Query：
学者姓名：吴升
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Recently, a variety of LiDAR-based methods for the 3D detection of single-class objects, large objects, or in straightforward scenes have exhibited competitive performance. However, their detection performance in complex scenarios with multi - sized and multi - class objects is limited. We observe that the core problem leading to this phenomenon is the insufficient feature learning of small objects in point clouds, making it difficult to obtain more discriminative features. To address this challenge, we propose a 3D object detection framework based on point clouds that takes into account the detection of small objects, termed VoxT-GNN. The framework comprises two core components: a Voxel-Level Transformer (VoxelFormer) for local feature learning and a Graph Neural Network Feed-Forward Network (GnnFFN) for global feature learning. By embedding GnnFFN as an intermediate layer between the encoder and decoder of VoxelFormer, we achieve flexible scaling of the global receptive field while maximally preserving the original point cloud structure. This design enables effective adaptation to objects of varying sizes and categories, providing a viable solution for detection applications across diverse scenarios. Extensive experiments on KITTI and Waymo Open Dataset (WOD) demonstrate the strong competitiveness of our method, particularly showing significant improvements in small object detection. Notably, our approach achieves the second-highest mAP of 65.44% across three categories (car, pedestrian, and cyclist) on KITTI benchmark. The source code is available at https:// github.com/yujianxinnian/VoxT-GNN.
Keyword ：
3D object detection 3D object detection Graph Neural Network(GNN) Graph Neural Network(GNN) Point cloud Point cloud Transformer Transformer
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zheng, Qiangwen , Wu, Sheng , Wei, Jinghui . VoxT-GNN: A 3D object detection approach from point cloud based on voxel-level transformer and graph neural network [J]. | INFORMATION PROCESSING & MANAGEMENT , 2025 , 62 (4) . |
| MLA | Zheng, Qiangwen 等. "VoxT-GNN: A 3D object detection approach from point cloud based on voxel-level transformer and graph neural network" . | INFORMATION PROCESSING & MANAGEMENT 62 . 4 (2025) . |
| APA | Zheng, Qiangwen , Wu, Sheng , Wei, Jinghui . VoxT-GNN: A 3D object detection approach from point cloud based on voxel-level transformer and graph neural network . | INFORMATION PROCESSING & MANAGEMENT , 2025 , 62 (4) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
[目的]关键路段的准确识别对于全路网的交通管理具有重要意义.目前对于关键路段的识别已取得了丰富的成果,但在大规模路网(如城市级别)中,现有方法往往无法识别出交通流量较小的局部区域内的相对关键路段.[方法]为弥补上述不足,本研究提出了一种基于路段动静态嵌入的两阶段特征学习方法来识别大规模路网中的关键路段.具体步骤如下:首先,使用手机定位数据提取出行路线并构建交通语料库.接着,进行两阶段特征学习:① 提取各路段静态嵌入并聚类,得到初始聚类中心;② 提取各路段动态嵌入矩阵并进行注意力池化,再对池化后得到的特征向量进行可微分聚类,并计算相关损失函数.当损失值收敛后,得到各路段融合特征,对其进一步聚类得到的聚类中心即为关键路段.[结果]最后,使用福州市三环内区域的手机定位数据构建交通语料库,并以该区域内路网为例,进行关键路段的识别实验和对比分析.结果表明本文方法能有效识别出大规模路网中的关键路段,且能识别出局部区域中的相对关键路段.[结论]同时,本文方法相较于其他方法在各评价指标上的整体表现更佳,说明其识别的关键路段更为合理.
