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.
52
datasets available to search
ShareScore release 0.9.0
Dataset results
52 results for “LVIS”
COCO, LVIS, Open Images V4 classes mapping
<p>This repository contains a mapping between the classes of COCO, LVIS, and Open Images V4 datasets into a unique set of 1460 classes.</p> <p>COCO [Lin et al 2014] contains 80 classes, LVIS [gupta2019lvis] contains 1460 classes, Open Images V4 [Kuznetsova et al. 2020] contains 601 classes.</p> <p>We built a mapping of these classes using a semi-automatic procedure in order to have a unique final list of 1460 classes. We also generated a hierarchy for each class, using <a href="https://wordnet.princeton.edu/">wordnet</a></p> <p>This repository contains the following files:</p> <ul> <li><em>coco_classes_map.txt</em>, contains the mapping for the 80 coco classes</li> <li><em>lvis_classes_map.txt</em>, contains the mapping for the 1460 coco classes</li> <li><em>openimages_classes_map.txt</em>, contains the mapping for the 601 coco classes</li> <li><em>classname_hyperset_definition.csv</em>, contains the final set of 1460 classes, their definition and hierarchy</li> <li><em>all-classnames.xlsx</em>, contains a side-by-side view of all classes considered</li> </ul> <p>This mapping was used in VISIONE [Amato et al. 2021, Amato et al. 2022] that is a content-based retrieval system that supports various search functionalities (text search, object/color-based search, semantic and visual similarity search, temporal search). For the object detection VISIONE uses three pre-trained models: VfNet [Zhang et al. 2021] (trained on COCO dataset), Mask R-CNN [He et al. 2017] (trained on LVIS), and a <a href="http://tfhub.dev/google/faster_rcnn/openimages_v4/inception_resnet_v2/1">Faster R-CNN+Inception ResNet</a> (trained on the Open Images V4).</p> <p>This is repository is released under a Creative Commons Attribution license, please cite the following paper if you use it in your work in any form:</p> <blockquote> <pre>@inproceedings{amato2021visione, title={The visione video search system: exploiting off-the-shelf text search engines for large-scale video retrieval}, author={Amato, Giuseppe and Bolettieri, Paolo and Carrara, Fabio and Debole, Franca and Falchi, Fabrizio and Gennaro, Claudio and Vadicamo, Lucia and Vairo, Claudio}, journal={Journal of Imaging}, volume={7}, number={5}, pages={76}, year={2021}, publisher={Multidisciplinary Digital Publishing Institute} } </pre> </blockquote> <p> </p> <p> </p> <p><em><strong>References:</strong></em></p> <p>[Amato et al. 2022] Amato, G. et al. (2022). VISIONE at Video Browser Showdown 2022. In: , et al. MultiMedia Modeling. <em>MMM 2022. Lecture Notes in Computer Science</em>, vol 13142. Springer, Cham. <a href="https://doi.org/10.1007/978-3-030-98355-0_52">https://doi.org/10.1007/978-3-030-98355-0_52</a></p> <p>[Amato et al. 2021] Amato, G., Bolettieri, P., Carrara, F., Debole, F., Falchi, F., Gennaro, C., Vadicamo, L. and Vairo, C., 2021. The visione video search system: exploiting off-the-shelf text search engines for large-scale video retrieval. <em>Journal of Imaging</em>, <em>7</em>(5), p.76.</p> <p>[Gupta et al.2019] Gupta, A., Dollar, P. and Girshick, R., 2019. Lvis: A dataset for large vocabulary instance segmentation. In <em>Proceedings of the IEEE/CVF conference on computer vision and pattern recognition</em> (pp. 5356-5364).</p> <p>[He et al. 2017] He, K., Gkioxari, G., Dollár, P. and Girshick, R., 2017. Mask r-cnn. In <em>Proceedings of the IEEE international conference on computer vision</em> (pp. 2961-2969).</p> <p>[Kuznetsova et al. 2020] Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A. and Duerig, T., 2020. The open images dataset v4. <em>International Journal of Computer Vision</em>, <em>128</em>(7), pp.1956-1981.</p> <p>[Lin et al. 2014] Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P. and Zitnick, C.L., 2014, September. Microsoft coco: Common objects in context. In <em>European conference on computer vision</em> (pp. 740-755). Springer, Cham.</p> <p>[Zhang et al. 2021] Zhang, H., Wang, Y., Dayoub, F. and Sunderhauf, N., 2021. Varifocalnet: An iou-aware dense object detector. In <em>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</em> (pp. 8514-8523).</p> <p> </p>
