A5100374491- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Digital Imaging for Blood Diseases
- Anomaly Detection Techniques and Applications
- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- AI in cancer detection
- Advanced Neural Network Applications
- Carbohydrate Chemistry and Synthesis
- Advanced Vision and Imaging
- Rough Sets and Fuzzy Logic
- Asymmetric Synthesis and Catalysis
- Axial and Atropisomeric Chirality Synthesis
- Visual Attention and Saliency Detection
- Optical measurement and interference techniques
- Image Retrieval and Classification Techniques
- Neural Networks and Applications
- Risk and Safety Analysis
- Genetic Mapping and Diversity in Plants and Animals
- Traffic Prediction and Management Techniques
- Engineering Structural Analysis Methods
- Data Visualization and Analytics
- Image and Object Detection Techniques
- vaccines and immunoinformatics approaches
- Hydrology and Drought Analysis
Beijing University of Technology
2003-2024
University of Macau
2024
Yunnan University
2024
Sichuan University
2023-2024
Beijing University of Civil Engineering and Architecture
2024
Case Western Reserve University
2023
West China Hospital of Sichuan University
2023
Ministry of Education of the People's Republic of China
2023
Xihua University
2023
Group Sense (China)
2022
Weakly supervised crowd counting involves the regression of number individuals present in an image, using only total as label. However, this task is plagued by two primary challenges: large variation head size and uneven distribution density. To address these issues, we propose a novel Hypergraph Association Crowd Counting (HACC) framework. Our approach consists new multi-scale dilated pyramid module that can efficiently handle size. Further, hypergraph association to solve problem density...
Most existing weakly supervised crowd counting methods utilize Convolutional Neural Networks (CNN) or Transformer to estimate the total number of individuals in an image. However, both CNN-based (grid-to-count paradigm) and Transformer-based (sequence-to-count take images as inputs a regular form. This approach treats all pixels equally but cannot address uneven distribution problem within human crowds. challenge would lead decline performance model. Compared with grid sequence, graph...
Cell localization still faces two unresolved challenges: 1) the dramatic variations in cell morphology, coupled with heterogeneous intensity distribution of lightly stained cells; 2) existing location maps lack scale information, resulting insufficient supervision for point and inaccurate density maps. To address first challenges, we introduce a novel gradient-aware shape-adaptive Difference-Deformable Convolution (DDConv), which enhances model's robustness to color by leveraging gradient...
Antibodies play a pivotal role in immune defense and serve as key therapeutic agents. The process of affinity maturation, wherein antibodies evolve through somatic mutations to achieve heightened specificity target antigens, is crucial for effective response. Despite their significance, assessing antibody-antigen binding remains challenging due limitations conventional wet lab techniques. To address this, we introduce AntiFormer, graph-based large language model designed predict antibody...
Abstract Spatial transcriptomics reveals the spatial distribution of genes in complex tissues, providing crucial insights into biological processes, disease mechanisms, and drug development. The prediction gene expression based on cost-effective histology images is a promising yet challenging field research. Existing methods for from exhibit two major limitations. First, they ignore intricate relationship between cell morphological information expression. Second, these do not fully utilize...
Abstract In this work, six novel axially unfixed biaryl‐based water‐compatible bifunctional organocatalysts were designed and synthesized for the organocatalytic access to a variety of 3‐alkyl‐3‐hydroxy‐2‐oxindole derivatives via aldol reactions in water. Organocatalyzed by 5a , direct isatins with enolisable ketones underwent readily water, furnishing structurally diverse 3‐alkyl‐3‐hydroxy‐2‐oxindoles various stereoselectivities (up to>99% dr >99% ee ). Moreover, plausible transition...
Dependability of software, a major concern in many computer applications, can be improved through several means. But systematic approaches for its evaluation do not exist, which is the prerequisite dependability control and improvement. Software an urgent problem to solved. T here some subjectivity about weighting coefficient when applying fuzzy comprehensive model evaluate software dependability. A new with combinational weight based on r ough s et t heory was proposed this paper. In model,...
<p style='text-indent:20px;'>The calibration of a 3D laser rangefinder (LRF) and camera is key technique in the field computer vision intelligent robots. This paper proposes new method for LRF based on optimization solution. The achieved by freely moving checkerboard pattern front LRF. images point clouds various poses are collected respectively. By using images, intrinsic parameters obtained. Then, two kinds geometric constraints, line-to-plane constraints plane-to-plane constructed to...
With the continuous growth of global population, insufficient food production has become an urgent problem to be solved in most countries. At present, using artificial intelligence technology improve suitability between land and crop varieties increase yields a consensus among agricultural researchers. However, there are still many problems existing works, such as limited phenotypic data poor performance models. In this regard, we take maize example collect large amount environmental climate...