Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
14,104 datasets
Sedimentological data from three research cruises conducted off southwest Victoria and Tasmania between 1985 and 1988. The dataset documents laboratory analyses on 135 cores, including grain size, calcium carbonate (CaCO3), and total organic carbon (TOC) measurements. The work was performed by the Bureau of Mineral Resources (BMR) and partners to model sedimentation on the continental margin.
A retrospective study of 150 children with sepsis admitted to a pediatric intensive care unit in China. Heparin-binding protein and routine inflammatory markers were measured within 24 and 48 hours of admission. The data was used to assess prognostic performance for outcomes including organ dysfunction progression, illness severity, and 28-day mortality.
A paper by David M. Williams presents the Quality as an Organizational Strategy (QOS) method for embedding improvement science into healthcare leadership systems. The 108.8 KB PDF document outlines five core activities for building a system of continuous improvement. It was last updated on May 29, 2026, and is licensed under CC-BY-4.0.
A 20.2 KB document by Zirong Liu, last updated in May 2026, describes the construction of an in vitro model for ischemic-type biliary lesion (ITBL). The model uses human intrahepatic cholangiocyte organoids (ICOs) cultured under ischemia and hypoxia conditions. The study evaluates the model's validity using immunofluorescence, RT-qPCR, Western blotting, and transcriptomic analysis.
Five commercially available biological control organisms were screened in plate assays against Cladosporium cladosporioides on raspberry. Three agents, including a Trichoderma sp., Bacillus subtilis QST 713, and B. amyloliquefaciens FZB24, were tested in field studies, showing significant reductions in fruit lesions. The dataset, 85.9 KB in size and authored by Lauren Helen Farwell, was last updated on 2026-05-11.
Research data assesses the efficacy of five biological control agents against the fungal pathogen Cladosporium cladosporioides on raspberries. The dataset includes results from dual-culture plate assays and field studies conducted in the UK, evaluating preventive and curative applications. It was authored by Lauren Helen Farwell and published on figshare under a CC-BY-4.0 license.
Near real-time data on unplanned road disruptions managed by the Victorian Department of Transport and Planning and local councils, refreshed every 60 seconds. It includes location, reason, lane closures, public advice, and tow truck allocations for accidents in the Melbourne Controlled Area. Data is collected from the Road Incident Database (RID) and a third-party probe system.
A 0.5m resolution bathymetry grid was created for the Australian Hydrographic Office from a survey conducted between 25-26 September 2020. The surface covers an area between Gantheaume Point and Talboys Rock, Broome, Western Australia, and is provided in MSL, LAT, and Ellipsoid vertical datums. Data was acquired using a Kongsberg EM 2040D multibeam echosounder and processed with Caris HIPS & SIPS software.
A dataset for vehicle brand logo classification and identification from surveillance and automated number plate recognition feeds. It contains real-world images from Kozhikode District, Kerala, India, and a training set augmented with 1,170 high-fidelity synthetic images. The dataset was created by Arun Natarajan and last updated on 2026-05-24.
Figshare data from a study investigating serotonin depletion's role in migraine susceptibility via trigeminal ganglion neuron sensitization. The dataset includes electrophysiological parameters, correlation analyses, and demographic data for neuron groups, published under a CC-BY-4.0 license. It was last updated on 2026-05-13.
Forty mesh traps collected litterfall every two weeks for five years in an old-growth upland forest in Brazil's Tapajos National Forest. The dataset reports the mean and standard error of mass for sorted components like leaves, fruits, flowers, wood, and miscellaneous material, converted to Mg/ha/yr. It was produced by NASA as part of the LBA-ECO project.
Evaluation metrics for the LiteFeatNet convolutional neural network tested on the RFMiD 2.0 dataset. The model, developed by Usman Rafi, was trained on 1,824 retinal fundus images across three disease classes and achieved a top testing accuracy of 90.33%. The dataset was last updated on May 11, 2026.
Class-wise performance metrics for the LiteFeatNet convolutional neural network evaluated on retinal fundus images. The dataset contains results from experiments using 1,824 images across three disease classes from the Retinal Fundus Multi-Disease Image Dataset (RFMiD), split 60:20:20 for training, validation, and testing. It was authored by Usman Rafi and last updated on May 11, 2026.
Usman Rafi published performance metrics for the LiteFeatNet model on May 11, 2026. The data includes testing accuracy, precision, recall, F1-score, and inference time results from experiments on the Retinal Fundus Multi-Disease Image Dataset (RFMiD). The model was evaluated on 1,824 images across three disease classes and compared against twelve state-of-the-art architectures.
1824 retinal fundus images from three disease classes were used to train the LiteFeatNet model. The dataset, created by Usman Rafi and last updated in May 2026, contains parameters likely used for augmenting the image data. The model achieved a testing accuracy of 90.33% and an inference time of 4 milliseconds per image.
A tabular dataset compares the performance and computational characteristics of a proposed lightweight CNN model against multiple state-of-the-art architectures. The data originates from experiments using 1,824 retinal fundus images from the Retinal Fundus Multi-Disease Image Dataset (RFMiD), split into three disease classes. The dataset was created by Usman Rafi and last updated on May 11, 2026.
Usman Rafi's dataset from 2026 contains performance metrics for the LiteFeatNet convolutional neural network. The model was trained and evaluated on 1,824 retinal fundus images from the Retinal Fundus Multi-Disease Image Dataset (RFMiD). It achieved a testing accuracy of 90.33% with an inference time of 4 milliseconds per image.
2012-2013 estimates of soil organic carbon stocks and wetland intrinsic potential across the Hoh River Watershed in Washington's Olympic Peninsula. The dataset includes high-resolution (4-m) raster layers of SOC at 1m and 30cm depths, SOC standard deviations, and WIP, plus 36 field observation records collected from 2020 to 2022. Data was produced by NASA using a random forest model and published equations.
IDEAM-authorized conformity assessment bodies for measuring pollutant emissions from mobile sources in Colombia. The dataset includes details such as laboratory equipment, authorized personnel, and software versions. Data is provided as raw, unvalidated information for transparency and open data compliance under Law 1712 of 2014.
Geophysical traverses and coring by the Atlantis II provide information on sedimentary and tectonic processes in the northeast Indian Ocean. The dataset includes seismic profiles used to create isopach maps and a diverse group of sediment cores from sites above and below the carbonate compensation depth. Data was contributed by the Australian Ocean Data Network and last updated in June 2026.