Query：
学者姓名：林志玮
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
Brain tumor segmentation is crucial in medical image processing but struggles to access and integrate information across dimensions, such as global-local, multi-scale, long-range dependencies information, and the receptive field, leading to suboptimal accuracy and robustness. This study proposes a novel attention network, the Cross-Dimensional Synergistic Network (CS-Net), for brain tumor segmentation, which incorporates three kinds of symmetrical relationships - also called cross-dimensional information, including global-local, vertical-horizontal axis, and large-small (multi-scale) relationships. The symmetrical relationships are translated into three attention mechanisms: Global-local Region Attention (GRA), Axis-aligned Translation Attention (ATA), and Multi-scale Fusion Attention (MFA). The GRA module enhances spatial perception by dividing the input feature map into non-overlapping sub-regions and computing attention weights between each sub-region (Local) and global features to capture finer spatial dependencies. The ATA module calculates the cross-directional attention between the entire original and shifted features, where the shifted features include horizontal and vertical shifts to learn the long-range dependencies and extend the receptive field in different directions. The MFA module executes self-attention interactions between feature maps at different scales to effectively integrate adjacent scale information. Experiments on the Brain Tumor Segmentation Challenge (BraTS) from the Medical Image Computing and Computer-Assisted Intervention (MICCAI) and the Medical Segmentation Decathlon (MSD) demonstrate significant performance improvements. Our model achieves 86.23%, 89.99%, and 1.2485 in the Dice coefficient, precision, and 95%Hausdorff Distance on the MICCAI BraTS dataset and achieves 81.57%, 86.70%, and 1.5547 in the Dice coefficient, precision, and 95%Hausdorff Distance on the MSD BraTS dataset, suppressing the state-of-the-art approaches.
Keyword ：
Artificial intelligence in healthcare Artificial intelligence in healthcare Axis-aligned feature translation Axis-aligned feature translation Brain tumor segmentation Brain tumor segmentation Global-local attention strategy Global-local attention strategy Medical image processing Medical image processing Multi-scale feature fusion Multi-scale feature fusion Symmetrical feature relationships Symmetrical feature relationships
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Chih-Wei , Lin, Ye . A cross-dimensional synergistic network for brain tumor segmentation [J]. | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2025 , 160 . |
| MLA | Lin, Chih-Wei 等. "A cross-dimensional synergistic network for brain tumor segmentation" . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 160 (2025) . |
| APA | Lin, Chih-Wei , Lin, Ye . A cross-dimensional synergistic network for brain tumor segmentation . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2025 , 160 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对传统蓝碳核算忽略部分生态系统的问题，研究综合考虑渔业、凋落物分解等生态系统价值。将蓝碳划分为地理、生物和生产蓝碳，并引入生境质量作为权重，优化评估方法。利用2007—2021年泉州湾六期遥感影像，结合ArcGIS提取湿地数据，基于InVEST（生态系统服务和权衡的综合评估）模型计算蓝碳总价值，并采用多元线性回归和灰色预测模型分析碳储量变化趋势。结果表明，泉州湾生境质量整体稳定，蓝碳总价值先降后升，揭示了其碳汇动态变化机制，为湿地生态价值评估提供科学参考。
Keyword ：
InVEST(生态系统服务和权衡的综合评估)模型 InVEST(生态系统服务和权衡的综合评估)模型 泉州湾 泉州湾 碳储量 碳储量 碳汇 碳汇 蓝碳 蓝碳
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张馨雯 , 林志玮 . 结合生境质量和多生态系统的湿地蓝碳评估与预测 [J]. | 科技和产业 , 2025 , 25 (19) : 76-84 . |
| MLA | 张馨雯 等. "结合生境质量和多生态系统的湿地蓝碳评估与预测" . | 科技和产业 25 . 19 (2025) : 76-84 . |
| APA | 张馨雯 , 林志玮 . 结合生境质量和多生态系统的湿地蓝碳评估与预测 . | 科技和产业 , 2025 , 25 (19) , 76-84 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
基于2013 年、2017 年、2021 年三期土地利用数据,探讨福建省九龙江口、漳江口和泉州湾三个重点湿地及其周边地区的生境质量时空演变特征.利用InVEST模型评估生境质量,并结合空间分析方法探究生境质量的空间分布特征及驱动因素.结果表明,①九龙江口和泉州湾以建设用地为主,漳江口以林地为主,土地利用格局或直接影响生境质量;②漳江口生境质量最高,九龙江口次之,泉州湾最低;③生境质量低值区(冷点区)主要集中在人口密集的平原地区,受城镇化扩张和产业活动影响显著.根据研究结果,该文提出优化湿地周边土地利用结构,提升生物多样性保护水平等建议,以提升区域生态安全水平.