Keyword ：
交通语料库 交通语料库 关键路段识别 关键路段识别 可微分聚类 可微分聚类 手机定位数据 手机定位数据 注意力池化 注意力池化 福州市 福州市
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 吴炜毅 , 吴升 . 基于路段动静态嵌入两阶段特征学习的关键路段识别方法 [J]. | 地球信息科学学报 , 2025 , 27 (1) : 167-180 . |
| MLA | 吴炜毅 等. "基于路段动静态嵌入两阶段特征学习的关键路段识别方法" . | 地球信息科学学报 27 . 1 (2025) : 167-180 . |
| APA | 吴炜毅 , 吴升 . 基于路段动静态嵌入两阶段特征学习的关键路段识别方法 . | 地球信息科学学报 , 2025 , 27 (1) , 167-180 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
[目的]城市功能区是城市规划和人类活动共同作用、相互影响的结果,其准确识别对于优化配置公共资源和高效组织商业活动具有重要意义.目前,许多研究利用新兴的社会感知大数据进行城市功能区识别,但往往未能挖掘这些数据中蕴含的深层次特征,或者未能充分捕捉和利用不同特征之间的相互关系和关联性,导致识别精度较低.[方法]针对这些问题,本研究提出了一种融合区域嵌入表示的城市功能区识别框架.该方法基于手机定位数据和兴趣点数据(Point of Interest,POI),采用Node2vec算法提取工作日与周末6个时段的区域间空间交互特征,并利用GloVe模型提取区域的语义特征.随后,通过多头注意力机制进行特征融合,并结合部分人工标注的功能区进行分类识别,在福州市三环以内地区进行了实证研究.[结果]实验结果表明,本方法生成的区域表示特征具有较高区分度,能够有效识别6类功能区,总体精度(OA)为81％,Kappa系数为0.77.[结论]与DTW_KNN和Word2Vec方法相比,精度分别提高了 30％和20％,能够充分挖掘具有全局性质的空间交互特征和语义特征.此外,消融实验进一步表明,与单一数据源或简单融合方法相比,本方法在捕捉区域内部和区域间复杂关系的同时,对重要特征赋予更高的权重,使得模型的整体OA值相较于单源数据提高了约18％和6％,相较于简单融合方法提高了约13％,尤其在住宅区和混合区的识别方面表现出了显著优势.
Keyword ：
POI POI 出行有向图 出行有向图 区域嵌入表示 区域嵌入表示 城市功能区识别 城市功能区识别 多头注意力机制 多头注意力机制 手机定位数据 手机定位数据
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 韦烨娜 , 吴升 . 融合区域嵌入表示的城市功能区识别方法 [J]. | 地球信息科学学报 , 2025 , 27 (2) : 424-440 . |
| MLA | 韦烨娜 等. "融合区域嵌入表示的城市功能区识别方法" . | 地球信息科学学报 27 . 2 (2025) : 424-440 . |
| APA | 韦烨娜 , 吴升 . 融合区域嵌入表示的城市功能区识别方法 . | 地球信息科学学报 , 2025 , 27 (2) , 424-440 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
地球剖分网格作为传统地理坐标参考的有效补充,具有形状近似、空间无缝不重叠、尺度连续、全球统一的刚性定位等优势,与REST(Representational State Transfer)Web服务的结合可完成空间区域位置标识下的影像数据互操作.基于此,本研究基于地球剖分网格探索遥感影像数据REST资源化方法,定义了面向资源架构(Re-source-Oriented Architecture,ROA)的URI标识模型,从面向资源的角度设计互操作协议函数,采用地球剖分网格单元的地址编码代替传统地理坐标以刚性定位资源化影像.最后,以北斗网格作为参考网格,开发分析就绪(A-nalysis-Ready)资源化影像服务原型系统,并开展互操作案例研究,验证了影像数据资源刚性定位互操作模型用于影像资源共享互操作的可行性和有效性.
Keyword ：
互操作 互操作 刚性定位 刚性定位 协议函数 协议函数 地球剖分网格 地球剖分网格 资源化 资源化
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘甫 , 余劲松弟 , 吴升 et al. 资源化影像刚性定位互操作模型研究 [J]. | 测绘与空间地理信息 , 2025 , 48 (2) : 7-12 . |
| MLA | 刘甫 et al. "资源化影像刚性定位互操作模型研究" . | 测绘与空间地理信息 48 . 2 (2025) : 7-12 . |
| APA | 刘甫 , 余劲松弟 , 吴升 , 邵远征 , 郑智嘉 , 佟瑞菊 et al. 资源化影像刚性定位互操作模型研究 . | 测绘与空间地理信息 , 2025 , 48 (2) , 7-12 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Travel mode recognition is a key issue in urban planning and transportation research. While traditional travel surveys use manual data collection and have limited coverage, poor timeliness, and insufficient sample capacity, recent advancements in Global Positioning System (GPS) technology allow large-scale data collection and offer novel opportunities to enhance travel mode recognition. However, existing studies often neglect regular differences and changes in motion states across different travel modes and fail to fully integrate multi-scale spatio-temporal features, which limits the accurate classification of travel modes. To fill this gap, this study proposes a multi-scale spatio-temporal attribute fusion (MSAF) model for precise travel mode identification using solely GPS trajectories without altering their sampling rate. The MSAF model segments GPS trajectories into various temporal and spatial scales, extracting local motion states and spatial features at multiple scales. The spatio-temporal feature extraction module is constructed to extract local motion states and capture spatio-temporal dependencies. Additionally, the model incorporates a multi-scale feature fusion module, which effectively combines features of various scales through a series of fusion techniques to obtain a comprehensive representation, enabling automatic and accurate travel mode identification. Experiments on real-world datasets, including the GeoLife Trajectories dataset and the Sussex-Huawei Locomotion-Transportation (SHL) dataset, demonstrate the effectiveness of the MSAF model, achieving a competitive accuracy of 95.16% and 91.70%. This represents an improvement of 2.50% to 7.95% and 0.8% to 6.62% over several state-of-the-art baselines, effectively addressing sample imbalance challenges. Moreover, the experiments demonstrate the significant role of multiscale feature fusion in improving model performance.
