GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    Cross-Attention-Guided Feature Alignment Network for Road Crack Detection
    MDPI AG ; 2023
    In:  ISPRS International Journal of Geo-Information Vol. 12, No. 9 ( 2023-09-19), p. 382-
    Details
    In: ISPRS International Journal of Geo-Information, MDPI AG, Vol. 12, No. 9 ( 2023-09-19), p. 382-
    Abstract: Road crack detection is one of the important issues in the field of traffic safety and urban planning. Currently, road damage varies in type and scale, and often has different sizes and depths, making the detection task more challenging. To address this problem, we propose a Cross-Attention-guided Feature Alignment Network (CAFANet) for extracting and integrating multi-scale features of road damage. Firstly, we use a dual-branch visual encoder model with the same structure but different patch sizes (one large patch and one small patch) to extract multi-level damage features. We utilize a Cross-Layer Interaction (CLI) module to establish interaction between the corresponding layers of the two branches, combining their unique feature extraction capability and contextual understanding. Secondly, we employ a Feature Alignment Block (FAB) to align the features from different levels or branches in terms of semantics and spatial aspects, which significantly improves the CAFANet’s perception of the damage regions, reduces background interference, and achieves more precise detection and segmentation of damage. Finally, we adopt multi-layer convolutional segmentation heads to obtain high-resolution feature maps. To validate the effectiveness of our approach, we conduct experiments on the public CRACK500 dataset and compare it with other mainstream methods. Experimental results demonstrate that CAFANet achieves excellent performance in road crack detection tasks, which exhibits significant improvements in terms of F1 score and accuracy, with an F1 score of 73.22% and an accuracy of 96.78%.
    Type of Medium: Online Resource
    ISSN: 2220-9964
    URL: Article
    DOI: 10.3390/ijgi12090382
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2655790-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    Inhibiting Osteolytic Breast Cancer Bone Metastasis by Bone‐Targeted Nanoagent via Remodeling the Bone Tumor Microenvironment Combined with NIR‐II Photothermal Therapy
    Wiley ; 2023
    In:  Small Vol. 19, No. 38 ( 2023-09)
    Details
    In: Small, Wiley, Vol. 19, No. 38 ( 2023-09)
    Abstract: Bone is one of the prone metastatic sites of patients with advanced breast cancer. The “vicious cycle” between osteoclasts and breast cancer cells plays an essential role in osteolytic bone metastasis from breast cancer. In order to inhibit bone metastasis from breast cancer, NIR‐II photoresponsive bone‐targeting nanosystems (CuP@PPy‐ZOL NPs) are designed and synthesized. CuP@PPy‐ZOL NPs can trigger the photothermal‐enhanced Fenton response and photodynamic effect to enhance the photothermal treatment (PTT) effect and thus achieve synergistic anti‐tumor effect. Meanwhile, they exhibit a photothermal enhanced ability to inhibit osteoclast differentiation and promote osteoblast differentiation, which reshaped the bone microenvironment. CuP@PPy‐ZOL NPs effectively inhibited the proliferation of tumor cells and bone resorption in the in vitro 3D bone metastases model of breast cancer. In a mouse model of breast cancer bone metastasis, CuP@PPy‐ZOL NPs combined with PTT with NIR‐II significantly inhibited the tumor growth of breast cancer bone metastases and osteolysis while promoting bone repair to achieve the reversal of osteolytic breast cancer bone metastases. Furthermore, the potential biological mechanisms of synergistic treatment are identified by conditioned culture experiments and mRNA transcriptome analysis. The design of this nanosystem provides a promising strategy for treating osteolytic bone metastases.
