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.
1,433
datasets available to search
ShareScore release 0.9.0
Dataset results
1,433 results for “masks”
TransProteus, Predicting 3D shapes, masks, and properties of materials, liquids, and objects inside transparent containers from images
<p>We present TransProteus, a dataset, for predicting the 3D structure and properties of materials, liquids, and objects inside transparent vessels from a single image without prior knowledge of the image source and camera parameters. Manipulating materials in transparent containers is essential in many fields and depends heavily on vision. This work supplies a new procedurally generated dataset consisting of 50k images of liquids and solid objects inside transparent containers. The image annotations include 3D models and material properties (color/transparency/roughness...) for the vessel and its content. The synthetic (CGI) part of the dataset was procedurally generated using 13k different objects, 500 different environments (HDRI), and 1450 material textures (PBR) combined with simulated liquids and procedurally generated vessels. In addition, we supply 104 real-world images of objects inside transparent vessels with depth maps of both the vessel and its content.</p> <p>Note that there are two files here:</p> <p><a href="https://zenodo.org/api/files/12b013ca-36be-4156-afd4-c93b5fa22093/Tansproteus_SimulatedLiquids2_New_No_Shift.7z">Transproteus_SimulatedLiquids2_New_No_Shift.7z</a></p> <p>and</p> <p><br> <a href="https://zenodo.org/api/files/2b833de0-4007-4682-ad5b-5e08bd63597e/TranProteus2.7z?versionId=f16e7126-8750-41f7-99e6-d35ca60399cc">TranProteus2.7z </a>, contain subset of the virtual CGI data set.</p> <p>https://zenodo.org/api/files/12b013ca-36be-4156-afd4-c93b5fa22093/Tansproteus_SimulatedLiquids2_New_No_Shift.7z</p> <p><a href="https://zenodo.org/api/files/2b833de0-4007-4682-ad5b-5e08bd63597e/TransProteus_RealSense_RealPhotos.7z">TransProteus_RealSense_RealPhotos.7z </a>: Contain real-world photos scanned with real sense with depth map of both the vessel and its content</p> <p>See ReadMe file in side the downloaded files for more details</p> <p>The full dataset (>100gb) can be found here:</p> <p><a href="https://e.pcloud.link/publink/show?code=kZfx55Zx1GOrl4aUwXDrifAHUPSt7QUAIfV">https://e.pcloud.link/publink/show?code=kZfx55Zx1GOrl4aUwXDrifAHUPSt7QUAIfV</a></p> <p>https://<a href="http://icedrive.net/1/6cZbP5dkNG">icedrive.net/1/6cZbP5dkNG</a></p> <p>See: <a href="https://arxiv.org/pdf/2109.07577.pdf"> https://arxiv.org/pdf/2109.07577.pdf</a> for more details</p> <p><strong><a href="https://zenodo.org/record/4736111#.YVOAx3tE1H4">**This dataset is complementary to LabPics dataset with 8k real images of materials in vessels in chemistry labs, medical labs, and other settings. The LabPics dataset can be downloaded from here:</a></strong></p> <p><strong><a href="https://zenodo.org/record/4736111#.YVOAx3tE1H4">https://zenodo.org/record/4736111#.YVOAx3tE1H4</a></strong></p> <p> </p> <p><strong>************************************************************************************</strong></p> <p><a href="https://zenodo.org/api/files/12b013ca-36be-4156-afd4-c93b5fa22093/Tansproteus_SimulatedLiquids2_New_No_Shift.7z">Transproteus_SimulatedLiquids2_New_No_Shift.7z </a>and <a href="https://zenodo.org/api/files/2b833de0-4007-4682-ad5b-5e08bd63597e/TranProteus2.7z?versionId=f16e7126-8750-41f7-99e6-d35ca60399cc">TranProteus2.7z</a></p> <p>The two folders contain relatively similar data styles.<br> The data in No_Shift contain images that were generated with no camera shift in the camera paramters. If you try to predict 3d model from an image as a depth map, this is easier to use (Otherwise, you need to adapt the image using the shift). For all other purposes, both folders are the same, and you can use either or both. In addition, a real image dataset for testing is given in the RealSense file.</p> <p> </p> <p> </p> <p> </p>
