Dual-stream detection and segmentation framework for vision based unmanned ground vehicle pothole perception on unstructured roads by Chenyuan He, He Yang, Zhouyu Zhang, Hai Wang, Yingfeng Cai, Long Chen, Can Zhong, Yiqun Zhang

“…Extensive experiments are conducted on a self-constructed dataset comprising 3,000 annotated images of unstructured roads. …”
Get full text

DCSLK: Combined large kernel shared convolutional model with dynamic channel Sampling by Zongren Li, Shuping Luo, Hongwei Li, Yanbin Li

“…This not only curtails the parameter count and mitigates the model complexity but also sustains the model's capacity to capture extensive spatial relationships. Additionally, in light of the problems of spatial feature information loss and augmented memory access during the 1 × 1 convolutional channel compression phase, this study further puts forward a dynamic channel sampling approach, which markedly elevates the accuracy of tumor subregion segmentation. …”
Get full text

Cerebral Amyloid Angiopathy Is Associated With Higher R2 Relaxation Rate: An MRI and Pathology Study by Md Tahmid Yasar, Arnold M. Evia, Mahir Tazwar, Sue E. Leurgans, David A. Bennett, Julie A. Schneider, Konstantinos Arfanakis

“…R2 abnormalities were significant in severe CAA, but were limited in terms of spatial extent and magnitude in moderate CAA, and were not detectable in mild CAA. …”
Get full text

Spatiotemporal predictions of the alternative prey hypothesis: Predator habitat use during decreasing prey abundance by Mitchell J. Brunet, Kevin L. Monteith, Katey S. Huggler, Daniel J. Thompson, Patrick W. Burke, Mark Zornes, Patrick Lionberger, Miguel Valdez, Joseph D. Holbrook

“…Further, we evaluated how spatial variation in access to primary prey affected habitat selection, and assessed similarity and overlap between habitats used by each prey species. …”
Get full text

Cyclic Learning Rate U-Shaped ResNet Embedded With Dual Attentions for Velocity Model Building by Chaobo Zhu, Zhiguo Wang, Feipeng Li, Huai Zhang, Jinghuai Gao

“…Seismic shot gathers typically exhibit weak spatial correlations between data and velocity models, further complicated by sparsity due to reflected events. …”
Get full text

An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic Requirements by Wei Zhu, Qingsheng Guo, Nai Yang, Ying Tong, Chuanbang Zheng

“…Road network data and building footprint data from OSM (Open Street Map) were used as auxiliary information to provide the MsM-GAN with cartographic knowledge about spatial shapes and spatial relationships when generating electronic map tiles from remote sensing images. …”
Get full text

An Autofocus Method for Long Synthetic Time and Large Swath Synthetic Aperture Radar Imaging Under Multiple Non-Ideal Factors by Kaiwen Zhu, Zhen Wang, Zehua Dong, Han Li, Linghao Li

“…The proposed method can effectively achieve SAR focusing with a long synthetic time and large swath, considering spatial and temporal variant non-ideal factors. Point target simulations and distributed target simulations based on real scenarios are conducted to validate the proposed method.…”
Get full text

Participatory and non-participatory forest ecosystem services valuation in Sub-Saharan Africa: a systematic literature review by Fatima Salaheldin Mohamad Ali, Jan Henning Sommer, Christian Borgemeister, Lisa Biber-Freudenberger

“…Based on our findings, we recommend conducting all types of research—participatory and non-participatory—but ideally, integrated approaches in forest ES valuation to support the effective and contextually relevant conservation strategies across Africa. …”
Get full text

A New Pallet-Positioning Method Based on a Lightweight Component Segmentation Network for AGV Toward Intelligent Warehousing by Bin Wu, Shijie Wang, Yi Lu, Yang Yi, Di Jiang, Mengmeng Qiao

“…To overcome the challenge of redundant computations in existing semantic segmentation models, which are unable to balance spatial details and high-level semantic information, this network utilizes a dual-branch attention mechanism within an encoder–decoder architecture to effectively capture spatial details. …”
Get full text

Hyperspectral Image Mixed Denoising via Robust Representation Coefficient Image Guidance and Nonlocal Low-Rank Approximation by Jiawei Song, Baolong Guo, Zhe Yuan, Chao Wang, Fangliang He, Cheng Li

“…However, most of these methods focus on optimizing the denoiser for representation coefficient images (RCIs) without considering how to construct RCIs that better inherit the spatial structure of the clean HSI, thereby affecting subsequent denoising performance. …”
Get full text

