Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
9,300
datasets available to search
ShareScore release 0.7.1
Dataset results
9,300 results for “detection”
A 3D human head dataset for non-coplanar keypoints detection
<p>This MRI volumes ("nii.gz" format) were part of the IXI dataset (<a href="https://brain-development.org/ixi-dataset/">IXI Dataset – Brain Development (brain-development.org)</a>). For our work, we focused on the T1-weighted images, which provided an higher degree of anatomical details. We chose and manually annotated 4 non-coplanar points inside these volumes, in order to train a 3D CNN to detect them. Such points could be exploited to perform alignment tasks. The annotation was carried out using 3D Slicer, and we encourage to use it for the visualization of the volumes and the relative annotations ("json" format). Below a description of the 4 keypoints:</p> <ul> <li>Keypoint 1: The cerebral aqueduct in correspondence of the transverse plane slice where the mammillary bodies are two well defined little balls.</li> <li>Keypoint 2: The point of contact between the two ventricles anterior horns before going into lateral ventricles (visualize on coronal plane)</li> <li>Keypoint 3: The right eye center in correspondence of the largest diameter circle (on the coronal plane)</li> <li>Keypoint 4: The left eye center in correspondence of the largest diameter circle (on the coronal plane)</li> </ul> <p>The dataset consists of 507 volumes with related annotations.</p>
Bus Violence: a large-scale benchmark for video violence detection in public transport
<p><strong>Dataset</strong></p> <p>The <em>Bus Violence </em>dataset<em> </em>is a large-scale collection of videos depicting violent and non-violent situations in public transport environments. This benchmark was gathered from multiple cameras located inside a moving bus where several people simulated violent actions, such as stealing an object from another person, fighting between passengers, etc. It contains 1,400 video clips manually annotated as having or not violent scenes, making it one of the biggest benchmarks for video violence detection in the literature.</p> <p>Specifically, videos are recorded from three cameras at 25 Frames Per Second (FPS) --- two cameras located in the corners of the bus (with resolution 960x540 px) and one fisheye in the middle (1280x960 px). The clips have a minimum length of 16 frames and a maximum of 48 frames, capturing a very precise action (either violence or non-violence). The dataset is perfectly balanced, containing 700 videos of violence and 700 videos of non-violence.</p> <p>The <em>Bus Violence</em> dataset is intended as a test data benchmark. However, for researchers interested in using our data also for training purposes, we provide training and test splits.</p> <p>In this repository, we provide</p> <ul> <li> <p>the 1,400 video clips divided into two folders named Violence /NoViolence, containing clips of violent situations and non-violent situations, respectively;</p> </li> <li> <p>two txt files containing the names of the videos belonging to the training and test splits, respectively.</p> </li> </ul> <p> </p> <p><strong>Citing our work</strong></p> <p>If you found this dataset useful, please cite the following paper</p> <blockquote> <pre>@inproceedings{bus_violence_dataset_2022, title = {Bus Violence: An Open Benchmark for Video Violence Detection on Public Transport}, doi = {10.3390/s22218345}, url = {https://doi.org/10.3390%2Fs22218345}, year = 2022, month = {oct}, publisher = {{MDPI} {AG}}, volume = {22}, number = {21}, pages = {8345}, author = {Luca Ciampi and Pawe{\l} Foszner and Nicola Messina and Micha{\l} Staniszewski and Claudio Gennaro and Fabrizio Falchi and Gianluca Serao and Micha{\l} Cogiel and Dominik Golba and Agnieszka Szcz{\k{e}}sna and Giuseppe Amato}, journal = {Sensors} } </pre> </blockquote> <p>and this Zenodo Dataset</p> <blockquote> <pre>@dataset{pawel_bus_violence_zenodo, author = {Paweł Foszner, Michał Staniszewski, Agnieszka Szczęsna, Michał Cogiel, Dominik Golba, Luca Ciampi, Nicola Messina, Claudio Gennaro, Fabrizio Falchi, Giuseppe Amato, Gianluca Serao}, title = {{Bus Violence: a large-scale benchmark for video violence detection in public transport}}, month = sep, year = 2022, publisher = {Zenodo}, version = {1.0.0}, doi = {10.5281/zenodo.7044203}, url = {https://doi.org/10.5281/zenodo.7044203} } </pre> </blockquote> <p> </p> <p><strong>Contact Information</strong></p> <p>Blees Sp. z o.o., Gliwice, Poland<br> mstaniszewski@blees.co</p> <p> </p> <p><strong>Acknowledgments</strong></p> <p>The presented dataset was supported by: European Union funds awarded to Blees Sp. z o.o. under grant POIR.01.01.01-00-0952/20-00 “Development of a system for analysing vision data captured by public transport vehicles interior monitoring, aimed at detecting undesirable situations/behaviours and passenger counting (including their classification by age group) and the objects they carry”); EC H2020 project "AI4media: a Centre of Excellence delivering next generation AI Research and Training at the service of Media, Society and Democracy" under GA 951911; research project INAROS (INtelligenza ARtificiale per il mOnitoraggio e Supporto agli anziani), Tuscany POR FSE CUP B53D21008060008.</p> <p> </p> <p><strong>License</strong></p> <p>The <em>Bus Violence </em>dataset was acquired by Blees Sp. z o.o. and is released under a Creative Commons Attribution license for non-commercial use.</p>
