Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
14,111 datasets
Ville de Shawinigan provides a polygonal layer of public parking lots on its territory. The dataset includes attributes such as name, location, and 24-hour and 2-hour seat counts. It is available in multiple formats including SHP, GEOJSON, and CSV.
Mingyue Chi's research dataset details the development and optimization of a plant-based yogurt using lotus seeds as the primary raw material. The data likely contains results from single-factor experiments and response surface methodology used to determine optimal probiotic strain combinations and fermentation parameters. The dataset was last updated on 2026-04-28.
Integrated Marine Observing Systems (IMOS) National Reference Station data includes phytoplankton pigment composition analysis from nine coastal sites across Australia. Sampling began between September 2008 and November 2010 and is ongoing for seven sites, with monthly collection from small vessels. The dataset is interoperable with other national and international programs through IMOS Infrastructure.
Nine coastal sites around Australia provide measurements of Secchi depth and total suspended solids. Sampling began between September 2008 and November 2010 and is ongoing at seven sites, with monthly collection from small vessels. The dataset is managed by the Integrated Marine Observing Systems (IMOS) National Mooring Network and superseded by a combined biogeochemical collection in 2022.
Four-channel electrogastrography recordings from six adult participants during a four-hour protocol. The data captures gastric electrical activity across fasting, food intake, and postprandial periods. The dataset was authored by Alonso Ochoa and last updated in June 2026.
World Bank data on Singapore's technology base, including research and development, scientific publications, high-technology exports, and intellectual property. The dataset is compiled from sources like UNESCO, the U.S. National Science Board, and the World Intellectual Property Organization. It was last updated on 2026-04-28.
Nine Australian coastal sites provide time-series data on salinity, carbon, alkalinity, oxygen, and nutrients from monthly water sampling. Sampling began between 2008 and 2010 and is ongoing for seven sites, with historical data available for three sites dating back to 1944. The dataset is part of the Integrated Marine Observing System (IMOS) National Mooring Network.
A 159.5 MB collection of files investigates spatiotemporal patterns of mortality from traumatic brain injury (TBI), kidney transplantation, and the prevalence of chronic kidney disease (CKD) in Brazil. The data was authored by Marcia Neves Oliveira and last updated on June 1, 2026. It uses space-time cube (STC) analysis to identify geographic disparities affecting organ donation potential and access to transplant services.
Democratic Republic of the Congo administrative boundaries for levels 0 to 3, structured into 26 provinces, 164 territories, and 519 health zones. The dataset was contributed by OCHA DRC, quality assured by OCHA FIS and HDX, and was reviewed for accuracy in December 2024. It is part of the Global Subnational Administrative Boundaries collection.
Afghanistan administrative boundaries for levels 0 to 2, structured into 34 provinces and 401 districts. The dataset was contributed by OCHA Afghanistan, quality assured by OCHA FIS and HDX, and is part of the Global Subnational Administrative Boundaries collection. It was last edited in March 2026 and is valid for use by the humanitarian community.
Macao SAR, China science and technology indicators from the World Bank's data portal. The dataset likely contains metrics on research and development, scientific publications, high-technology exports, intellectual property, and related fees. It was last updated on 2026-04-28 and aggregates data from sources including UNESCO, the U.S. National Science Board, UN Statistics Division, IMF, and WIPO.
251.7 KB of thermochemical and kinetic data for the CH + N2 reaction leading to prompt NO formation. The dataset contains results from composite coupled cluster protocols and two-dimensional master equation simulations, predicting rate coefficients with uncertainties reduced to less than a factor of 1.3. It was authored by Thanh Lam Nguyen and last updated on 2026-05-21.
98.95% accuracy was achieved by the LGF-CBAM model on the Cocoa_Pod_Disease_Gh dataset. This dataset was used to evaluate a novel deep learning framework for classifying cocoa pod diseases, contributed by Henry Techie-Menson and last updated in April 2026. The 5.5 KB Excel file likely contains summary metrics from cross-dataset evaluations on four other cocoa disease image sets.
A 5.5 KB Excel file containing summary data of split disease conditions, likely including model performance metrics. The dataset was authored by Henry Techie-Menson and last updated on April 30, 2026. It supports research on a novel deep learning framework for cocoa disease classification.
Hyperparameters used to train a ResNetV2-101 model with a Learnable Gated Fusion Convolutional Block Attention Module (LGF-CBAM). The dataset was authored by Henry Techie-Menson and last updated on 2026-04-30. It is a small 5.5 KB XLS file.
Henry Techie-Menson's research dataset, last updated April 30, 2026, contains performance metrics for a novel deep learning model on multiple cocoa pod disease image datasets. The 5.5 KB XLS file likely includes accuracy, F1, and PPV scores from cross-dataset evaluations. Results are reported for the Cocoa_Pod_Disease_Gh, Cocoa Diseases (YOLOv4), Black and Borer Pod Rot, Cacao Diseases in Davao, and Coffee and Cocoa datasets.
Chao Zhang published a table of sensitivity and specificity metrics for the Inception-ResNetV2-SE model on May 14, 2026. The data shows model performance across different probability thresholds for classifying peritoneal metastasis on a test set. The file is a 12.0 KB XLSX spreadsheet licensed under CC-BY-4.0.
A 17.9 MB dataset from figshare characterizes the 40 cm⁻¹ 'gateway' mode of the thermosalient phase transition in the 4-DBpFO organic crystal. The data was generated using an Activity Weighted Velocities (AWV) method integrating classical trajectories with hybrid Density Functional Theory (DFT) Raman activities, benchmarked against experimental spectra. The dataset was authored by Daria Ruth Galimberti and last updated on May 14, 2026.
FAIRHiveFrames-1K is a publicly available dataset of 1,265 manually annotated hive frame images designed to support research in precision apiculture and computer vision. It contains 124,669 annotated regions of interest across seven biologically meaningful categories, derived from a USDA–ARS multi-sensor research reservoir. The dataset is distributed with multiple annotation formats, fixed train/validation splits, and baseline model weights.
World Bank Group data on Japan's technology base, last updated 2026-04-28. The dataset likely contains indicators such as research and development expenditure, scientific publications, high-technology exports, and intellectual property metrics. It aggregates data from sources including UNESCO, the U.S. National Science Board, and the World Intellectual Property Organization.