Keyword ：
时空演变 时空演变 湿地 湿地 生境质量 生境质量 福建省 福建省
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 胡卉 , 蔡伟鑫 , 林志玮 . 福建重点河口湿地生境质量时空分异特征及其驱动机制 [J]. | 海峡科学 , 2025 , (1) : 84-91 . |
| MLA | 胡卉 等. "福建重点河口湿地生境质量时空分异特征及其驱动机制" . | 海峡科学 1 (2025) : 84-91 . |
| APA | 胡卉 , 蔡伟鑫 , 林志玮 . 福建重点河口湿地生境质量时空分异特征及其驱动机制 . | 海峡科学 , 2025 , (1) , 84-91 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
在信息技术飞速发展的背景下，教育领域正经历着深刻的变革。大语言模型作为人工智能的重要成果，为课堂教学提供了新的可能性。探讨了大语言模型在课堂教学中的应用，揭示了这一技术带来的机遇与挑战。一方面，对提高教学效率、促进学生自主学习、个性化学习路径设计以及多学科交叉学习等具有积极作用；另一方面，可能导致过度依赖、师生交流弱化以及模型可解释性和内容准确性不足等问题。提出了相应的应对措施，旨在实现教育质量的提升并推动教育领域的创新和发展。
Keyword ：
人工智能 人工智能 大语言模型 大语言模型 教育领域 教育领域
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 林志玮 , 周尚泰 , 周金兰 . 大语言模型与课堂教学：理论与实践探究 [J]. | 教育教学论坛 , 2025 , 4 (11) : 149-152 . |
| MLA | 林志玮 等. "大语言模型与课堂教学：理论与实践探究" . | 教育教学论坛 4 . 11 (2025) : 149-152 . |
| APA | 林志玮 , 周尚泰 , 周金兰 . 大语言模型与课堂教学：理论与实践探究 . | 教育教学论坛 , 2025 , 4 (11) , 149-152 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
基于2013年、2017年、2021年三期土地利用数据，探讨福建省九龙江口、漳江口和泉州湾三个重点湿地及其周边地区的生境质量时空演变特征。利用InVEST模型评估生境质量，并结合空间分析方法探究生境质量的空间分布特征及驱动因素。结果表明，(1)九龙江口和泉州湾以建设用地为主，漳江口以林地为主，土地利用格局或直接影响生境质量；(2)漳江口生境质量最高，九龙江口次之，泉州湾最低；(3)生境质量低值区(冷点区)主要集中在人口密集的平原地区，受城镇化扩张和产业活动影响显著。根据研究结果，该文提出优化湿地周边土地利用结构，提升生物多样性保护水平等建议，以提升区域生态安全水平。
Keyword ：
时空演变 时空演变 湿地 湿地 生境质量 生境质量 福建省 福建省
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 胡卉 , 蔡伟鑫 , 林志玮 . 福建重点河口湿地生境质量时空分异特征及其驱动机制——以九龙江口、漳江口和泉州湾为例 [J]. | 海峡科学 , 2025 , 8 (01) : 84-91 . |
| MLA | 胡卉 等. "福建重点河口湿地生境质量时空分异特征及其驱动机制——以九龙江口、漳江口和泉州湾为例" . | 海峡科学 8 . 01 (2025) : 84-91 . |
| APA | 胡卉 , 蔡伟鑫 , 林志玮 . 福建重点河口湿地生境质量时空分异特征及其驱动机制——以九龙江口、漳江口和泉州湾为例 . | 海峡科学 , 2025 , 8 (01) , 84-91 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Brain tumor segmentation is an essential issue in medical image segmentation. However, it is still challenging to consider the relationship between modules and efficiently fuse the features between adjacent scales. In this paper, we propose a novel cross-attention network for brain tumor segmentation, namely multi-scales and multi-modules cross-attention UNet (MM-UNet), which contains two mechanisms, module and scale cross- attentions. The module cross-attention (MCA) MCA ) strategy connects and exchanges global information between adjacent modules. The scale cross-attention (SCA) SCA ) strategy has two policies, the scale-related non-local relationship module ( SCA SNR ) and the scale-related channel-based relationship module ( SCA SCR ), that fuses the information between adjacent scales to mix the multi-scale information. Experiments on well-known tumor datasets, BraTS 2020, which has 369 cases, and has been classified into training, validation, and testing sets with 17,576, 4395, and 5735 images, to evaluate the performance by segmenting three regions, the whole tumor area (WT), core tumor area (CT) and enhancing tumor area (ET). Moreover, we consider three numerical metrics, dice, precision, and Hausdorff metrics, and various visualization results to objectively evaluate and intuitively display the experimental results. The proposed model surpasses state-of-the-art methods and achieves 0.8519, 0.8889, and 1.2647 with a base version network in dice, precision, sensitivity, and Hausdorff metrics, respectively. Moreover, we demonstrate the visualization with segmentation results and heatmaps in various scenarios to present the robustness of the proposed network in each region.