Canopy top height models at 10m GSD from airborne LIDAR (derived from LVIS and small-footprint ALS)
<p>Rasterized canopy top height models (CTHM) at 10m ground sampling distance (GSD) derived from airborne LIDAR.</p><p>The CTHMs were created to be comparable to GEDI canopy top heights (within 25m footprints) using two sources:</p><p>1) NASA's LVIS airborne LIDAR campaigns (here we rasterized the RH98).<br>2) High-resolution canopy height models derived from small-footprint airborne laser scanning campaigns in Europe (max pooled with a circular 25m footprint corresponding to the GEDI footprint).</p><p>The original LVIS LIDAR data is available here: <a href="https://lvis.gsfc.nasa.gov">https://lvis.gsfc.nasa.gov</a></p><p>Links to the original ALS data are available here: <a href="https://publications.jrc.ec.europa.eu/repository/bitstream/JRC126223/jrc126223_jrc126223_lidaropensourcedata.pdf">https://publications.jrc.ec.europa.eu/repository/bitstream/JRC126223/jrc126223_jrc126223_lidaropensourcedata.pdf</a></p><p>Code to create GEDI-like canopy top heights from high-resolution ALS data is available here: https://github.com/langnico/global-canopy-height-model</p><p>More information is available in the Lang et al. (2022). Please cite our paper if you use these derived data in your own work.</p><p><strong>Reference:</strong></p><p>Lang, N., Jetz, W., Schindler, K., & Wegner, J. D. (2023). A high-resolution canopy height model of the Earth. Nature Ecology & Evolution, 1-12, <a href="https://doi.org/10.1038/s41559-023-02206-6">https://doi.org/10.1038/s41559-023-02206-6</a></p>
Feasibility Study of the LVIS™ (Low-profile Visualized Intraluminal Support)Device
ClinicalTrials.gov study NCT01541254. IPD Sharing: Not stated. Countries: 1. Publications: 1.
Pivotal Study of the LVIS (Low Profile Visualized Intraluminal Support)
ClinicalTrials.gov study NCT01793792. IPD Sharing: Not stated. Countries: 1. Publications: 1.
Safety and Efficacy of the LVIS and LVIS JR Devices in the Endovascular Treatment of Intracranial Aneurysms
ClinicalTrials.gov study NCT03553771. IPD Sharing: NO. Countries: 1. Publications: 1.
Chinese Registry of Assisted Embolization for Unruptured Wide Necked Intracranial Aneurysm Using LVIS Stent
ClinicalTrials.gov study NCT02830373. IPD Sharing: UNDECIDED. Countries: 1. Publications: 6.
Chinese Registry of Assisted Embolization for Ruptured Wide Necked Intracranial Aneurysm Using LVIS Stent
ClinicalTrials.gov study NCT02830386. IPD Sharing: UNDECIDED. Countries: 1. Publications: 7.
ABoVE: LVIS L3 Gridded Vegetation Structure across North America, 2017 and 2019
This dataset provides Level 3 (L3) footprint-level gridded metrics and attributes collected from NASA's Land, Vegetation, and Ice Sensor (LVIS)-Facility instrument for each flightline from 2017 and 2019. In 2017, the LVIS-Facility instrument was flown at a nominal flight altitude of 28,000 ft onboard a Dynamic Aviation Super King Air B200T. In 2019, the LVIS-Facility and LVIS-Classic instruments were flown at a nominal flight altitude of 41,000 feet onboard the NASA Gulfstream V. LVIS data are collected as waveforms over footprints of ~10-m diameter. The L3 data include grids of canopy relative height (RH), complexity, canopy cover (CC), ground elevation, and the number of LVIS footprints available to produce a pixel's estimate.. These 30-m resolution grids describe the vertical column of the vegetation canopy in detail with relative canopy height metrics and are enriched with an additional set of canopy cover estimates at a variety of height thresholds. The LVIS-Facility instrument 2017 and 2019 acquisitions span Arctic, boreal, temperate, and sub-tropical landscapes in support of a variety of Arctic-Boreal Vulnerability Experiment (ABoVE)- and Global Ecosystem Dynamics Investigation (GEDI)-related science. In the ABoVE study domain of arctic and boreal Alaska and Western Canada, some of these acquisitions coincide spatially with legacy small-footprint airborne lidar. Data are included for the ABoVE domain and also for the continental U.S. and central America in support of GEDI calibration and validation. Data files are provided in GeoTIFF format and one geopackage file shows flightlines.