Unsupervised New Physics detection at 40 MHz: h+ -> tau nu Signal Benchmark Dataset
<p>Unsupervised New Physics detection at 40 MHz data challenge</p> <p>Signal Benchmark Dataset consisting of h+ -> tau nu decays produced in collision events (simulation of LHC 13 TeV proton-proton collisions) pre-filtered by a requirement of a muon or electron with 23 GeV transverse momentum. Data format description available on the data challenge web page: https://mpp-hep.github.io/ADC2021/</p>
Unsupervised New Physics detection at 40 MHz: h^0 -> tau tau Signal Benchmark Dataset
<p>Unsupervised New Physics detection at 40 MHz data challenge</p> <p>Signal Benchmark Dataset consisting of h^0 -> tau tau decays produced in collision events (simulation of LHC 13 TeV proton-proton collisions) pre-filtered by a requirement of a muon or electron with 23 GeV transverse momentum. Data format description available on the data challenge web page: https://mpp-hep.github.io/ADC2021/</p>
Unsupervised New Physics detection at 40 MHz: LQ -> b tau Signal Benchmark Dataset
<p>Unsupervised New Physics detection at 40 MHz data challenge</p> <p>Signal Benchmark Dataset consisting of Leptoquarks -> b tau decays produced in collision events (simulation of LHC 13 TeV proton-proton collisions) pre-filtered by a requirement of a muon or electron with 23 GeV transverse momentum. Data format description available on the data challenge web page: https://mpp-hep.github.io/ADC2021/</p>
Unsupervised New Physics detection at 40 MHz: Black Box Dataset
<p>Unsupervised New Physics detection at 40 MHz data challenge</p> <p>Signal Benchmark Dataset consisting of the signal+background Black Box datasets, containing collision events (simulation of LHC 13 TeV proton-proton collisions) pre-filtered by a requirement of a muon or electron with 23 GeV transverse momentum. Data format description available on the data challenge web page: https://mpp-hep.github.io/ADC2021/</p>
Unsupervised New Physics detection at 40 MHz: Training Dataset
<p>Unsupervised New Physics detection at 40 MHz data challenge</p> <p>Training dataset, consisting of a cocktail of Standard Model collision events (simulation of LHC 13 TeV proton-proton collisions) pre-filtered by a requirement of a muon or electron with 23 GeV transverse momentum. Data format description available on the data challenge web page: https://mpp-hep.github.io/ADC2021/</p>
Unsupervised New Physics detection at 40 MHz: A -> 4 leptons Signal Benchmark Dataset
<p>Unsupervised New Physics detection at 40 MHz data challenge</p> <p>Signal Benchmark Dataset consisting of A -> 4 leptons decays produced in collision events (simulation of LHC 13 TeV proton-proton collisions) pre-filtered by a requirement of a muon or electron with 23 GeV transverse momentum. Data format description available on the data challenge web page: https://mpp-hep.github.io/ADC2021/</p>
Wikipedia. Events and collective memory detection dataset
<p>This is the data accompanying the code (https://github.com/mizvol/WikiBrain), required to reproduce results of "Wikipedia graph mining: dynamic structure of collective memory" paper (https://arxiv.org/abs/1710.00398).</p>
Quality Assessment in DevOps: Automated Analysis of a Tax Fraud Detection System
<p>The dataset includes the results of the performance analysis of Big Blu case study under different workloads, number of available resources and execution demand of activities</p>
FG-OVD: Fine-grained Open-Vocabulary Object Detection Benchmark Suite
<p>A collection of annotations for PACO images containing free-form fine-grained textual captions of objects, their parts, and their attributes. It also comprises several sets of negative captions that can be used to test and evaluate the fine-grained recognition ability of open-vocabulary models.</p>
A new merged dataset of global ocean chlorophyll-a concentration for better trend detection