NII Face Mask Dataset
<p>=====================================================================<br> # NII Face Mask Dataset v1.0<br> =====================================================================</p> <p>Authors:<br> Trung-Nghia Le (1), Khanh-Duy Nguyen (2), Huy H. Nguyen (1), Junichi Yamagishi (1), Isao Echizen (1)</p> <p>Affiliations:<br> (1)National Institute of Informatics, Japan <br> (2)University of Information Technology-VNUHCM, Vietnam</p> <p>National Institute of Informatics <br> Copyright (c) 2021</p> <p>Emails:<br> {ltnghia, nhhuy, jyamagis, iechizen}@nii.ac.jp, {khanhd}@uit.edu.vn</p> <p>Arxiv: https://arxiv.org/abs/2111.12888<br> NII Face Mask Dataset v1.0: https://zenodo.org/record/5761725</p> <p>=============================== INTRODUCTION ===============================</p> <p>The NII Face Mask Dataset is the first large-scale dataset targeting mask-wearing ratio estimation in street cameras. This dataset contains 581,108 face annotations extracted from 18,088 video frames (1920x1080 pixels) in 17 street-view videos obtained from the Rambalac's YouTube channel.</p> <p>- https://www.youtube.com/c/Rambalac</p> <p>The videos were taken in multiple places, at various times, before and during the COVID-19 pandemic. The total length of the videos is approximately 56 hours.</p> <p><br> =============================== REFERENCES ===============================</p> <p>If your publish using any of the data in this dataset please cite the following papers:</p> <p>#Pre-print version<br> @article{Nguyen202112888,<br> title={Effectiveness of Detection-based and Regression-based Approaches for Estimating Mask-Wearing Ratio},<br> author={Nguyen, Khanh-Duy and Nguyen, Huy H and Le, Trung-Nghia and Yamagishi, Junichi and Echizen, Isao},<br> archivePrefix={arXiv},<br> arxivId={2111.12888},<br> url={https://arxiv.org/abs/2111.12888},<br> year={2021}<br> }</p> <p>#Final version<br> @INPROCEEDINGS{Nguyen2021EstMaskWearing,<br> author={Nguyen, Khanh-Duv and Nguyen, Huv H. and Le, Trung-Nghia and Yamagishi, Junichi and Echizen, Isao},<br> booktitle={2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)}, <br> title={Effectiveness of Detection-based and Regression-based Approaches for Estimating Mask-Wearing Ratio}, <br> year={2021},<br> pages={1-8},<br> url={https://ieeexplore.ieee.org/document/9667046},<br> doi={10.1109/FG52635.2021.9667046}}</p> <p><br> ======================== DATA STRUCTURE ==================================</p> <p><br> 1. Directory Structure<br> -------------------------------</p> <p>./NFM<br> ├── dataset<br> │ ├── train.csv: annotations for the train set.<br> │ ├── test.csv: annotations for the test set.<br> └── README_v1.0.md</p> <p><br> 2. Description for each files in detail.<br> ---------------------------------------------------------</p> <p>We use the same structure for two CSV files (train.csv and test.csv). Both CSV files have the same columns:<br> <1st column>: video_id (a source video can be found by following the link: https://www.youtube.com/watch?v=<video_id>)<br> <2nd column>: frame_id (the index of a frame extracted from the source video)<br> <3rd column>: timestamp in milisecond (the timestamp of a frame extracted from the source video)<br> <4th column>: label (for each annotated face, one of three labels was attached with a bounding box: 'Mask'/'No-Mask'/'Unknown')<br> <5th column>: left<br> <6th column>: top<br> <7th column>: right<br> <8th column>: bottom<br> Four coordinates (left, top, right, bottom) were used to denote a face's bounding box. </p> <p><br> ============================== COPYING ================================</p> <p>This repository is made available under Creative Commons Attribution License (CC-BY). </p> <p>Regarding Creative Commons License: Attribution 4.0 International (CC BY 4.0), <br> please see https://creativecommons.org/licenses/by/4.0/</p> <p>THIS DATABASE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND <br> ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED <br> WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. <br> IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, <br> INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, <br> BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, <br> OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, <br> WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) <br> ARISING IN ANY WAY OUT OF THE USE OF THIS DATABASE, EVEN IF ADVISED OF THE <br> POSSIBILITY OF SUCH DAMAGE</p> <p><br> ====================== ACKNOWLEDGEMENTS ================================</p> <p>This research was partly supported by JSPS KAKENHI Grants (JP16H06302, JP18H04120, JP21H04907, JP20K23355, JP21K18023), and JST CREST Grants (JPMJCR20D3, JPMJCR18A6), Japan.</p> <p>This dataset is based on the Rambalac's YouTube channel: https://www.youtube.com/c/Rambalac<br> </p>
Jewelry segmentation masks for the 11k Hands dataset
<p>We provide an additional set of segmentation masks for jewelry in the 11K Hands dataset [1]. We filtered out a total of 3179 hands <br> with jewelry and were manually annotated using CVAT. For ease of use, the maks have the same size and filename as the original images and are exported in png format. The pixel value represents whether jewelry exists, being 0 background and 1 jewelry.</p> <p>The 11k Hands [1] dataset is a collection of 11,076 hand photos (1600 × 1200 pixels) from 190 people aged 18 to 75 years old. Each hand was shot from both the dorsal and palmar sides, on a uniform white background, at roughly the same distance from the camera. Each image has a metadata record that includes the following information: the subject ID, gender, age, skin color, and a set of information about the captured hand, such as right- or left-hand, hand side (dorsal or palmar), and logical indicators indicating whether the hand image contains accessories, nail polish, or irregularities. You can download <a href="https://drive.google.com/open?id=1KcMYcNJgtK1zZvfl_9sTqnyBUTri2aP2">here</a> the original 11K Hands dataset and the <a href="https://drive.google.com/file/d/1RC86-rVOR8c93XAfM9b9R45L7C2B0FdA/view?usp=sharing">metadata</a>.</p> <p>In the future, we will add our paper if accepted. In the meantime, if you use the masks provided on this webpage, please cite our DOI: <em>10.5281/zenodo.6541286</em> and the original 11K Hands paper.</p> <p>[1] Mahmoud Afifi, "11K Hands: Gender recognition and biometric identification using a large dataset of hand images." Multimedia Tools and Applications, 2019.</p>
YOGData: Labelled data (YOLO and Mask R-CNN) for yogurt cup identification within production lines
<p><strong>D</strong><strong>ata abstract:</strong><br> The YogDATA dataset contains images from an industrial laboratory production line when it is functioned to quality yogurts. The case-study for the recognition of yogurt cups requires training of Mask R-CNN and YOLO v5.0 models with a set of corresponding images. Thus, it is important to collect the corresponding images to train and evaluate the class. Specifically, the YogDATA dataset includes the same labeled data for Mask R-CNN (coco format) and YOLO models. For the YOLO architecture, training and validation datsets include sets of images in jpg format and their annotations in txt file format. For the Mask R-CNN architecture, the annotation of the same sets of images are included in json file format (80% of images and annotations of each subset are in training set and 20% of images of each subset are in test set.) <br> </p> <p><strong>Paper abstract:</strong><br> The explosion of the digitisation of the traditional industrial processes and procedures is consolidating a positive impact on modern society by offering a critical contribution to its economic development. In particular, the dairy sector consists of various processes, which are very demanding and thorough. It is crucial to leverage modern automation tools