). Method Clinical, so…
View article: Long Non-coding RNA HOTAIR in Central Nervous System Disorders: New Insights in Pathogenesis, Diagnosis, and Therapeutic Potential
Long Non-coding RNA HOTAIR in Central Nervous System Disorders: New Insights in Pathogenesis, Diagnosis, and Therapeutic Potential Open
Central nervous system (CNS) disorders, such as ischemic stroke, neurodegenerative diseases, multiple sclerosis, traumatic brain injury, and corresponding neuropathological changes, often lead to death or long-term disability. Long non-cod…
View article: Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
Tasks Integrated Networks: Joint Detection and Retrieval for Image Search Open
The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly. Howev…
View article: Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN
Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN Open
Conventional object detection models inevitably encounter a performance drop as the domain disparity exists. Unsupervised domain adaptive object detection is proposed recently to reduce the disparity between domains, where the source domai…
View article: Multi-adversarial Faster-RCNN for Unrestricted Object Detection
Multi-adversarial Faster-RCNN for Unrestricted Object Detection Open
Conventional object detection methods essentially suppose that the training and testing data are collected from a restricted target domain with expensive labeling cost. For alleviating the problem of domain dependency and cumbersome labeli…
View article: End-to-End Detection and Re-identification Integrated Net for Person Search
End-to-End Detection and Re-identification Integrated Net for Person Search Open
This paper proposes a pedestrian detection and re-identification (re-id) integration net (I-Net) in an end-to-end learning framework. The I-Net is used in real-world video surveillance scenarios, where the target person needs to be searche…
View article: Differential expression of circulating microRNAs in blood and haematoma samples from patients with intracerebral haemorrhage
Differential expression of circulating microRNAs in blood and haematoma samples from patients with intracerebral haemorrhage Open
Objective To measure the differential expression of microRNAs (miRNAs) in peripheral blood samples from patients with intracerebral haemorrhage (ICH) and to measure the levels of hsa-miR-21-5p in peripheral blood and haematoma samples from…
View article: Characterization of Carbohydrate Surface Markers on Mouse Embryonic Stem Cells
Characterization of Carbohydrate Surface Markers on Mouse Embryonic Stem Cells Open
Glycosylation of proteins and lipids on cell surface have been shown to be important in maintaining pluripotency and stem cell fate in embryonic stem cells.Lectins have been widely used to characterize carbohydrate modifications on cell su…