<p>Chlorophyll-a concentration (Chla) is recognized as an essential climate variable and is one of the primary parameters of ocean-color satellite products. Ocean-color missions have accumulated continuous Chla data for over two decades since the launch of SeaWiFS in 1997. However, the on-orbit life of a single mission is about five to ten years. To build a dataset with a time span long enough to serve as a climate data record (CDR), it is necessary to merge the Chla data from multiple sensors. The European Space Agency has developed two sets of merged Chla products, namely GlobColour and OC-CCI, which have been widely used. Nonetheless, issues remain in the long-term trend analysis of these two datasets because the intermission differences in Chla have not been completely corrected. To obtain more accurate Chla trends in the global and various oceans, we produced a new dataset by merging Chla records from the Sea-viewing Wide Field-of-view Sensor, Medium-spectral Resolution Imaging Spectrometer, Moderate Resolution Imaging Spectroradiometer, Visible Infrared Imaging Radiometer Suite, and Ocean and Land Colour Instrument with intermission differences corrected in this work. The fitness of the dataset as a CDR was validated by using in situ Chla and comparing the trend estimates to the multi-annual variability of different satellite Chla records. </p>
Transposable elements in rice detected by TEF
<p>Next generation sequence data of '<a href="https://www.gene.affrc.go.jp/databases-core_collections_wr_en.php">World Rice Core Collection</a>' and '<a href="https://www.gene.affrc.go.jp/databases-core_collections_jr_en.php">Rice Core Collection of Japanese Landraces</a>' distributing NARO genebank have been analyzed by the software '<a href="https://pubmed.ncbi.nlm.nih.gov/36418944/">Transposable Elements Finder</a>'. This data is an additional supplementary data of the TEF paper.</p> <p>Transposition evidences were detected by direct comparison of NGS short reads between Japonica rice Nipponbare (wrc01) and other cultivars. Nearby 21,000 kinds of head and tail sequence pairs of TE have been identified by TEF. Head and tail sequences of TE, chromosome number, position, and name of detected rice cultivar were listed. </p> <ul> <li>This version is TE list of <em>Oryza sativa</em> detected by TEFv1.4.</li> <li>Positions of TE transpositions were mapped on <a href="https://rapdb.dna.affrc.go.jp/download/archive/irgsp1/IRGSP-1.0_genome.fasta">Os-Nipponbare-Reference-IRGSP-1.0</a> distributed from <a href="https://rapdb.dna.affrc.go.jp/">The Rice Annotation Project Database</a>.</li> <li>Accession Numbers of NGS data are listed in Japanese page '<a href="https://www.gene.affrc.go.jp/databases-core_collections_wr.php">World Rice Core Collection</a>' and in NCBI SRA page '<a href="https://www.ncbi.nlm.nih.gov/Traces/study/?acc=DRP006572&o=acc_s%3Aa">Rice Core Collection of Japanese Landraces</a>'.</li> <li>The TEF software is available at: <a href="https://github.com/akiomiyao/tef">https://github.com/akiomiyao/tef</a></li> <li>Miyao, A., Yamanouchi, U. Transposable element finder (TEF): finding active transposable elements from next generation sequencing data. <em>BMC Bioinformatics</em> <strong>23</strong>, 500 (2022). <a href="https://doi.org/10.1186/s12859-022-05011-3">https://doi.org/10.1186/s12859-022-05011-3</a></li> </ul>
API traces for malware detection
<p>The dataset consists of traces of benign and malware samples. There are approximately 330k traces in the dataset, each meticulously collected and curated for research and analysis purposes, with an uncompressed size of 550GB. The dataset was collected during the second half of 2023. The file "shas_by_families.json" links each SHA(which is also the individual filenames) with the associated malware or benign family. Each file is in json format and includes the parameters of the API call as well.</p> <p> </p> <p>If you are using this dataset, please cite our work on Arxiv.<br>@misc{fellicious2025malwaredetectionbasedapi,<br> title={Malware Detection based on API calls}, <br> author={Christofer Fellicious and Manuel Bischof and Kevin Mayer and Dorian Eikenberg and Stefan Hausotte and Hans P. Reiser and Michael Granitzer},<br> year={2025},<br> eprint={2502.12863},<br> archivePrefix={arXiv},<br> primaryClass={cs.CR},<br> url={https://arxiv.org/abs/2502.12863}, <br>}</p>
Rafael et al., 2018: Deep Learning-Based Culture-Free Bacteria Detection in Urine Using Large-Volume Microscopy (Dataset)
<p>Dataset containing 1um polystyrene beads, urine samples, urine samples mixed with ecoli and homogenous ecoli. Dataset is the post-processing version of the images to remove static background. Original model was trained on the post-processed images exclusiviely.</p>
Detection of Submicron- and Nanoplastics Spiked in Environmental Fresh- and Saltwater with Raman Spectroscopy
