NCL Data2026 · dataset
Code, split files, out-of-fold predictions and latency measurements for "Coil leakage, training variance and FLOP proxies in the evaluation of real-time steel surface defect detectors"<p dir="ltr">Supplementary material for the article "Coil leakage, training variance and FLOP proxies in the evaluation of real-time steel surface defect detectors" (submitted to the Journal of Real-Time Image Processing).</p><p dir="ltr">The study re-evaluates real-time steel surface defect detectors on NEU-DET and GC10-DET with five-fold cross-validation, coil-disjoint folds for GC10-DET, repeat
Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Crystal structure
Data from: A pilot computer-vision model trained to identify slide-mounted scale insect pests from the family Rhizoecidae<p dir="ltr">Using root mealybugs (Hemiptera: Rhizoecidae) as a test case, this study gathered high-resolution extended depth of field images from slide-mounted museum specimens and trained a convolutional neural network (CNN) to identify and distinguish among 16 species that are encountered as agricultural pests in plant quarantine or greenhouses. A pretrained EfficientNetV2-M model was trained u
ZivaHub + Deakin Research Online + DMU Figshare + HKU DataHub + Swinburne Figshare + DaYta Ya Rona + SUNScholarData + figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
DySPAM-Net dataset<p dir="ltr">This dataset contains field-collected mango (Mangifera indica L.) canopy images acquired for the development and evaluation of DySPAM-Net (Dynamic Sequential Phenology-Aware Multimodal Network), a deep-learning framework for early-stage mango yield prediction.</p><p dir="ltr">The dataset was collected from a commercial mango orchard in Gujarat, India, using smartphone-based field imag
ZivaHub + Deakin Research Online + DMU Figshare + HKU DataHub + Swinburne Figshare + DaYta Ya Rona + SUNScholarData + figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Data and code for: Evaluating Multitask Deep Learning for Multi-Crop Plant Health Recognition under Seed Variation and Crop Transfer<p dir="ltr">This item contains the data records and code supporting the study "Evaluating Multitask Deep Learning for Multi-Crop Plant Health Recognition under Seed Variation and Crop Transfer" (Cogent Food & Agriculture, under review).</p><p dir="ltr">The study compares four output formulations (single-task joint classification, independent multitask heads, multitask fusion, and fusion condition
ZivaHub + Deakin Research Online + DMU Figshare + HKU DataHub + Swinburne Figshare + DaYta Ya Rona + SUNScholarData + figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
<b>Multimodal Assessment of Historic Building Facades: From Component Core Morphotypes to Building-Level Visible Vulnerability</b><p dir="ltr">该数据集和可重复性包随手稿<b>历史建筑立面检查与建筑层评估的多模态计算》一书。</b> 该研究开发了一种多模态计算工作流程,用于对地理分散的历史建筑立面进行初步检查和建筑层级评估。</p><p dir="ltr">该研究包括<b>220座历史建筑、448张实地照片,以及来自</b>中国东铁路沿线三个研究区的2770个立面构件实例。该工作流程集成了YOLO26m-seg用于组件实例分割,Qwen2.5-VL用于结构化可视化解释,以及基于SAM2的Grounding DINO用于可见光构建和立面测量。</p><p dir="ltr">该库包含补充材料、机器可读统计表、建筑级分析结果、鲁棒性和敏感性分析、空间邻接输出、人工审核统计数据以及研究中使用的可重复性脚本。补充材料包括<b>图S1–S10和表S1–S38</b>,涵盖模型参数、编码粒度分析、立面质量阈值、群集感
ZivaHub + Deakin Research Online + DMU Figshare + UCL Research Data Repository2026 · dataset · unknown
Enhancing gait recognition with 3D markerless motion captureIn recent years gait has increased in popularity as a biometric and gait recognition has matured into a larger field that is is attracting international interest. Most current state-of-the-art gait recognition systems use appearance-based methods which are fast and capable of high performance on gait datasets. With the emergence of deep learning the focus of appearance-based methods has shifted, f
ZivaHub + Deakin Research Online + DMU Figshare + UCL Research Data Repository2026 · dataset · unknown
Deep learning for processing histopathology imagesHistopathology is the study and diagnosis of disease via tissue microscopy and it is currently the ‘gold-standard‘ in formally diagnosing many types of disease including cancers.<br>Due to increasing workloads on pathologists, there is a growing need for automated image analysis pipelines that are able to filter out obviously benign samples. However, these algorithms are sensitive to factors of va
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset · unknown
