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.
1,389
datasets available to search
ShareScore release 0.9.0
Dataset results
1,389 results for “Multimodal”
Immunohistochemistry of Multimodal profiling of lung granulomas in macaques reveals cellular correlates of tuberculosis control
<p>(A) Architecture of macaque TB lung granuloma, where lymphocytes and macrophages are present in distinct regions. Immunohistochemistry and confocal microscopy were performed on a granuloma from an animal at 11 weeks post-Mtb infection to visualize localization of CD11c+ macrophages (cyan), CD3+ T cells (yellow), and CD20+ B cells (magenta)</p> <p>(B) Detection of mast cells in a 10-week NHP granuloma using immunohistochemistry, staining for tryptase (green) and c-kit (CD117)(red).</p> <p>(C) Detection of mast cells in a human lung granuloma. Hematoxylin and eosin stain and immunohistochemistry with multinucleated giant cells (stars, (top left) and c-kit (CD117) staining (indicated by arrows, top and bottom right).</p>
Fabrication and characterization of a multimodal 3D printed mouse phantom for ionoacoustic quality assurance in image-guided pre-clinical proton radiation research
<p>Dataset related to the publication: "Fabrication and characterization of a multimodal 3D printed mouse phantom for ionoacoustic quality assurance in image-guided pre-clinical proton radiation research"</p>
RU-AI: A Large Multimodal Dataset for Machine Generated Content Detection
<p>This repository contains all the collected and aligned data for RU-AI dataset. It is constructed based on three large publicly available datasets: Flickr8K, COCO, and Places205, by adding their corresponding machine-generated pairs from five different generative models in each modality. </p>
Raw data for the main figures of the paper: "Demixing fluorescence time traces transmitted by multimode fibers"
<p><strong>RawMovies.zip </strong></p> <p>This zip file includes the raw movies for each main figure of the paper. </p> <p>For figures 02, 03, 04, 04 and 06, we included 2 tiff files (2 stacks of images): <br>- The first one gives the measured footprints of the sources (ground truth). <br>- The second one is the raw movie (temporal sequence of images) acquired on the microscope for the specific experiment. </p> <p>For figure 07, the tiff file corresponds to a movie acquired while moving a single fluorescent bead away from the optical axis of the microscope (as in figure 7c). </p> <p><strong>RawRata.zip</strong></p> <p>This zip file contains raw data for figures 03, 04, 05 and 06. We have included two files for each figure:<br>- the _gt file is a matrix of the GT time traces (dimensions: number of sources x number of time bins)<br>- the other file is a 3D matrix corresponding to all the images acquired during the experiment. The first time frames are the measured footprints of each of the sources (ground truth). They were acquired by illuminating each source sequentially. The remaining frames correspond to the raw movie acquired during the experiment while illuminating the sources with the GT time traces. Dimensions of this 3D matrix are: (number of pixels in the x dimension) x (number of pixels in the y dimension) x (number of sources + number of time bins)</p> <p>This raw data is the input data to the python analysis function located in :<br>https://github.com/comediaLKB/DemixedFiberPhotometry. </p>
Data underlying the paper titled "Integrating multimodal Raman and photoluminescence microscopy with enhanced insights through multivariate analysis"
<p>The folder includes Raman and Photoluminescence surface maps of microsamples from Cultural Heritage materials. The maps were obtained using a multimodal optical microscope that integrates Raman and Photoluminescence optical techniques to perform a raster scanning of microsample surface. </p> <p>Data refer to the publication: https://doi.org/10.1088/2515-7647/ad5773</p> <p> </p>
Figure 2 in A sense of scale: Foraging cetaceans' use of scale-dependent multimodal sensory systems
Figure 2. Scale-of-senses schematic of the hypothetical interchange of sensory modalities used by baleen whales to locate prey at variable scales. The line for audition of signals from prey is faded to denote a lack of evidence for this sensory system in baleen whales. X-axis on log scale, with equivalent metric distance given in gray type, and associated scale below. Y-axis ranks the relative use of each sensory modality between 0 (no contribution) and 10 (highest contribution) relative to its own information capacity, not relative to other senses.