<p>ABSTRACT</p> <p>Detection of small plastic particles in environmental water samples has been a topic of increasing interest in recent years. A multitude of techniques, such as variants of Raman spectroscopy, have been employed to facilitate their analysis in such complex sample matrices. However, these studies are often conducted for a limited number of plastic types in matrices with relatively little additional materials. Thus, much remains unknown about what parameters influence the detection limits of Raman spectroscopy for more environmentally relevant samples. To address this, this study utilizes Raman spectroscopy to detect six plastic particle types; 161 and 33 nm polystyrene, < 450 nm and 36 nm poly(ethylene terephthalate), 121 nm polypropylene, and 126 nm polyethylene; spiked into artificial saltwater, artificial freshwater, North Sea, Thames River, and Elbe River water. Overall, factors such as plastic particle properties, water matrix composition, and experimental setup were shown to influence the final limits of detection.</p>
Extra data to accompany code in GitHub burntfields_punjab, both used in Walker et. al. 2022, Detecting crop burning in India using satellite data
<p>Supplementary data files to accompany GitHub code 'burntfields_punjab' supporting Walker et. al. (2022) Detecting crop burning in India using satellite data [<a href="https://arxiv.org/abs/2209.10148">available here</a>] and Jack et. al. (2024) Money (not) to burn: Payments for ecosystem services to reduce crop residue burning).</p> <p>Includes custom Sentinel-2 cloud masks and data from Sentinel-2 Spectral Mixture Analysis to highlight Char (burning) based on general concept and methods from Daldegan et. al (2019). Spectral mixture analysis in Google Earth Engine to model and delineate fire scars over a large extent and a long time-series in a rainforest-savanna transition zone. Remote Sensing of Environment 232, 111340. </p> <p>Note: Bands in weekly BASMA layers are: 0 = green vegetation, 1 = Non-productive vegetation and bare soil, 2 = Char (burned).</p> <p>further details are provided at: <a href="https://github.com/klwalker-sb/burntfields_punjab">https://github.com/klwalker-sb/burntfields_punjab</a> (archived at: <a href="https://doi.org/10.5281/zenodo.11225292" target="_blank" rel="noopener">DOI: 10.5281/zenodo.11225292</a>)</p>
Raw images from: Detecting life by behavior, the overlooked sensitivity of behavioral assays
<p>Raw images of the manuscript entitle: "Detecting life by behavior, the overlooked sensitivity of behavioral assays"</p> <p>Description: Using a magnetotactic bacterial species,<em> Magnetospirillum magneticum</em>, we conduct a lab sensitivity experiment comparing PCR with the hanging drop behavioral assay, using a dilution series.</p> <p>Data:</p> <p>1.-Gel image resulted from the <em>Magnetospirillum magneticum </em>PCR assays. </p> <p>2.-Microphotographs of <em>Magnetospirillum magneticum </em>obtained using the hanging drop technique and serial dilution. </p> <p>3.-Videos 1 to 4.Environmental samples were taken from Agmon Hula lake, (33° 10′ N 35° 60′ E). We used the HDT (see main MS) to morphologically identify magnetotactic bacterial species.</p>
UAV-based imagery for road damage detection
<p>This dataset contains a set of annotated examples of damage present to the road, obtained via an UAV in Poznań, Poland. The imagery was obtained by flying a UAV over a set of roads at approximately 70m above ground level, and further creating an ortophotomosaics of three different pieces of road. Lastly, the ortophotomosaics were patched into non-overlapping patches of 512x512 pixel size, and each patch was manually labeled with a set of objects and classes proposed in the UAPD dataset (https://doi.org/10.1016/j.autcon.2021.103991, https://github.com/tantantetetao/UAPD-Pavement-Distress-Dataset).</p> <p>Patches without a significant presence of the road-like objects were discarded, and the data includes:</p> <ul> <li>ortophotomosaics -- a set of three original ortophotomosaics with ground sampling distance of 2.54 cm/pixel in .tif format,</li> <li>labeled patches -- a set of 99 patches containing road with annotations in both PASCAL VOC (.xml) and YOLO (.txt) formats</li> </ul> <p>Lastly, this data has been used as a holdout set in a Master's thesis conducted at Poznań University of Technology.</p>
Dataset for the comparison of performance of two leak detectors using hydrogen reference leaks (supplement to paper "Advancing Hydrogen Leak Detection: Design and Calibration of Reference Leaks")
<p>Excel file containing some measurements made in December 2023, using three hydrogen reference leaks, to assess the performance of two distinct leak detectors, one portable and made specifically for hydrogen and one MSLD in hydrogen-mode.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.