Stratification Effects on Estuarine Mixing: Comparative Analysis of the Danshui Estuary and a Thermal Discharge Outlet by Yaozhao Zhong, Hwa Chien

“…The horizontal dispersion coefficients calibrated by spatial scale showed no significant difference between different tides (flood tide: 0.53 ± 0.18 m² s⁻¹, ebb tide: 0.46 ± 0.17 m² s⁻¹). …”
Get full text

Fault diagnosis method for rigid guides in vertical shaft hoisting systems by WANG Jianfeng, JIN Yuanzhi, ZHANG Yong, WANG Yongzhen, HE Jiacong

“…Channel attention and spatial attention modules were introduced and combined with the residual learning mechanism to design a residual attention module, which simultaneously captured channel and spatial feature information, extracting more discriminative features. …”
Get full text

MLHI-Net: multi-level hybrid lightweight water body segmentation network for urban shoreline detection by Jianhua Ye, Pan Li, Yunda Zhang, Ze Guo, Shoujin Zeng, Youji Zhan

“…The over-parameterized convolutional layers enhance the interactive ability of feature representation and context information. The removal of spatial and channel redundancy, in conjunction with interactive reconstruction, serves to simulate attention and enhance the learning ability of waterscape. …”
Get full text

Imported malaria in Cabo Verde (2010-2024): Risks to post-elimination stability. by Adilson José DePina, Giovanni Leite Lima, António Lima Moreira, El Hadji Amadou Niang, Klauss Kleydmann S Garcia

“…Joinpoint Regression Analysis was performed to assess time trends, and Holt-Winters additive models were applied for time-series forecasting. Spatial data visualization was also conducted. A total of 383 imported malaria cases were reported. …”
Get full text

The Role of a Smartphone Application in Monitoring the Risk of Hearing Loss Associated with Personal Listening Devices in Young Adults by Deniz Tuz, Selin Sariçamlik, Ceren Bodur, Gülce Kirazli, Pelin Piştav Akmeşe

“…Methods A cross-sectional study was conducted on 99 healthy iPhone Operating System (iOS) smartphone users aged 17 to 31 years. …”
Get full text

Ecological and temporal drivers of human-gaur conflict in Tamil Nadu, India by Thekke Thumbath Shameer, Priyambada Routray, A. Udhayan, Rangaswamy Kanchana, Senbagapriya Sekar, Sivaranjani Shankar, Dhayanithi Vasanthakumari, Selvakumar Subramaniyam

“…We analyzed spatial and temporal trends by categorizing data by forest division and date of occurrence and predicted conflict risk zones using an ensemble modeling approach via the sdm package. …”
Get full text

Evaluating Water Levels From the Surface Water and Ocean Topography (SWOT) Mission in a Hyper‐Tidal Coastal and Estuarine Environment by I. D. Lichtman, P. S. Bell, C. Gommenginger, C. Banks, F. M. Calafat, J. Brown, S. D. P. Williams

“…SWOT's altimetry images reveal complex, changing spatial patterns across the Land‐Ocean Aquatic Continuum. …”
Get full text

GDText-VM: an arbitrary-shaped scene text detector based on globally deformable VMamba by Yingnan Zhao, Zheng Hu, Fangqi Ding, Jielin Jiang, Xiaolong Xu

“…This detector incorporates a global channel-spatial attention mechanism along with Fourier contour modeling. …”
Get full text

An Omni-Dimensional Dynamic Convolutional Network for Single-Image Super-Resolution Tasks by Xi Chen, Ziang Wu, Weiping Zhang, Tingting Bi, Chunwei Tian

“…Specifically, ODConvNet comprises four key components: a Feature Extraction Block (FEB) that captures low-level spatial features; an Omni-dimensional Dynamic Convolution Block (DCB), which utilizes a multidimensional attention mechanism to dynamically reweight convolution kernels across spatial, channel, and kernel dimensions, thereby enhancing feature expressiveness and context modeling; a Deep Feature Extraction Block (DFEB) that stacks multiple convolutional layers with residual connections to progressively extract and fuse high-level features; and a Reconstruction Block (RB) that employs subpixel convolution to upscale features and refine the final HR output. …”
Get full text

WTSM-SiameseNet: A Wood-Texture-Similarity-Matching Method Based on Siamese Networks by Yizhuo Zhang, Guanlei Wu, Shen Shi, Huiling Yu

“…This approach not only preserves the spatial structure of texture features but also improves the interpretability and stability of the fused features and the model. …”
Get full text