Figure 1 in A sense of scale: Foraging cetaceans' use of scale-dependent multimodal sensory systems
Figure 1. Scale-of-senses schematic of the hypothetical interchange of sensory modalities used by dolphins to locate prey at variable scales. The line for chemoreception is faded to denote a lack of support for the sensory system in dolphins. X-axis on log scale, with equivalent metric distance given in gray type, and associated scale below. Y-axis ranks the relative use of each sensory modality between 0 (no contribution) and 10 (highest contribution) relative to its own information capacity, not relative to other senses.
MSD-I: Million Song Dataset with Images for Multimodal Genre Classification
<p>The Million Song Dataset (https://labrosa.ee.columbia.edu/millionsong/) is a collection of metadata and precomputed audio features for 1 million songs. Along with this dataset, a dataset with annotations of 15 top-level genres with a single label per song was released. In our work, we combine the CD2c version of this genre datase (http://www.tagtraum.com/msd_genre_datasets.html) with a collection of album cover images. </p> <p><br> The final dataset contains 30,713 tracks from the MSD and their related album cover images, each annotated with a unique genre label among 15 classes. Based on an initial analysis on the images, we identified that this set of tracks is associated to 16,753 albums, yielding an average of 1.8 songs per album.</p> <p>We randomly divide the dataset into three parts: 70% for training, 15% for validation, and 15% for test, with no artist and album overlap across these sets. This is crucial to avoid possible overfitting, as the classifier may learn to predict the artist instead of the genre. </p> <p> </p> <p>Content:</p> <p>MSD-I dataset (mapping, metadata, annotations and links to images)<br> Data splits and feature vectors for TISMIR single-label classification experiments </p> <p>These data can be used together with the Tartarus deep learning python module https://github.com/sergiooramas/tartarus.</p> <p> </p> <p>Scientific References:</p> <p>Please cite the following paper if using MSD-I dataset or Tartarus software.</p> <p>Oramas, S., Barbieri, F., Nieto, O., and Serra, X (2018). Multimodal Deep Learning for Music Genre Classification, Transactions of the International Society for Music Information Retrieval, V(1).</p>
Multimodal optical measurement for study of lower limb tissue viability in patients with diabetes mellitus
<p>According to the International Diabetes Federation, the challenges of early stage diagnosis and treatment effectiveness monitoring in diabetes is currently one of the highest priorities in modern healthcare. In this experimental study, the potential of combined measurements of skin fluorescence and blood perfusion by the laser Doppler flowmetry method in diagnostics of low limb diabetes complications was evaluated. With the use of Monte Carlo probabilistic modelling, the diagnostic volume and depth of the diagnosis were evaluated. The experimental study involved 76 patients with type 2 diabetes mellitus. These patients were divided into two groups depending on the degree of complications. The control group consisted of 48 healthy volunteers. The local thermal stimulation was selected as a stimulus on the blood microcirculation system. Experimental studies have shown that diabetic patients have elevated values of normalised fluorescence amplitudes, as well as a lower perfusion response to local heating. In the group of people with diabetes with trophic ulcers, these parameters also significantly differ from the control and diabetes only groups. Thus, the intensity of skin fluorescence and level of tissue blood perfusion can act as markers for various degrees of complications from the beginning of diabetes to the formation of trophic ulcers.</p>