Keyword ：
GPS trajectory GPS trajectory multi-scale attributes multi-scale attributes spatio-temporal convolution spatio-temporal convolution trajectory segmentation trajectory segmentation travel mode identification travel mode identification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fan, Kunkun , Li, Daichao , Jin, Xinlei et al. A multi-scale attributes fusion model for travel mode identification using GPS trajectories [J]. | GEO-SPATIAL INFORMATION SCIENCE , 2024 . |
| MLA | Fan, Kunkun et al. "A multi-scale attributes fusion model for travel mode identification using GPS trajectories" . | GEO-SPATIAL INFORMATION SCIENCE (2024) . |
| APA | Fan, Kunkun , Li, Daichao , Jin, Xinlei , Wu, Sheng . A multi-scale attributes fusion model for travel mode identification using GPS trajectories . | GEO-SPATIAL INFORMATION SCIENCE , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The construction of China's ecological civilization, known as 'Beautiful China', necessitates implementing precision watershed management through scientifically informed decision-making. This entails optimizing the spatial distribution of watershed best management practices (the so- called BMP scenario) and proposing multistage implementation plans, or roadmaps that align with practical requirements based on the overarching vision of comprehensive water shed management.The'water shed system simulation-scenariooptimization' method frame work (the simulation-and-optimization-based frame work for short) has demonstrated considerable potential in recent years. To address challenges arising from practical applications of this framework, this study systematically conducted the methodological research: (1) proposing a novel watershed process modeling framework that strikes a balance between modeling flexibility and high-performance computing to model and simulate watershed systems efficiently; (2) introducing slope position units as BMP configuration units and enabling dynamic boundary adjustments during scenario optimization, effectively incorporating practical knowledge of watershed management to ensure reasonable outcomes; (3) presenting an optimization method for determining the implementation orders of BMPs that considers stepwise investment constraints, thereby recommending feasible roadmaps that meet practical needs; and (4) designing a user-friendly participatory watershed planning system to facilitate collaborative decision-making among stakeholders. The effectiveness and practical value of these new methods, tools, and prototype systems are validated through application cases in a representative small watershed. This research contributes to advancing precision watershed management and provides valuable insights for sustainable ecological conservation. The methods proposed within the simulation-and-optimization-based framework in this study are universal methods, which means their application does not depend on the specific implementation, such as the watershed process model, the BMP types considered, the designed BMP configuration strategy, and so on. Further studies should be conducted not only to deepen related theory and method research but also to strengthen promotion and application, especially cooperating with local watershed management agents to provide valuable insights for their sustainable ecological conservation. © 2024 Science Press. All rights reserved.