AfriSAR: Canopy Cover and Vertical Profile Metrics Derived from LVIS, Gabon, 2016
This dataset includes footprint-level canopy structure products derived from data collected using NASA's Land, Vegetation, and Ice Sensor (LVIS) during flights over five forested sites in Gabon during February and March 2016. Three types of canopy structure information are included for each flight: 1) vertical profiles of canopy cover fraction in 1-meter bins, 2) vertical profiles of plant area index (PAI) in 1-meter bins, and 3) footprint summary data of total recorded energy, leaf area index, canopy cover fraction, and vertical foliage profiles in 10-meter bins. Canopy structure metrics are provided for each waveform (20-m footprint) collected by the LVIS instrument. These data were collected by NASA as part of the AfriSAR project. AfriSAR is a NASA collaboration with the European Space Agency (ESA), German Aerospace Center (DLR), and the Gabonese Space Agency (AGEOS) that is collecting data useful for deriving forest canopy structure and will help prepare for and calibrate current and upcoming spaceborne missions that aim to gauge the role of forests in Earth's carbon cycle.
AfriSAR: Gridded Forest Biomass and Canopy Metrics Derived from LVIS, Gabon, 2016
This dataset contains gridded forest characterization products derived from full-waveform lidar data acquired by NASA's airborne Land, Vegetation, and Ice Sensor (LVIS) instrument for five forested sites in Gabon, Africa, during the 2016 NASA-ESA AfriSAR campaign. The LVIS lidar instrument was flown over study sites in Lope, Mondah/Akanda, Pongara, Rabi, and Mabouni from February to March 2016. Derived canopy cover, canopy heights, bare ground elevation, plant area index (PAI), and foliage height diversity (FHD), and respective uncertainties are provided at a 25 m resolution for each of the five study sites. Aboveground biomass density (AGBD) and uncertainty were modeled at 50 m and 100 m resolutions for the Lope, Mondah, and Mabounie sites using field inventory data and waveform height and cover metrics. Lidar grid cell data collection statistics (i.e., number of shots and flight lines) and a data mask are also included. This research leverages high-quality forest inventory datasets collected during the AfriSAR campaign for one of the least studied and most unique forest ecosystems in the world.
LVIS™ Evo™ and HydroCoil® Embolic System for Intracranial Aneurysm Treatment
ClinicalTrials.gov study NCT04999423. IPD Sharing: NO. Countries: 5. Publications: 0.
Post-Market Surveillance Study to Evaluate the Long-Term Safety and Effectiveness of the LVIS Device
ClinicalTrials.gov study NCT05453240. IPD Sharing: Not stated. Countries: 1. Publications: 0.
IceBridge LVIS POS/AV L1B Corrected Position and Attitude Data, Version 1
This data set contains georeferencing data from the Applanix 510 and 610 POS AV systems flown with the Land, Vegetation, and Ice Sensor (LVIS) over Greenland, Antarctica, and Alaska. The data were collected as part of Operation IceBridge funded campaigns, including the Arctic Radiation - IceBridge Sea and Ice Experiment (ARISE).
TRAIL: Treatment of Intracranial Aneurysms With LVIS® System
ClinicalTrials.gov study NCT02921711. IPD Sharing: UNDECIDED. Countries: 0. Publications: 0.
Pre-IceBridge LVIS L2 Geolocated Ground Elevation and Return Energy Quartiles V001
This data set contains surface elevation data over Greenland measured by the NASA Land, Vegetation, and Ice Sensor (LVIS), an airborne lidar scanning laser altimeter.
ICESat-2 Calibration/Validation LVIS L1B Georeferenced Imagery V001
This data set contains georeferenced imagery from the NASA Land, Vegetation, and Ice Sensor (LVIS) PhaseOne medium-format camera, which was operated on high-altitude segments of flights during the ICESat-2 2022 Arctic Summer calibration campaign.
LVIS Facility L2 Geolocated Surface Elevation and Canopy Height Product V001
This data set contains Level-2 geolocated surface elevation and canopy height measurements collected by the NASA Land, Vegetation, and Ice Sensor (LVIS) Facility, an imaging lidar and camera sensor suite.
LVIS Classic L2 Geolocated Surface Elevation and Canopy Height Product V001
This data set contains Level-2 geolocated surface elevation and canopy height measurements collected by the NASA Land, Vegetation, and Ice Sensor (LVIS) Facility, an imaging lidar and camera sensor suite.
IceBridge LVIS-GH L1B Geolocated Return Energy Waveforms V001
This data set contains energy waveform data measured by the NASA Land, Vegetation, and Ice Sensor (LVIS), an airborne lidar scanning laser altimeter, aboard the Global Hawk Unmanned Aerial Vehicle. The data were collected as part of NASA Operation IceBridge funded campaigns.
IceBridge LVIS L0 Raw Ranges V001
This data set contains raw Inertial Measurement Unit (IMU), Global Positioning System (GPS), and camera data over Greenland, Antarctica, and Alaska measured by the NASA Land, Vegetation, and Ice Sensor (LVIS), an airborne lidar scanning laser altimeter. The data were collected as part of Operation IceBridge funded campaigns, including the Arctic Radiation - IceBridge Sea and Ice Experiment (ARISE).
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.