    Type of Medium: Online Resource
    ISSN: 1613-6810 , 1613-6829
    URL: Issue
    URL: Article
    DOI: 10.1002/smll.v19.38
    DOI: 10.1002/smll.202301003
    Language: English
    Publisher: Wiley
    Publication Date: 2023
    detail.hit.zdb_id: 2168935-0
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Progressive Context-Aware Aggregation Network Combining Multi-Scale and Multi-Level Dense Reconstruction for Building Change Detection
    MDPI AG ; 2023
    In:  Remote Sensing Vol. 15, No. 8 ( 2023-04-07), p. 1958-
    Details
    In: Remote Sensing, MDPI AG, Vol. 15, No. 8 ( 2023-04-07), p. 1958-
    Abstract: Building change detection (BCD) using high-resolution remote sensing images aims to identify change areas during different time periods, which is a significant research focus in urbanization. Deep learning methods are capable of yielding impressive BCD results by correctly extracting change features. However, due to the heterogeneous appearance and large individual differences of buildings, mainstream methods cannot further extract and reconstruct hierarchical and rich feature information. To overcome this problem, we propose a progressive context-aware aggregation network combining multi-scale and multi-level dense reconstruction to identify detailed texture-rich building change information. We design the progressive context-aware aggregation module with a Siamese structure to capture both local and global features. Specifically, we first use deep convolution to obtain superficial local change information of buildings, and then utilize self-attention to further extract global features with high-level semantics based on the local features progressively, which ensures capability of the context awareness of our feature representations. Furthermore, our multi-scale and multi-level dense reconstruction module groups extracted feature information according to pre- and post-temporal sequences. By using multi-level dense reconstruction, the following groups are able to directly learn feature information from the previous groups, enhancing the network’s robustness to pseudo changes. The proposed method outperforms eight state-of-the-art methods on four common BCD datasets, including LEVIR-CD, SYSU-CD, WHU-CD, and S2Looking-CD, both in terms of visual comparison and objective evaluation metrics.
    Type of Medium: Online Resource
    ISSN: 2072-4292
    URL: Article
    DOI: 10.3390/rs15081958
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2513863-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    Recent advances in the metal/organic hybrid nanomaterials for cancer theranostics
    Elsevier BV ; 2024
    In:  Coordination Chemistry Reviews Vol. 504 ( 2024-04), p. 215654-
    Details
    In: Coordination Chemistry Reviews, Elsevier BV, Vol. 504 ( 2024-04), p. 215654-
    Type of Medium: Online Resource
    ISSN: 0010-8545
    URL: Article
    DOI: 10.1016/j.ccr.2023.215654
    RVK:
    VA 3900
    Language: English
    Publisher: Elsevier BV
    Publication Date: 2024
    detail.hit.zdb_id: 1499984-5
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 5
    Online Resource
    Online Resource
    MDFD: A multi-source data fusion detection framework for Sybil attack detection in VANETs
    Elsevier BV ; 2023
    In:  Computer Networks Vol. 224 ( 2023-04), p. 109608-
    Details
    In: Computer Networks, Elsevier BV, Vol. 224 ( 2023-04), p. 109608-
    Type of Medium: Online Resource
    ISSN: 1389-1286
    URL: Article
    DOI: 10.1016/j.comnet.2023.109608
    Language: English
    Publisher: Elsevier BV
    Publication Date: 2023
    detail.hit.zdb_id: 1499744-7
    detail.hit.zdb_id: 224452-4
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 6
    Online Resource
    Online Resource
    Scene Text Detection Based On Fusion Network
    World Scientific Pub Co Pte Ltd ; 2021
    In:  International Journal of Pattern Recognition and Artificial Intelligence Vol. 35, No. 10 ( 2021-08), p. 2153005-
    Details
    In: International Journal of Pattern Recognition and Artificial Intelligence, World Scientific Pub Co Pte Ltd, Vol. 35, No. 10 ( 2021-08), p. 2153005-
    Abstract: Due to the robustness resulted from scale transformation and unbalanced distribution of training samples in scene text detection task, a new fusion framework TSFnet is proposed in this paper. This framework is composed of Detection Stream, Judge Stream and Fusion Stream. In the Detection Stream, loss balance factor (LBF) is raised to improve the region proposal network (RPN). To predict the global text segmentation map, the algorithm combines regression strategy and case segmentation method. In the Judge Stream, a classification of the samples is proposed based on the Judge Map and the corresponding tags to calculate the overlap rate. As a support of Detection Stream, feature pyramid network is utilized in the algorithm to extract Judge Map and calculate LBF. In the Fusion Stream, a new fusion algorithm is raised. By fusing the output of the two streams, we can position the text area in the natural scene accurately. Finally, the algorithm is experimented on the standard data sets ICDAR 2015 and ICDAR2017-MLT. The test results show that the [Formula: see text] values are 87.8% and 67.5 7%, respectively, superior to the state-of-the art models. This proves that the algorithm can solve the robustness issues under the unbalance between scale transformation and training data.
