2 datasets found

  1. OSCAR: Occluded Stereo dataset for Convolutional Architectures with...

    • zenodo.org
    bin, zip
    Updated Oct 22, 2021
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Markus Roland Ernst; Markus Roland Ernst; Jochen Triesch; Jochen Triesch; Thomas Burwick; Thomas Burwick (2021). OSCAR: Occluded Stereo dataset for Convolutional Architectures with Recurrence [Dataset]. http://doi.org/10.5281/zenodo.3540900
    Explore at:
    zip, binAvailable download formats
    Unique identifier
    https://doi.org/10.5281/zenodo.3540900
    Dataset updated
    Oct 22, 2021
    Dataset provided by
    Zenodohttp://zenodo.org/
    Authors
    Markus Roland Ernst; Markus Roland Ernst; Jochen Triesch; Jochen Triesch; Thomas Burwick; Thomas Burwick
    Description

    OSCAR, the Occluded Stereo dataset for Convolutional Architectures with Recurrence. Version: 1.0
    (dataset as presented in our ESANN 2020 conference publication "Recurrent Feedback Improves Recognition of Partially Occluded Objects")

    If you make use of the dataset, please cite as follows:

    Ernst M.R., Triesch J., Burwick T. (2020). Recurrent Feedback Improves Recognition of Partially Occluded Objects. In Proceedings of the 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

    Contents

    • readme.md - detailed description and sample pictures
    • img.zip - folder that contains images for the readme file
    • licence.md - licence agreement for using the datasets
    • os-mnist.zip - compressed archive of the occluded stereo multi-MNIST dataset (~1,7GB)
    • os-ycb.zip - compressed archive of the occluded stereo ycb-object dataset (~1.1GB)
  2. Z

    OSCAR: Occluded Stereo dataset for Convolutional Architectures with...

    • data.niaid.nih.gov
    • zenodo.org
    Updated Dec 31, 2021
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Jochen Triesch (2021). OSCAR: Occluded Stereo dataset for Convolutional Architectures with Recurrence [Dataset]. https://data.niaid.nih.gov/resources?id=zenodo_3540899
    Explore at:
    Dataset updated
    Dec 31, 2021
    Dataset provided by
    Thomas Burwick
    Markus Roland Ernst
    Jochen Triesch
    Description

    OSCAR, the Occluded Stereo dataset for Convolutional Architectures with Recurrence. Version: 2.0 (dataset as presented in our JOV 2021 journal publication "Recurrent Processing Improves Occluded Object Recognition and Gives Rise to Perceptual Hysteresis")

    If you make use of the dataset, please cite as follows:

    Ernst, M. R., Burwick, T., & Triesch, J. (2021). Recurrent Processing Improves Occluded Object Recognition and Gives Rise to Perceptual Hysteresis. In Journal of Vision

    Contents

    readme.md - detailed description and sample pictures

    img.zip - folder that contains images for the readme file

    licence.md - licence agreement for using the datasets

    os-fmnist2c.zip - compressed archive of the occluded stereo FashionMNIST dataset (centered, ~1.1GB)

    os-fmnist2r.zip - compressed archive of the occluded stereo FashionMNIST dataset (random, ~1.2GB)

    os-mnist2c.zip - compressed archive of the occluded stereo MNIST dataset (centered, ~865MB)

    os-mnist2r.zip - compressed archive of the occluded stereo MNIST dataset (random, ~851MB)

    os-ycb2.zip - compressed archive of the occluded stereo ycb-object dataset (~1.1GB)

    os-ycb2_highres.zip - compressed archive of the occluded stereo ycb-object dataset (high resolution, ~9.8GB)

    OSCARv2_dataset.py - python script to directly load image data from folder, pytorch dataset

  3. Not seeing a result you expected?
    Learn how you can add new datasets to our index.

Share
FacebookFacebook
TwitterTwitter
Email
Click to copy link
Link copied
Close
Cite
Markus Roland Ernst; Markus Roland Ernst; Jochen Triesch; Jochen Triesch; Thomas Burwick; Thomas Burwick (2021). OSCAR: Occluded Stereo dataset for Convolutional Architectures with Recurrence [Dataset]. http://doi.org/10.5281/zenodo.3540900
Organization logo

OSCAR: Occluded Stereo dataset for Convolutional Architectures with Recurrence

Explore at:
zip, binAvailable download formats
Unique identifier
https://doi.org/10.5281/zenodo.3540900
Dataset updated
Oct 22, 2021
Dataset provided by
Zenodohttp://zenodo.org/
Authors
Markus Roland Ernst; Markus Roland Ernst; Jochen Triesch; Jochen Triesch; Thomas Burwick; Thomas Burwick
Description

OSCAR, the Occluded Stereo dataset for Convolutional Architectures with Recurrence. Version: 1.0
(dataset as presented in our ESANN 2020 conference publication "Recurrent Feedback Improves Recognition of Partially Occluded Objects")

If you make use of the dataset, please cite as follows:

Ernst M.R., Triesch J., Burwick T. (2020). Recurrent Feedback Improves Recognition of Partially Occluded Objects. In Proceedings of the 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

Contents

  • readme.md - detailed description and sample pictures
  • img.zip - folder that contains images for the readme file
  • licence.md - licence agreement for using the datasets
  • os-mnist.zip - compressed archive of the occluded stereo multi-MNIST dataset (~1,7GB)
  • os-ycb.zip - compressed archive of the occluded stereo ycb-object dataset (~1.1GB)
Search
Clear search
Close search
Google apps
Main menu