Keyword ：
Brain tumor segmentation Brain tumor segmentation Cross-attention Cross-attention Multi-modules Multi-modules Multi-scale fusion Multi-scale fusion Non-local attention Non-local attention
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Chih-Wei , Chen, Zhongsheng . MM-UNet: A novel cross-attention mechanism between modules and scales for brain tumor segmentation [J]. | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2024 , 133 . |
| MLA | Lin, Chih-Wei 等. "MM-UNet: A novel cross-attention mechanism between modules and scales for brain tumor segmentation" . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 133 (2024) . |
| APA | Lin, Chih-Wei , Chen, Zhongsheng . MM-UNet: A novel cross-attention mechanism between modules and scales for brain tumor segmentation . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2024 , 133 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The Transformer-based instance segmentation framework retains crucial features using learnable queries, which consist of two main components: positional queries and content queries. These queries are then employed to determine the category of each mask. The current challenge remains in how to initialize these queries to achieve higher performance. The paper introduces Spec-Mask2former, a query generation model tailored for Transformer-based instance segmentation. Observations reveal the utility of frequency information as global prior knowledge, aiding queries in extracting key image features effectively. A Multi-scale Frequency Mean Query Generator (MFMQG) is proposed, leveraging Discrete Wavelet Transform (DWT) to extract frequency information and blend it with content queries. Additionally, to address positional query lag, a Position Enhance Block (PEB) is introduced. Experimental results demonstrate Spec-Mask2former's outstanding performance on a tree species instance segmentation dataset, achieving 30.7 AP and 41 mAP50 © 2024 IEEE.
Keyword ：
Discrete wavelet transforms Discrete wavelet transforms Image reconstruction Image reconstruction Image segmentation Image segmentation Query processing Query processing Structured Query Language Structured Query Language Trees (mathematics) Trees (mathematics)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhu, Lirong , Lin, Ye , Lin, Chih-Wei . Transformer-based Instance Segmentation with Multi-Scale Spectrum-Averaging Blend Queries [J]. | 2024 9th International Symposium on Computer and Information Processing Technology, ISCIPT 2024 , 2024 : 515-518 . |
| MLA | Zhu, Lirong 等. "Transformer-based Instance Segmentation with Multi-Scale Spectrum-Averaging Blend Queries" . | 2024 9th International Symposium on Computer and Information Processing Technology, ISCIPT 2024 (2024) : 515-518 . |
| APA | Zhu, Lirong , Lin, Ye , Lin, Chih-Wei . Transformer-based Instance Segmentation with Multi-Scale Spectrum-Averaging Blend Queries . | 2024 9th International Symposium on Computer and Information Processing Technology, ISCIPT 2024 , 2024 , 515-518 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, a popular query-based end-to-end framework has been used for instance segmentation. However, queries update based on individual layers or scales of feature maps at each stage of Transformer decoding, which makes queries unable to gather sufficient multi-scale feature information. Therefore, querying these features may result in inconsistent information due to disparities among feature maps and leading to erroneous updates. This study proposes a new network called GateInst, which employs a dual-path auto-select mechanism based on gate structures to overcome these issues. Firstly, we design a block-wise multi-scale feature fusion module that combines features of different scales while maintaining low computational cost. Secondly, we introduce the gated-enhanced queries Transformer decoder that utilizes a gating mechanism to filter and merge the queries generated at different stages to compensate for the inaccuracies in updating queries. GateInst addresses the issue of insufficient feature information and compensates for the problem of cumulative errors in queries. Experiments have shown that GateInst achieves significant gains of 8.4 AP, 5.5 AP50\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$AP_{50}$$\end{document} over Mask2Former on the self-collected Tree Species Instance Dataset and performs well compared to non-Mask2Former-like and Mask2Former-like networks on self-collected and public COCO datasets, with only a tiny amount of additional computational cost and fast convergence. Code and models are available at https://github.com/FAFU-IMLab/GateInst.