Keyword ：
Computation theory Computation theory Decision making Decision making Decision support systems Decision support systems Ecology Ecology Investments Investments Soil conservation Soil conservation Water conservation Water conservation Water management Water management Watersheds Watersheds
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Qin, Chengzhi , Zhu, Liangjun , Shen, Shen et al. Methods for supporting decision-making of precision watershed management based on watershed system simulation and scenario optimization [J]. | Acta Geographica Sinica , 2024 , 79 (1) : 58-75 . |
| MLA | Qin, Chengzhi et al. "Methods for supporting decision-making of precision watershed management based on watershed system simulation and scenario optimization" . | Acta Geographica Sinica 79 . 1 (2024) : 58-75 . |
| APA | Qin, Chengzhi , Zhu, Liangjun , Shen, Shen , Wu, Tong , Xiao, Guirong , Wu, Sheng et al. Methods for supporting decision-making of precision watershed management based on watershed system simulation and scenario optimization . | Acta Geographica Sinica , 2024 , 79 (1) , 58-75 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Remote sensing scene classification (RSSC) is essential in Earth observation, with applications in land use, environmental status, urban development, and disaster risk assessment. However, redundant background interference, varying feature scales, and high interclass similarity in remote sensing images present significant challenges for RSSC. To address these challenges, this article proposes a novel hierarchical graph-enhanced transformer network (HGTNet) for RSSC. Initially, we introduce a dual attention (DA) module, which extracts key feature information from both the channel and spatial domains, effectively suppressing background noise. Subsequently, we meticulously design a three-stage hierarchical transformer extractor, incorporating a DA module at the bottleneck of each stage to facilitate information exchange between different stages, in conjunction with the Swin transformer block to capture multiscale global visual information. Moreover, we develop a fine-grained graph neural network extractor that constructs the spatial topological relationships of pixel-level scene images, thereby aiding in the discrimination of similar complex scene categories. Finally, the visual features and spatial structural features are fully integrated and input into the classifier by employing skip connections. HGTNet achieves classification accuracies of 98.47%, 95.75%, and 96.33% on the aerial image, NWPU-RESISC45, and OPTIMAL-31 datasets, respectively, demonstrating superior performance compared to other state-of-the-art models. Extensive experimental results indicate that our proposed method effectively learns critical multiscale visual features and distinguishes between similar complex scenes, thereby significantly enhancing the accuracy of RSSC.
Keyword ：
Attention mechanism Attention mechanism Attention mechanisms Attention mechanisms Data mining Data mining Earth Earth Feature extraction Feature extraction graph neural network (GNN) graph neural network (GNN) Graph neural networks Graph neural networks Remote sensing Remote sensing remote sensing scene classification (RSSC) remote sensing scene classification (RSSC) Scene classification Scene classification Sensors Sensors spatial structural feature spatial structural feature transformer transformer Transformers Transformers Visualization Visualization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Ziwei , Xu, Weiming , Yang, Shiyu et al. A Hierarchical Graph-Enhanced Transformer Network for Remote Sensing Scene Classification [J]. | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING , 2024 , 17 : 20315-20330 . |
| MLA | Li, Ziwei et al. "A Hierarchical Graph-Enhanced Transformer Network for Remote Sensing Scene Classification" . | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 17 (2024) : 20315-20330 . |
| APA | Li, Ziwei , Xu, Weiming , Yang, Shiyu , Wang, Juan , Su, Hua , Huang, Zhanchao et al. A Hierarchical Graph-Enhanced Transformer Network for Remote Sensing Scene Classification . | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING , 2024 , 17 , 20315-20330 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The accurate extraction of agricultural parcels from remote sensing images is crucial for advanced agricultural management and monitoring systems. Existing methods primarily emphasize regional accuracy over boundary quality, often resulting in fragmented outputs due to uniform crop types, diverse agricultural practices, and environmental variations. To address these issues, this paper proposes DSTBA-Net, an end-to-end encoder-decoder architecture. Initially, we introduce a Dual-Stream Feature Extraction (DSFE) mechanism within the encoder, which consists of Residual Blocks and Boundary Feature Guidance (BFG) to separately process image and boundary data. The extracted features are then fused in the Global Feature Fusion Module (GFFM), utilizing Transformer technology to further integrate global and detailed information. In the decoder, we employ Feature Compensation Recovery (FCR) to restore critical information lost during the encoding process. Additionally, the network is optimized using a boundary-aware weighted loss strategy. DSTBA-Net aims to achieve high precision in agricultural parcel segmentation and accurate boundary extraction. To evaluate the model's effectiveness, we conducted experiments on agricultural parcel extraction in Denmark (Europe) and Shandong (Asia). Both quantitative and qualitative analyses show that DSTBA-Net outperforms comparative methods, offering significant advantages in agricultural parcel extraction.