    Type of Medium: Online Resource
    ISSN: 0218-0014 , 1793-6381
    URL: Article
    DOI: 10.1142/S0218001421530050
    Language: English
    Publisher: World Scientific Pub Co Pte Ltd
    Publication Date: 2021
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 7
    Online Resource
    Online Resource
    Surface modification effect on particle size and stability of Yellow Pigment
    IOP Publishing ; 2020
    In:  IOP Conference Series: Earth and Environmental Science Vol. 558, No. 4 ( 2020-08-01), p. 042020-
    Details
    In: IOP Conference Series: Earth and Environmental Science, IOP Publishing, Vol. 558, No. 4 ( 2020-08-01), p. 042020-
    Abstract: NaOH solutions with different concentration were used to pre-treat YPs (yellow pigments) in order to investigate surface modification effects on stability and particle size of pre-treated yellow pigments (PYPs). The coupling agent KH550 was used to treat PYP10 (yellow pigment pre-treated with 10% NaOH) to be compared for PYPs. The YPs (yellow pigments) were pre-treated by NaOH solutions and rinsed with C2H5OH, then the filtrates and residues were analysed by spectrophotometer and laser granularity analyser; The filtrates are stratified after the PYPs rinsed with C2H5OH. Microscope and Natural settling experiment were used to analyse the particle size and stability in residues. The results show that the particle size of wet PYPs decreased with the concentration of NaOH, and the particle size of PYP30 was smaller than that of PYP10-KH550 (PYP10 treated with 5% KH550). The laser granularity analyser results show that the particle size of dry PYPs increased with the concentration of NaOH. The settle time of PYPs in water indicated that the stability of PYPs increased with the concentration of NaOH and PYP10-KH550 has the poorest stability. These results indicated that PYP30 has smallest particles and best stability, and it has the potential to be used in industry.
    Type of Medium: Online Resource
    ISSN: 1755-1307 , 1755-1315
    URL: Article
    DOI: 10.1088/1755-1315/558/4/042020
    Language: Unknown
    Publisher: IOP Publishing
    Publication Date: 2020
    detail.hit.zdb_id: 2434538-6
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 8
    Online Resource
    Online Resource
    Tuning nano-architectures and improving bioactivity of conducting polypyrrole coating on bone implants by incorporating bone-borne small molecules
    Royal Society of Chemistry (RSC) ; 2014
    In:  J. Mater. Chem. B Vol. 2, No. 45 ( 2014-10-21), p. 7872-7876
    Details
    In: J. Mater. Chem. B, Royal Society of Chemistry (RSC), Vol. 2, No. 45 ( 2014-10-21), p. 7872-7876
    Type of Medium: Online Resource
    ISSN: 2050-750X , 2050-7518
    URL: Article
    DOI: 10.1039/C4TB01053A
    Language: English
    Publisher: Royal Society of Chemistry (RSC)
    Publication Date: 2014
    detail.hit.zdb_id: 2702241-9
    detail.hit.zdb_id: 2705149-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 9
    Online Resource
    Online Resource
    Building Change Detection in Remote Sensing Imagery with Focal Self-Attention and Multi-Level Feature Fusion
    MDPI AG ; 2023
    In:  Electronics Vol. 12, No. 13 ( 2023-06-24), p. 2796-
    Details
    In: Electronics, MDPI AG, Vol. 12, No. 13 ( 2023-06-24), p. 2796-