Development of structural assessment approaches for bridges using vision based unmanned aerial systemsThis thesis aims to advance remote sensing techniques for bridge structures using Unmanned Aerial Systems (UAS) to (1) enhance the bridge inspection process particularly for crack detection and (2) to enhance the bridge assessment process by utilising UAS to measure bridge displacements. <br><br>To enhance the bridge inspection process, the study is trying to address the challenges associated with
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Scour depth prediction, using computer vision at a FlexiArch bridgeScour induced failure of masonry arch bridges is the most common cause of bridge collapse, especially during extreme flood events. Over recent years there has been a significant number of documented scour-induced failures of this bridge stock across the world. The extent of the scour can erode the supporting soil or sediment around the bridge piers or abutments, leading to a loss of support for th
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset · unknown
Deep learning of dyadic interaction visual cues for human-robot collaboration in assembly tasks<p></p><p>This thesis examines the integration of multiple visual cues in dyadic interactions through deep learning to improve interactivity and intuitiveness in human-robot interactions, particularly in assembly tasks. Serving as a preliminary effort, these bodies of work seek to address the critical deficiencies in current dyadic human robot interaction methodologies, which typically depend on i
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Alternative 3D processing techniques for complex automated material handlingThis project presents a new method for applying classical image processing and morphology to 3D vision systems. The motivation for this project is to allow for the further development of Autonomous Guided Vehicles (AGVs), specifically in their ability to interact with complex objects that cannot be characterised by current learning data sets, placed in un-structured environments. Current trends in
Teesside University Research Data Repository2026 · dataset · unknown
CLBP-400: A Real-World Video Dataset for Cuff-Less Blood Pressure Estimation via rPPGThe development of remote blood pressure (BP) measurement algorithms using remote photoplethysmography (rPPG) has significant limitations, including the small size of publicly available datasets, privacy concerns regarding facial videos, and a lack of diverse, realistic datasets associated with actual BP measurements. To address these challenges, this study aimed to provide comprehensive, simultan
UCL Research Data Repository2026 · dataset · unknown
Development of a time-synchronised multi-input computer vision system for structural monitioring utilising deep learning for vehicle identificationA reliable transport infrastructure is vital to the commercial and lifestyle demands of a developed country, with the majority of journeys occurring by road. Bridges are a key component of this infrastructure, if a bridge fails or is unnecessarily closed it has widespread adverse effects throughout the surrounding area. Detailed monitoring is essential to ensure adequate maintenance of these struct
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
Цифровизация нефтегазовой отрасли: Как компьютерные технологии меняют добычу и переработку углеводородов<p dir="ltr">· <b>Цифровой двойник месторождения:</b> Компьютерная система создаёт виртуальную копию всей инфраструктуры — от отдельной скважины до магистрального трубопровода. Это позволяет виртуально тестировать различные сценарии эксплуатации без риска для реального оборудования.</p>
ZivaHub + Deakin Research Online + DMU Figshare + HKU DataHub + Swinburne Figshare + DaYta Ya Rona + SUNScholarData + figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Visualization1.aviRotating-object measurement
ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset
TOWARD SPATIAL INTELLIGENCE AND PHYSICALLY REALISTIC WORLD MODELS<p dir="ltr">Spatial intelligence requires models to infer and maintain coherent three-dimensional structure, preserve objects and relations across viewpoints, compose interactable environments, and respect geometric and physical constraints. Progress toward such world models is limited by two forms of data scarcity: a shortage of diverse, high-quality real-world spatial observations and the narro
Hugging Face Datasets2026 · dataset