Multimodal scRNA-seq
<p>Figure depicting the breadth of multimodal scRNA-seq technologies. For a complete list of references, see https://github.com/arnavm/multimodal-scRNA-seq</p>
Toward multimodal information and AI interaction: a quasi-experiment with ChatGPT
<p>The development of argumentative text and information comprehension (CoI) skills related to the critical reconstruction of meaning (CT) is crucial in undergraduate education. Especially now in the era of social media and AI-mediated information. Generative AI aids in information creation, but its unconscious use can complicate complex information navigation. Argument maps (AM), commonly used for analyzing analog and static texts, can help visualize, understand, and rework multimodal and dynamic arguments and information.</p> <p>Stemming from the Vygotskian idea, our study used a design-based research approach on the use of AMs and ChatGPT as socio-technical artifacts to stimulate and support the understanding of information (CoI) and thus the development of critical thinking (CT). The workshop introduced the multimodal element through a 3-group quasi-experiment. The first group dealt with fully analog texts, the second group used maps with multimodal textual modes, and the third group only interacted with ChatGPT. The research focused on comparing the three groups and focusing on the two experimental groups (experimental macro-focus). </p> <p>The research had three main objectives: 1) to test whether AMs improved students' CoI enhancement and critical processing (CT); 2) to determine whether interaction with ChatGPT supported information reprocessing and critical construction of opinions and assessment tools; and 3) to determine whether interaction with ChatGPT alone, without AMs, still fostered greater integration of information and viewpoints.</p> <p>Our preliminary analysis showed that AMs improved students' CoI and CT, especially when exposed to multimodal information. ChatGPT interaction increased critical reflection and awareness of AI's role in education. Students using only ChatGPT performed well in argumentative reworking, suggesting that interaction with the chatbot can be effective. However, integrating AMs and ChatGPT could provide optimal support for comprehension and critical thinking skills.</p> <p>This Zenodo record follows the full analysis process with R (https://cran.r-project.org/bin/windows/base/ ) and Nvivo (https://lumivero.com/products/nvivo/) composed of the following datasets, script and results:</p> <p>1. Comprehension of Text and AMs Results - Arg_Map.xlsx</p> <p>2. Critical Thinking level - CriThink.xlsx</p> <p>3. Descriptive and Inferential Statistics Comprehension and Critical Thinking - Preliminary Analysis.R</p> <p>4. Elaboration and Integration Opinion - Opi_G1.xlsx; Opi_G2.xlsx & Opi_G3.xlsx</p> <p>5. Descriptive and Inferential Statistics Opinion level - Preliminary Analysis_opi.R</p> <p>6. Sentiment Analysis - Sentiment Analysis.R</p> <p>7. Vocabulary Frequent words - Vocabulary.csv</p> <p>8. Codebook qualitative Analysis with Nvivo (Codebook.xlsx)</p> <p>9. Results Nvivo Analysis G1 & G2 - Codebook-ChatGPT_G1&G2.docx</p> <p> </p> <p>Any comments or improvements are welcome!</p>
Figure 1 in Strategies for false positive reduction and multimodal lesion characterization in computer-aided diagnosis of breast cancer
Figure 1. - Representative ultrasound images at four-month post copulation (8 Sep. 2010) before resorption, five-month post copulation (20 Oct. 2010) during resorption, and six-month post copulation (3 Nov. 2010) after resorption. A: Uterine horn; B: Fetus; C: Ovary; D: Follicle.