    Abstract: Accurate and intelligent building change detection greatly contributes to effective urban development, optimized resource management, and informed decision-making in domains such as urban planning, land management, and environmental monitoring. Existing methodologies face challenges in effectively integrating local and global features for accurate building change detection. To address these challenges, we propose a novel method that uses focal self-attention to process the feature vector of input images, which uses a “focusing” mechanism to guide the calculation of the self-attention mechanism. By focusing more on critical areas when processing image features in different regions, focal self-attention can better handle both local and global information, and is more flexible and adaptive than other methods, improving detection accuracy. In addition, our multi-level feature fusion module groups the features and then constructs a hierarchical residual structure to fuse the grouped features. On the LEVIR-CD and WHU-CD datasets, our proposed method achieved F1-scores of 91.62% and 89.45%, respectively. Compared with existing methods, ours performed better on building change detection tasks. Our method therefore provides a framework for solving problems related to building change detection, with some reference value and guiding significance.
    Type of Medium: Online Resource
    ISSN: 2079-9292
    URL: Article
    DOI: 10.3390/electronics12132796
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2662127-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 10
    Online Resource
    Online Resource
    Trends in respiratory diseases before and after the COVID-19 pandemic in China from 2010 to 2021
    Springer Science and Business Media LLC ; 2023
    In:  BMC Public Health Vol. 23, No. 1 ( 2023-02-01)
    Details
    In: BMC Public Health, Springer Science and Business Media LLC, Vol. 23, No. 1 ( 2023-02-01)
    Abstract: The ongoing benefits of coronavirus disease 2019 (COVID-19) nonpharmaceutical interventions (NPIs) for respiratory infectious diseases in China are still unclear. We aimed to explore the changes in seven respiratory infectious diseases before, during, and after COVID-19 in China from 2010 to 2021. Methods The monthly case numbers of seven respiratory infectious diseases were extracted to construct autoregressive integrated moving average (ARIMA) models. Eight indicators of NPIs were chosen from the COVID-19 Government Response Tracker system. The monthly case numbers of the respiratory diseases and the eight indicators were used to establish the Multivariable generalized linear model (GLM) to calculate the incidence rate ratios (IRRs). Results Compared with the year 2019, the percentage changes in 2020 and 2021 were all below 100% ranging from 3.81 to 84.71%. Pertussis and Scarlet fever started to increase in 2021 compared with 2020, with a percentage change of 183.46 and 171.49%. The ARIMA model showed a good fit, and the predicted data fitted well with the actual data from 2010 to 2019, but the predicted data was bigger than the actual number in 2020 and 2021. All eight indicators could negatively affect the incidence of respiratory diseases. The seven respiratory diseases were significantly reduced during the COVID-19 pandemic in 2020 and 2021 compared with 2019, with significant estimated IRRs ranging from 0.06 to 0.85. In the GLM using data for the year 2020 and 2021, the IRRs were not significant after adjusting for the eight indicators in multivariate analysis. Conclusion Our study demonstrated the incidence of the seven respiratory diseases decreased rapidly during the COVID-19 pandemic in 2020 and 2021. At the end of 2021, we did see a rising trend for the seven respiratory diseases compared to the year 2020 when the NPIs relaxed in China, but the rising trend was not significant after adjusting for the NPIs indicators. Our study showed that NPIs have an effect on respiratory diseases, but Relaxation of NPIs might lead to the resurgence of respiratory diseases.
    Type of Medium: Online Resource
    ISSN: 1471-2458
    URL: Article
    DOI: 10.1186/s12889-023-15081-4
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2023
    detail.hit.zdb_id: 2041338-5
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...