DragonCheat-AI/DragonData-4Dragon 4 Dataset Dataset for object detection in Standoff 2. Contains labeled screenshots with two classes: ct (Counter-Terrorist) and tr (Terrorist). Contents Format: YOLO (images + .txt labels) Classes: ct, tr Split: train / valid / test License MIT
ZivaHub2026 · dataset
A Direct Coordinate-Propagation Algorithm for<p dir="ltr">We define a coordinate representation for a restricted class of CNF formulas assembled</p><p dir="ltr">from bounded local cells. Every local Boolean assignment is represented by a normalized</p><p dir="ltr">deficit coordinate, and every clause excludes exactly its unique complementary coordinate on</p><p dir="ltr">its own support. Neighboring cells communicate through shared coordinat
figshare + Loughborough Research Repository2026 · Astronomical catalogue
Dataset associated with "Instrumented Vehicle Multi-Sensor Dataset: LiDAR, GNSS, and Stereo Camera Recordings of Roadside Sign Approaches"<p dir="ltr">This dataset contains time-synchronized LiDAR point cloud, GNSS/INS, and stereo camera recordings from an instrumented test vehicle (Chevrolet Bolt EUV, Virginia Tech AutoDrive Challenge platform) performing four controlled approaches toward roadside regulatory traffic signs. Recordings were collected at nominal speeds of 15, 20, and 25 mph, including one run incorporating a braking m
figshare + Loughborough Research Repository2026 · Astronomical catalogue
KerbTrack-Syn: A Large-Scale Synthetic Dataset for Kerbside Household Bulk Waste Detection<p dir="ltr">KerbTrack-Syn is a large-scale synthetic dataset comprising 5,114 high-resolution images of kerbside household bulk waste scenes. The dataset was generated using a real-image-guided FLUX-LoRA workflow derived from the KerbTrack benchmark dataset and is intended to support research in object detection, illegal dumping monitoring, smart waste management, synthetic data generation, and A
figshare + Loughborough Research Repository2026 · Astronomical catalogue
Table 1_TB-YOLOv8n: an improved YOLOv8n-based model for tip-burn detection in plant factory-grown pakchoi under LED lighting.docxIntroduction<p>Plant factory-grown pakchoi is prone to tip-burn under high-density cultivation, limited airflow, and rapid growth conditions, which reduces leaf integrity and commercial quality. Image-based detection of small or mild visible tip-burn symptoms remains challenging because the affected regions are usually small, irregularly shaped, low in color contrast, and easily disturbed by red-b
Teesside University Research Data Repository2026 · dataset
Enhancement Without Replacement: Route-Preserving Residual Fusion for Low-Light Visible–Thermal Pedestrian DetectionThis dataset contains the reproducibility materials supporting the manuscript "Enhancement Without Replacement: Route-Preserving Residual Fusion for Low-Light Visible–Thermal Pedestrian Detection" (submitted to Machine Vision and Applications). The deposited materials include model configurations for ConcatFusion-s, ConcatFusion-s-wide, RoutePreserve-s no-KD, residual-source variants, and insertio
figshare + Loughborough Research Repository2026 · Astronomical catalogue
Dataset split files for ExDark and RUODThis file contains the fixed train/validation/test split lists for the ExDark and RUOD datasets used in the revised manuscript. The split files are provided to support reproducible dataset partitioning and fair comparison across all evaluated methods. The original ExDark and RUOD images are not redistributed and should be downloaded from their official sources.
Teesside University Research Data Repository2026 · dataset
Vehicle Images for Binary Classification of Unsafe Passenger Hanging in Dhaka, BangladeshThis dataset contains 523 images for binary classification of unsafe passenger hanging in buses and legunas in Dhaka, Bangladesh. Positive means unsafe passenger hanging (251 images); Negative means safe/normal (272 images). These image-level class definitions were confirmed by the project representative during dataset preparation. The original hierarchy is preserved under Final_Dataset: Bus/Posit
figshare2026 · Astronomical catalogue
ALHCTNet<p dir="ltr">Micro-expression recognition plays an important role in fields<br>such as interpersonal communication, emotion analysis, and psychological research. At present, the micro-expression recognition<br>task has achieved certain results, but maintaining a stable and high<br>recognition accuracy is still a performance bottleneck problem of<br>this task. To address this problem, we propose th