Synthetic Lunar Terrain: A Multimodal Open Dataset for Training and Evaluating Neuromorphic Vision Algorithms
<p><strong>Synthetic Lunar Terrain (SLT) </strong>is a dataset based on a reconstruction of a typical <strong>cratered lunar surface landscape </strong>at the <a href="https://set.adelaide.edu.au/atcsr/space-research/exterres-laboratory" target="_blank" rel="noopener">EXTERRES Laboratory</a> at University of Adelaide, Roseworthy Campus. On a surface area of <strong>3.6m x 4.8m</strong>, multiple synthetic craters with different sizes and geometries were sculpted into<strong> lunar regolith simulant</strong>. A <strong>9kW metal-halide lamp</strong> illuminated the scene, providing high contrast drop-shadows from the rims of craters and similar surface features that are characteristic for the Earth's moon.</p> <p>The purpose of this dataset is to provide multimodal recordings of visual information to develop and test algorithms on a hardware analogue of the moon rather than relying on computer simulations. In particular, comparisons between <strong>neuromorphic vision sensors</strong> like <strong>event-based cameras</strong> and imaging with <strong>conventional monocular cameras</strong> are at the core of this work. For this purpose, an event-based camera (Gen4 Prophesee with Prophesee-Sony IMX636 sensor) was mounted downward-pointing next to a optical camera (Basler a2A1920-160ucPRO with Sony IMX392 sensor) on an extendable rod which was moved above the surface in a slow and continuous sweep. In total, SLT consists of camera recordings from 21 different positions/settings, with clockwise and anti-clockwise motions under varying, extreme lighting conditions.</p> <p>The event-stream and grayscale image data can be further referenced via a detailed <strong>3D point cloud</strong> obtained by a FARO Focus S70 3D Scanner. This 3D Scan was post-processed, realigned and resampled into a 3D point cloud of <strong>~6.25M points, </strong>with a surface density of <strong>1.862 p/mm²</strong>, providing a ground-truth for the crater geometries.</p> <p>In detail, SLT contains the following:</p> <ul> <li>eventbased.zip: <ul> <li><strong>42 camera orbits</strong> in the binary <strong>EVT 3.0</strong> format (<a href="https://docs.prophesee.ai/stable/data/encoding_formats/evt3.html" target="_blank" rel="noopener">Prophesee docs</a>) </li> <li>corresponding <strong>.mp4 </strong>event-frame video rendering for visualization purposes (33.333ms accumulation time at 30FPS)</li> <li>corresponding<strong> .bias</strong> file containing settings used during recording</li> </ul> </li> <li>code.zip: <ul> <li>Standalone C++ code of the <strong>metavision EVT3-to-RAW file decoder</strong>, allowing to convert the binary EVT 3.0 format into a plaintext <strong>.csv </strong>that includes <ul> <li>the coordinates of the event-pixel,</li> <li>the polarity change,</li> <li>and the time-stamp of the event.</li> </ul> </li> <li>This code is an unmodified redistribution from the <a href="https://www.prophesee.ai/metavision-intelligence/" target="_blank" rel="noopener">Metavision SDK</a>, version 4.6.0, released by Prophesee under Apache License 2.0.</li> </ul> </li> <li> optical.zip: <ul> <li><strong>42 image sequences</strong> in <strong>.tif</strong> format (LZW, 1920x1200px, 8bit, grayscale) <ul> <li>Length of image sequences varies between about 300 to 700 images per sequence</li> </ul> </li> </ul> </li> <li>3d_scan.zip: <ul> <li><strong>SLT3d_scan.ply:</strong> 3D point cloud of the scene Stanford Polygon File Format</li> <li><strong>SLT3d_scan.xyz:</strong> 3D point cloud with plaintext x y z coordinates, white-space separated</li> </ul> </li> <li>cratermap.png: <ul> <li>Annotations of <strong>130 different surface features</strong> that have been manually identified as crater-like with approximate x,y-coordinates.</li> </ul> </li> <li>positionmap.png: <ul> <li>Illustration of the different positions from which the rod was moved over the scene (not to scale).