and through-engineering solutions to increase their efficiency and continuously meet challenging standards. Towards this end, in this work, an intelligent algorithm based on machine vision and artificial intelligence, which identifies dairy products within production lines, is presented. Furthermore, in order to train and validate the model, the YogDATA dataset was created that includes yogurt cups within a production line. Specifically, we evaluate two deep learning models (Mask R-CNN and YOLO v5.0) to recognise and detect each yogurt cup in a production line, in order to automate the packaging processes of the products. According to our results, the performance precision of the two models is similar, estimating its at 99\%. </p> <p> </p>
Molecular evidence for introgressive hybridization in New Zealand masked gulls
<p>Genetic data and codes to reproduce the analyses from the manuscript :<br> <br> Given, A. D., Mills, J. A., Momigliano, P., & Baker, A. J. (2022). Molecular evidence for introgressive hybridization in New Zealand masked gulls. <em>Ibis</em>. https://doi.org/10.1111/ibi.13117</p> <p>The data and codes are in two zipped folders</p> <ol> <li>FSC.zip</li> <li>PopGen.zip</li> </ol> <p>The FSC.zip folder contains data and scripts to reproduce the fastsimcoal simulations and to calculate summary statistics from observed and simulated data. It also includes the results from these analyses and an R script to run ABC model selection via random forest. </p> <p>The PopGen.zip folder contains the microsatellite dataset in both <em>genepop</em> (RB-BB.gen)<em> </em>and <em>structure </em>(RB-BB.str) formats , the results from STRUCTURE analyses (folder RB-BB_STRUCT), and an R script (Popgen_analyses.r) to reproduce population genetic analyses (PCA and summary statistics: <em>F</em><sub>ST</sub>, and estimate HWE, <em>H</em><sub>O</sub> and <em>H</em><sub>E</sub>) and plots. </p>
VENuS cloud mask training dataset
<p>Training dataset for cloud masking for VENμS satellite images. Samples are pixel-wise labelled scenes over the land of Israel, with a special focus on the southern, arid area.</p> <p> </p> <p>Contains three classes:</p> <p>* 0: Cloud-less pixels<br> * 1: Thick clouds<br> * 2: Thin clouds</p>
Training data for 'Repeat masking with RepeatMasker' tutorial (Galaxy Training Material)
<p>Data needed for the 'Repeat masking with RepeatMasker' tutorial (Galaxy Training Material).</p> <p>The assembly was generated following the 'Genome assembly using PacBio data' tutorial</p>
KappaSet: Sentinel-2 KappaZeta Cloud and Cloud Shadow Masks
<p><strong>General information</strong></p> <p>The dataset consists of 9251 labelled sub-tiles from 1038 Sentinel-2 (S2) Level-1C (L1C) products distributed over the globe. In terms of seasonal distribution, S2 products can be divided into the following groups:</p> <ul> <li> <p>Winter products: 29 austral and 142 boreal S2 products</p> </li> <li> <p>Sprint products: 45 austral and 257 boreal S2 products</p> </li> <li> <p>Summer products: 30 austral and 293 boreal S2 products</p> </li> <li> <p>Autumn products: 29 austral and 213 boreal S2 products</p> </li> </ul> <p>Each S2 product was oversampled at 10 m resolution for 512 x 512 pixels sub-tiles. From each S2 product, the most challenging ~5 sub-tiles per product were selected for labelling. Each selected L1C S2 product represents different clouds, such as cumulus, stratus, or cirrus, which are spread over various geographical locations around the world. The classification pixel-wise map consists of the following categories:</p> <ul> <li> <p>0 – UNDEFINED: pixels that the labeler is not sure which class they belong to;</p> </li> <li> <p>1 – CLEAR: pixels without clouds or cloud shadows;</p> </li> <li> <p>2 – CLOUD SHADOW: pixels with cloud shadows;</p> </li> <li> <p>3 – SEMI TRANSPARENT CLOUD: pixels with thin clouds through which the land is visible; include cirrus clouds that are on the high cloud level (5-15km).