A5085287554- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Robotics and Sensor-Based Localization
- Soybean genetics and cultivation
- Plant Molecular Biology Research
- Text and Document Classification Technologies
- Educational Methods and Teacher Development
- Multimodal Machine Learning Applications
- Nematode management and characterization studies
- Video Surveillance and Tracking Methods
- Legume Nitrogen Fixing Symbiosis
- Remote-Sensing Image Classification
- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Medical Image Segmentation Techniques
- Light effects on plants
- Infrared Target Detection Methodologies
- Educational Innovations and Challenges
Jilin Academy of Agricultural Sciences
2019-2025
University of Chinese Academy of Sciences
2019-2024
Chongqing University of Posts and Telecommunications
2023
Guangzhou University
2021
Northeast Institute of Geography and Agroecology
2019
Chinese Academy of Sciences
2019
The development of detection methods for oriented object remains a challenging task. A considerable obstacle is the wide variation in shape (e.g., aspect ratio) objects. Sample selection general has been widely studied as it plays crucial role performance method and achieved great progress. However, existing sample strategies still overlook some issues: (1) most them ignore information; (2) they do not make potential distinction between selected positive samples; (3) can only be applied to...
Typical representations for arbitrary-oriented object detection tasks include the oriented bounding box (OBB), quadrilateral (QBB), and point set (PointSet). Each representation encounters problems that correspond to its characteristics, such as boundary discontinuity, square-like problems, ambiguity, isolated points, which lead inaccurate detection. Although many effective strategies have been proposed various representations, there is still no unified solution. Current methods based on...
The pseudo response regulator (PRR) gene is an important component of the core oscillator involved in plant circadian rhythms and plays role regulating growth development stress responses. In this study, we investigated function GmPRR7b by overexpression editing approaches. It was found that a delaying flowering. While overexpressing plants showed significantly delayed flowering compared to untransformed WT, edited flowered earlier than control WT. On basis previous research results...
Flowering time and maturity are important agronomic traits for soybean cultivars to adapt different latitudes achieve maximal yield. Genetic studies on genes quantitative trait loci (QTL) that control flowering extensive. In particular, the molecular bases of E1-E4, E6, E9, E10, J have been deciphered. For a better understanding regulation gene networks, we need understand if more factors carrying biological functions also involved in soybeans. We developed population derived from cross...
Typical representations for arbitrary-oriented object detection tasks include oriented bounding box (OBB), quadrilateral (QBB), and point set (PointSet). Each representation encounters problems that correspond to its characteristics, such as the boundary discontinuity, square-like problem, ambiguity, isolated points, which lead inaccurate detection. Although many effective strategies have been proposed various representations, there is still no unified solution. Current methods based on...
Object detection for remote sensing images (RSI) has made significant progress in recent years. However, existing supervised methods typically require a large amount of labeled data, whose acquisition, and particularly that RSI, can be quite expensive. For natural images, many semi-supervised have been proposed to tackle the lack while few studies focused on object RSI. To address this problem, paper proposes RS-PCL, which is method applying Pseudo labeling Consistency Learning The RS-PCL...
With the rapid development of Internet, netizens will express their personal opinions on various social platforms[. This experiment uses Weibo comments as datasets and learning algorithms to perform sentiment analysis text content. In past, most pre-trained models were based BERT model, which considered contextual semantics but lacked relevant knowledge information, resulting in unsatisfactory training results. order provide information language representation models, a graph is introduced...