Keyword ：
agricultural parcel extraction agricultural parcel extraction boundary-aware weighted loss boundary-aware weighted loss dual-stream feature extraction (DSFE) dual-stream feature extraction (DSFE) feature compensation restoration (FCR) feature compensation restoration (FCR) global feature fusion module (GFFM) global feature fusion module (GFFM)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Weiming , Wang, Juan , Wang, Chengjun et al. Utilizing Dual-Stream Encoding and Transformer for Boundary-Aware Agricultural Parcel Extraction in Remote Sensing Images [J]. | REMOTE SENSING , 2024 , 16 (14) . |
| MLA | Xu, Weiming et al. "Utilizing Dual-Stream Encoding and Transformer for Boundary-Aware Agricultural Parcel Extraction in Remote Sensing Images" . | REMOTE SENSING 16 . 14 (2024) . |
| APA | Xu, Weiming , Wang, Juan , Wang, Chengjun , Li, Ziwei , Zhang, Jianchang , Su, Hua et al. Utilizing Dual-Stream Encoding and Transformer for Boundary-Aware Agricultural Parcel Extraction in Remote Sensing Images . | REMOTE SENSING , 2024 , 16 (14) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Predicting urban crowd flow spatial distributions plays a critical role in optimizing urban public safety and traffic congestion management. The spatial dependency between regions and the temporal dynamics of the local crowd flow are two important features in urban crowd flow prediction. However, few studies considered geographic characteristic in terms of spatial features. To fill this gap, we propose an urban crowd flow prediction model integrating geographic characteristics (FPM-geo). First, three geographic characteristics, proximity, functional similarity, and road network connectivity, are fused by a residual multigraph convolution network to model the spatial dependency relationship. Then, a long short-term memory network is applied as a framework to integrate both the temporal dynamic patterns of local crowd flow and the spatial dependency between regions. A 4-day mobile phone dataset validates the effectiveness of the proposed method by comparing it with several widely used approaches. The result shows that the root mean square error decreases by 15.37% compared with those of the typical models with the prediction interval at the 15-min level. The prediction error increases with the crowd flow size in a local area. Moreover, the error reaches the top of the morning peak and the evening peak and slopes down to the bottom at night.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Yu , Wu, Sheng , Zhao, Zhiyuan et al. An urban crowd flow model integrating geographic characteristics [J]. | SCIENTIFIC REPORTS , 2023 , 13 (1) . |
| MLA | Zhang, Yu et al. "An urban crowd flow model integrating geographic characteristics" . | SCIENTIFIC REPORTS 13 . 1 (2023) . |
| APA | Zhang, Yu , Wu, Sheng , Zhao, Zhiyuan , Yang, Xiping , Fang, Zhixiang . An urban crowd flow model integrating geographic characteristics . | SCIENTIFIC REPORTS , 2023 , 13 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This paper proposes a novel model for named entity recognition of Chinese crop diseases and pests. The model is intended to solve the problems of uneven entity distribution, incomplete recognition of complex terms, and unclear entity boundaries. First, a robustly optimized BERT pre-training approach-whole word masking (RoBERTa-wwm) model is used to extract diseases and pests' text semantics, acquiring dynamic word vectors to solve the problem of incomplete word recognition. Adversarial training is then introduced to address unclear boundaries of diseases and pest entities and to improve the generalization ability of models in an effective manner. The context features are obtained by the bi-directional gated recurrent unit (BiGRU) neural network. Finally, the optimal tag sequence is obtained by conditional random fields (CRF) decoding. A focal loss function is introduced to optimize conditional random fields (CRF) and thus solve the problem of unbalanced label classification in the sequence. The experimental results show that the model's precision, recall, and F1 values on the crop diseases and pests corpus reached 89.23%, 90.90%, and 90.04%, respectively, demonstrating effectiveness at improving the accuracy of named entity recognition for Chinese crop diseases and pests. The named entity recognition model proposed in this study can provide a high-quality technical basis for downstream tasks such as crop diseases and pests knowledge graphs and question-answering systems.
Keyword ：
adversarial training adversarial training crop diseases and pests crop diseases and pests deep learning deep learning named entity recognition named entity recognition pre-training language model pre-training language model
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liang, Jianqin , Li, Daichao , Lin, Yiting et al. Named Entity Recognition of Chinese Crop Diseases and Pests Based on RoBERTa-wwm with Adversarial Training [J]. | AGRONOMY-BASEL , 2023 , 13 (3) . |
| MLA | Liang, Jianqin et al. "Named Entity Recognition of Chinese Crop Diseases and Pests Based on RoBERTa-wwm with Adversarial Training" . | AGRONOMY-BASEL 13 . 3 (2023) . |
| APA | Liang, Jianqin , Li, Daichao , Lin, Yiting , Wu, Sheng , Huang, Zongcai . Named Entity Recognition of Chinese Crop Diseases and Pests Based on RoBERTa-wwm with Adversarial Training . | AGRONOMY-BASEL , 2023 , 13 (3) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