</p> </li> <li> <p>4 – CLOUD: pixels with cloud; include stratus and cumulus clouds that are on the low cloud level (from 0-0.2km to 2km).</p> </li> <li> <p>5 – MISSING: missing or invalid pixels.</p> </li> </ul> <p>The dataset was labelled using Computer Vision Annotation Tool (CVAT) and Segments.ai. With the possibility of integrating an active learning process in Segments.ai, the labelling was performed semi-automatically. The distribution of the dataset is presented in the Figure below. Color represents the season from which the product was chosen.</p> <p>The dataset limitations must be considered: the data mostly covers terrestrial regions (around 91%) and includes some water areas (around 9%); only around 7% of the dataset contains snow. Current sub-tiles do not have georeferencing. </p> <p><strong>Contributions and Acknowledgements</strong></p> <p>The data were annotated by Olga Wold, Mariana Rohtsalu, Nikita Murin, Joosep Truupõld and Fariha Harun. The data verification and Software Development were performed by Indrek Sünter, Heido Trofimov, Anton Kostiukhin, Marharyta Domnich, Mihkel Järveoja, Olga Wold and Tetiana Shtym. The methodology was developed by Kaupo Voormansik, Indrek Sünter, Marharyta Domnich and Tetiana Shtym.</p> <p>The data were collected, processed, and checked as a part of “KappaMask: AI-based Cloudmask Processor for Sentinel-2” project. We thank Segments.ai team for providing a wonderful annotation tool that was actively used to prepare the dataset. In the end, we thank European Space Agency (ESA) for supporting, advising, and funding the project.</p> <p>The project was funded by <em><strong>European Space Agency,</strong></em> Contract No. 4000132124/20/I-DT.</p>
GEOGLAM Best Available Crop Type Masks
<p>Best Available Crop Specific masks (BACS) over the major production and export countries for wheat, maize, rice, and soybeans, in the context of the G20 Global Agriculture Monitoring Program, GEOGLAM. The countries covered by GEOGLAM-BACS account for a total of 84% of soy, 54% of maize, 62% of wheat, and 92% of rice production globally.</p>
Segmentation masks of ZooScan images focusing on images with several objects separated by a human operator
<p>All information is available from the original publication page: https://doi.org/10.17882/99663</p>
bacteria_masking:v21.1.1 complementary file (fasta)
<p>This archive contains the 42216 fasta files used to build the kraken database here : https://zenodo.org/records/11518607</p> <p>This is 24Gb large and could not be added in the original record.</p>
Figure 1 in First record of River Warbler Locustella fluviatilis and additional records for Plain Nightjar Caprimulgus inornatus and Lesser Masked Weaver Ploceus intermedius in Djibouti
Figure 1. Male Lesser Masked Weaver Ploceus intermedius, Camp Lemonnier, Djibouti, 5 February 2016, in the late stages of definitive moult showing orange-chestnut hindcrown feathers and diagnostic creamy-white eye (Carla J. Dove)
covid_masking:v1
<p>This is a Kraken2 database containing only the SARS-cov2 genome reference with accession number MN908947.3.</p> <p>This was built with the masking option and default parameter.</p>
FIGURE 2 in First record of a breeding colony of Masked Booby (Sula dactylatra Lesson, 1831; Sulidae) in the main island of the archipelago of Fernando de Noronha (Pernambuco, Brazil)
FIGURE 2: Map of Fernando de Noronha Archipelago, highlighting the location of the breeding colony of Sula dactylatra, located at the end of the Capim-açu trail (03°52'49.38"S; 32°27'29.47"W). Unscaled. Source: © 2016 google maps.
FIGURE 1 in First record of a breeding colony of Masked Booby (Sula dactylatra Lesson, 1831; Sulidae) in the main island of the archipelago of Fernando de Noronha (Pernambuco, Brazil)
FIGURE 1: Breeding colony of Sula dactylatra located at the end of the Capim-açu trail, main island of Fernando de Noronha archipelago, September 2015. Photo: Deborah Gutierrez, 2015.