Keyword ：
Gated-enhanced query transformer Gated-enhanced query transformer Instance segmentation Instance segmentation Masked-attention transformer Masked-attention transformer Multi-scale feature enhancement Multi-scale feature enhancement Weighted query fusion Weighted query fusion
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Chih-Wei , Lin, Ye , Zhou, Shangtai et al. Gateinst: instance segmentation with multi-scale gated-enhanced queries in transformer decoder [J]. | MULTIMEDIA SYSTEMS , 2024 , 30 (5) . |
| MLA | Lin, Chih-Wei et al. "Gateinst: instance segmentation with multi-scale gated-enhanced queries in transformer decoder" . | MULTIMEDIA SYSTEMS 30 . 5 (2024) . |
| APA | Lin, Chih-Wei , Lin, Ye , Zhou, Shangtai , Zhu, Lirong . Gateinst: instance segmentation with multi-scale gated-enhanced queries in transformer decoder . | MULTIMEDIA SYSTEMS , 2024 , 30 (5) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本实用新型公开了一种移动式冷链物流储存装置，包括：冷链车厢、温度监控设备、移动装载设备和货物位置调整设备；温度监控设备包括安装在冷链车厢的内侧壁上的摄像机构、光源和温度传感器；移动装载设备包括货板、安装于货板底部的滚轮和平行安装于冷链车厢内底部的滑轨；货物位置调整设备包括位于货板上方和下方的上边框和下边框、沿着上边框和下边框四周设置的轨道、沿着轨道上设置的驱动机构、货篮和滑动机构，货篮安装于货板的正面，滑动机构滑动安装在轨道上，滑动机构的一端与货篮固定，另一端与驱动机构固定连接；通过驱动机构转动来带动滑动机构沿着轨道移动，带动货篮移动。本实用新型监测能力好、装卸效率高、保证货物安全和环境洁净。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 林志玮 , 林烨 . 一种移动式冷链物流储存装置 : CN202323592708.4[P]. | 2023-12-27 . |
| MLA | 林志玮 et al. "一种移动式冷链物流储存装置" : CN202323592708.4. | 2023-12-27 . |
| APA | 林志玮 , 林烨 . 一种移动式冷链物流储存装置 : CN202323592708.4. | 2023-12-27 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In this study, we proposed a network structure based on the shifted attention mechanism, namely U-Shiftformer, to overcome the limitation of existing convolution neural networks (CNNs) in brain tumor segmentation that lacks multimodal information interaction. The U-Shiftformer takes the U-shape encoder-decoder structure as the backbone and embeds the proposed Shiftformer module to exchange the information between modalities in the downsampling process. The Shiftformer module contains one standard attention, and three proposed shifted attention modules, in which the shifted attention module considers the information exchange by constructing the relationship between adjacent modalities. In the experiments, we compare the proposed U-Shiftformer with SOTA networks in the dice, precision, and Hausdorff metrics. Its average accuracies of these metrics surpass all the comparison networks and achieve 0.8424, 0.8675, 0.9244, and 1.2961 in dice, precision, sensitivity, and Hausdorff metrics, respectively. © 2023 IEEE.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Chih-Wei , Chen, Zhongsheng . U-Shiftformer: Brain Tumor Segmentation Using A Shifted Attention Mechanism [J]. | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings , 2023 , 2023-June . |
| MLA | Lin, Chih-Wei et al. "U-Shiftformer: Brain Tumor Segmentation Using A Shifted Attention Mechanism" . | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2023-June (2023) . |
| APA | Lin, Chih-Wei , Chen, Zhongsheng . U-Shiftformer: Brain Tumor Segmentation Using A Shifted Attention Mechanism . | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings , 2023 , 2023-June . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