</li> </ul> </li> <li>sample.zip: <ul> <li>A sample containing 1 event-camera orbit with the corresponding image sequence (for convenience only, to test the dataset without the need to download it's entirety)</li> </ul> </li> </ul> <p>The global coordinate frame of this dataset puts the origin at the centre of the scene. The shorter side of the terrain is roughly aligned with the x-axis, the longer side with the y-axis. The z-axis represents height/depth (compare with <strong>cratermap.png</strong>). The different conditions (compare with <strong>positionmap.png</strong>) from which the data was taken are encoded as follows:</p> <ul> <li><strong>A1, ..., A9</strong> refer to the left side of the scene (negative x)</li> <li><strong>B1, ..., B9 </strong>refer to the right side of the scene (positive x)</li> <li><strong>S1, S2, S3</strong> and <strong>S4 </strong>describe special lighting conditions and/or parameter settings</li> <li><strong>CW </strong>refers to a "clockwise" sweeping of the camera-rod, relative to the position</li> <li><strong>ACW</strong> refers to an "anti-clockwise" sweeping of the camera-rod, relative to the position</li> </ul> <p>The light from the metal-halide lamp was directed through a small opening, shining along the positive y-axis. In some of the setups, an obstacle was placed between the surface and the opening, blocking out part of the light to create a light-dark separator on the surface, emulating the <strong>terminator</strong> on the Moon between it's day and night side, resulting in highly contrastive images.</p> <p>We encourage you to consult and cite our related publication, should you find SLT useful.</p> <ul> <li>Märtens, M., Farries, K., Culton, J. and Chin, TJ. "<strong>Synthetic Lunar Terrain: A Multimodal Open Dataset for Training and Evaluating Neuromorphic Vision Algorithms</strong>", Proceedings of "<em>International Symposium on Artificial Intelligence, Robotics and Automation in Space (I-SAIRAS), 2024</em>", pp. 609-614</li> </ul> <p> </p>
Dataset related to article "Distribution of pamiparib, a novel inhibitor of poly(ADP-ribose)-polymerase (PARP), in tumor tissue analyzed by multimodal imaging"
<p>This record contains data related to article "Distribution of pamiparib, a novel inhibitor of poly(ADP-ribose)-polymerase (PARP), in tumor tissue analyzed by multimodal imaging"</p> <p><span>Pamiparib is a potent and selective oral PARP1/2 inhibitor (PARPi). Pamiparib has good bioavailability and showed greater cytotoxic potency and similar DNA-trapping capacity compared to olaparib. It is not affected by ATP-binding cassette transporters. Consequently, pamiparib may be useful in overcoming drug resistance caused by poor drug distribution in tumor due to overexpression of these efflux pump [1]. Mass spectrometry imaging (MSI) is a powerful technology that allows to study drugs distribution in tissues while maintaining spatial information [2]. Here, MSI was applied to visualize pamiparib in tumor in combination with spatial metabolomics and lipidomics, LC-MS/MS analysis, immunofluorescence analysis, and histological staining to gain a comprehensive understanding of how pamiparib is distributed. The results show that pamiparib was evenly distributed in ovarian tumor models, including those that overexpress P-glycoprotein (P-gp). In contrast, olaparib was not detected by MSI in any of the analyzed tumors, despite the comparable sensitivity of the analytical method. This difference in tumor distribution was confirmed by LC-MS/MS analysis. </span></p>
MultiFranceFences: A novel deep learning dataset for automated fence detection from multimodal aerial imagery
<p>The <strong>MultiFranceFences</strong> dataset is a large-scale, multimodal remote sensing benchmark for the semantic segmentation of fences across various landscapes in France. This dataset integrates high-resolution orthophotographs (RGB through BDOrtho) and Digital Surface Models (DSM) derived from LiDARHD data. </p> <p>MultiFranceFences is suitable for deep learning models in semantic segmentation, including state-of-the-art models like UNet, D-LinkNet, and the newly proposed H-IncepUNet, which integrates handcrafted features and multi-scale feature extraction modules for enhanced fence detection.</p> <p><strong>Dataset features:</strong></p> <ul> <li><strong>Multimodal imagery</strong>: Combines orthophotographs and DSM data from LiDARHD for fences semantic segmentation (folders <em>ortho</em> and <em>lidar</em>).</li> <li><strong>Buffer options</strong>: 2-meter and 3-meter buffer fence annotations to fit varying detection requirements (folders <em>fences_2m</em> and <em>fences_3m</em>).</li> <li><strong>Diverse landscapes</strong>: Covers rural, and natural environments across France.</li> <li><strong>Validated dataset</strong>: Manually cleaned and validated to remove erroneous fence labels under tree canopies or areas with limited visibility.</li> </ul> <p>Each patch is named according to the nomenclature of the original BDOrtho tile, followed by the specific x and y coordinates of the patch within that tile.</p>