Gaia data, Pan-STARRS photometry, and stream selection masks for the region around the GD-1 stream
<p>This file contains:</p> <ul> <li>relevant columns from Gaia DR2</li> <li>Pan-STARRS (PS1) photometry (grizy)</li> <li>de-reddened PS1 photometry (g0, r0, etc.)</li> <li>binary masks to apply to select out stars that pass our proper motion and color-magnitude diagram selection (pm_mask, gi_cmd_mask)</li> <li>a binary mask to apply to select out stars in the stream track defined in <a href="https://arxiv.org/abs/1805.00425">Price-Whelan & Bonaca (2018) </a>(stream_track_mask)</li> <li>GD-1 positional coordinates (phi1, phi2)</li> <li>Proper motions in the GD-1 coordinate system (pm_phi1_cosphi2, pm_phi2)</li> <li>Proper motions in the GD-1 coordinate system, corrected for solar reflex motion (pm_phi1_cosphi2_no_reflex, pm_phi2_no_reflex)</li> </ul> <p>To select out probable members of the GD-1 stream in, e.g., Python, use:</p> <pre><code class="language-python">from astropy.table import Table tbl = Table.read('gd1-with-masks.fits') tbl = tbl[tbl['pm_mask'] & tbl['gi_cmd_mask']]</code></pre> <p>To select out only stars within the stream track identified in <a href="https://arxiv.org/abs/1805.00425">Price-Whelan & Bonaca (2018)</a>, do:</p> <pre><code class="language-python">from astropy.table import Table tbl = Table.read('gd1-with-masks.fits') tbl = tbl[tbl['pm_mask'] & tbl['gi_cmd_mask'] & tbl['stream_track_mask']</code></pre> <pre> </pre>
Repeat-masked <i>Strix occidentalis caurina</i> nuclear genome version 1.0 and complete mitochondrial genome
<p><strong>StrOccCau_1.0_nuc_finalMito_RepeatMasked.fa.bz2</strong> : This file is homology-based and <em>de novo</em> model-based repeat-masking of the reference <em>Strix occidentalis caurina</em> genome StrOccCau_1.0_nuc.fa from Hanna et al., 2017a,b) with the mitochondrial genome from Hanna et al. (2017c).</p> <p><strong>StrOccCau_1.0_nuc_finalMito_RepeatMasked.bed.bgz</strong> : This is a file in Browser Extensible Data (BED) format that provides the genomic intervals of the N-regions in the above masked assembly. The N-regions include hard-masked low complexity and repeat regions as well as N-regions that were gaps in the original assembly. I compressed the file using the bgzip tool from HTSlib version 1.7 (Davies et al. 2018).</p> <p>See full details of the creation of these files in section 2.1 of the materials and methods at protocols.io (http://dx.doi.org/10.17504/protocols.io.rmrd456).</p> <p>If you use these data, please cite the following:</p> <p>Hanna ZR. 2018. Repeat-masked <em>Strix occidentalis caurina</em> nuclear genome version 1.0 and complete mitochondrial genome. Version 1.0.0. <em>Zenodo.</em></p> <p> </p> <p><strong>References</strong></p> <p>Davies R, Randall JC, McCarthy SA, Bonfield J, Pollard MO, Marshall J, et al. 2018. HTSlib. Version 1.7. [Accessed 2018 Mar 19]. Available from: https://github.com/samtools/htslib</p> <p>Hanna ZR, Henderson JB, Wall JD, Emerling CA, Fuchs J, Runckel C, et al. 2017a. Northern Spotted Owl (<em>Strix occidentalis caurina</em>) Genome: Divergence with the Barred Owl (<em>Strix varia</em>) and Characterization of Light-Associated Genes. Genome Biology and Evolution. 9: 2522–2545. DOI: 10.1093/gbe/evx158</p> <p>Hanna ZR, Henderson JB, Wall JD, Emerling CA, Fuchs J, Runckel C, et al. 2017b. Supplemental dataset for Northern Spotted Owl (<em>Strix occidentalis caurina</em>) genome assembly version 1.0. <em>Zenodo</em>. DOI: 10.5281/zenodo.822859</p> <p>Hanna ZR, Henderson JB, Sellas AB, Fuchs J, Bowie RCK, Dumbacher JP. 2017c. Complete mitochondrial genome sequences of the northern spotted owl (<em>Strix occidentalis caurina</em>) and the barred owl (<em>Strix varia</em>; Aves: Strigiformes: Strigidae) confirm the presence of a duplicated control region. <em>PeerJ</em>. 5: e3901. DOI: 10.7717/peerj.3901</p> <p> </p>
Raw data: Supra-threshold perception and neural representation of tones presented in noise in conditions of masking release