ProtNote: a multimodal method for protein-function annotation
<div> <div>Understanding protein sequence-function relationships is essential for advancing protein biology and engineering. However, fewer than 1% of known protein sequences have human-verified functions, and scientists continually update the set of possible functions. While deep learning methods have demonstrated promise for protein function prediction, current models are limited to predicting only those functions on which they were trained. Here, we introduce ProtNote, a multimodal deep learning model that leverages free-form text to enable both supervised and zero-shot protein function prediction. ProtNote not only maintains near state-of-the-art performance for annotations in its train set, but also generalizes to unseen and novel functions in zero-shot test settings. We envision that ProtNote will enhance protein function discovery by enabling scientists to use free text inputs, without restriction to predefined labels – a necessary capability for navigating the dynamic landscape of protein biology.</div> </div>
Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections
<p>A pre-trained model of the paper "Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections," CoRL 2020.</p>
A niching particle swarm optimization strategy combined with cluster analysis for the multimodal inversion of surface waves
<p>The data include two study cases used for multimodal surface wave inversion.</p> <p>For case 1, the data present a combination of active and passive surface wave methods.</p> <p>For case 3, we use Rayleigh waves to detect a low-velocity soft interlayer underneath the road.</p> <p>Detailed description can be found in the data description document.</p>
Multimodal Identity Preserved Tracking (MIPT) Dataset
<p>Human behavioral analysis applications in the fields of ambient assisted living (AAL) and human security monitoring require continuous video analysis of individuals. Although intelligent systems deployed in these areas are intended to have a positive impact on the persons involved, subsequent continuous monitoring naturally raises ethical concerns and questions about privacy implications. To address these issues, we present a foundation for identity-preserving 3D human behavior analysis. The dataset is large, at a total of ~85k annotated frames. To reduce privacy intrusion, it consists entirely of spatio-temporally aligned depth and thermal sequences. Annotation is provided as 3D bounding boxes, along with pose labels and consistent person IDs for use in tracking. The dataset is designed to be flexible. Data representation in either image view or point clouds and the option for projected 2D bounding boxes, allows use in a variety of 2D or 3D tasks. Target applications of our work are privacy-sensitive domains that currently require continuous monitoring using RGB-based systems, including ambient assisted living tasks (e.g., motion rehabilitation, fall detection, vital sign detection) and human security monitoring applications, such as construction safety, critical care and correctional facility monitoring.</p> <p>This database may be used for non-commercial research purpose only. If you publish material based on this database, we request that you include a reference to our paper [1].</p> <p>[1] T. Heitzinger and M. Kampel “<em>A Foundation for 3D Human Behavior Detection in Privacy-Sensitive Domains</em>”,<br> in <em>32</em><em>nd</em><em> British Machine Vision Conference (BMVC)</em>, 2021</p>
Datasets for "MGTCOM: Community Detection in Multimodal Graphs"
<p>These are the datasets used in <em><strong>"MGTCOM: Community Detection in Multimodal Graphs"</strong></em></p> <p>The dataset preparation code can be found in <a href="https://github.com/EgorDm/MGTCOM">our repository</a>.</p> <p>Each dataset consists of a heterogenous graph with additional edge or node timestamps and preprocessed feature vectors.</p> <p>For each dataset, the files are split into raw and processed folders.<br> * `<em>raw</em>` folder: contains a set of parquet files with formatted raw dataset data. Files follow the naming convention `node_<name>` or `edge_<from>_<rel_name>_<to>`.<br> * `<em>processed</em>` folder: contains preprocessed datasets in <a href="https://pytorch-geometric.readthedocs.io/en/latest/">pytorch geometric</a> graph data format</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.