<p>Raw data of three experiments:</p> <p>1) Exp1: Psychoacoustical masked thresholds of tone in noise masker (ASCII format)</p> <p>2) Exp2: 64ch EEG data (Biosemi data format .bdf)</p> <p>3) Exp3: Salience rating of a tone masked by various maskers and levels above masked threshold. (ASCII format)</p> <p>Preprint with details on experiments submitted to BioRxiv: https://doi.org/10.1101/575720</p>
Mask R-CNN on NYUv2
<p><strong>Mask R-CNN on NYUv2</strong></p> <p>This repository mainly contains information from the execution of the <a href="https://github.com/facebookresearch/maskrcnn-benchmark">Mask R-CNN network </a>[1] on images from the <a href="https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html">NYUv2 dataset</a> [2] as well as additional metadata. It was created for analyzing the output of Mask R-CNN and post-processing it using contextual information for improving its performance. This work has been carried out by <a href="http://mapir.isa.uma.es/jotaraul">Dr. Jose-Raul Ruiz-Sarmiento</a> (MAPIR group, University of Málaga) and <a href="https://lishuda.wordpress.com/">Dr. Shuda Li</a> (AVG group, University of Oxford) in the scope of the European project<a href="http://www.movecare-project.eu/"> MoveCare: Multiple-actOrs Virtual Empathic CARgiver for the Elder</a> (Ref: 732158).</p> <p>Concretely, <strong>this repository includes</strong>:</p> <p>- metadata:<br> + coco_nyu_mapping.txt: Mapping between the categories in COCO dataset and those in NYUv2.<br> + coco_object_categories.txt: Object categories considered in COCO dataset.<br> + nyu_object_categories.txt: Object categories used in NYUv2 dataset.<br> + nyu_scene_categories.txt: Scene categories considered in NYUv2.<br> + objects_and_categories_in_images.txt: For each image in NYUv2, the categories of the appearing objects.</p> <p>- nyu_content:<br> + masks_in_X (Where X is the image index)<br> - Y.png: Where Y is the object index in the image, represents the binary mask of that object.<br> - pixels_labelled.png: Binary mask indicating the labelled pixels in image X.<br> + bboxesX.txt: Where X is the image index, includes the ground truth bounding boxes of the objects in it. Format is: min_x min_y max_x max_y.</p> <p>- preds:<br> + X: Where X is the image index.<br> - Y.png: Where Y is the object index in the image, as detected by Mask R-CNN. Binary image containing the mask of such detected object.<br> + X.txt: Where X is the image index. File containing the objects detected by Mask R-CNN, including: idx class score min_x min_y max_x max_y masks_file, being min_x min_y max_x and max_y bounding box information, while masks_file refers to X/Y.png as described above.<br> + result_X.png: Where X is the image index. Image showing the detections with a socre higher than 0.3.<br> + gt_iou_X: Where X is the image index.<br> - Y: Where Y is the index of the detected object.<br> + Z.png Where Z is the index of the object in the ground truth. Image showing the masks of both objects, Y and Z, for visually checking their overlapping.<br> - Y.txt: Where Y is the index of the detected object. File containing:<br> + The intersection ratio of the object mask Y with the labelled part of the image.<br> + The IoU value for the mask of object Y and those of ground truth objects.<br> <br> <br> <strong>References:</strong></p> <p>[1] He, Kaiming, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. "Mask r-cnn." In Proceedings of the IEEE international conference on computer vision, pp. 2961-2969. 2017.<br> [2] Silberman, Nathan, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. "Indoor segmentation and support inference from rgbd images." In European Conference on Computer Vision, pp. 746-760. Springer, Berlin, Heidelberg, 2012.</p>
Figure 3 in Biology and management of the masked chafer Cyclocephala disticcta Burmeister &Melolonthidae, Dynastinae, Cyclocephalini)
Figure 3. Adult Cyclocephala disticcta bred in captivity. A, Newly hatched male; B, Male one day after hatching; C, Liquid*releasing behavior. Adult mean size: 10 mm.
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.