OSCAR: Occluded Stereo dataset for Convolutional Architectures with Recurrence

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)

Resources

Name Format Description Link
0 http://data.europa.eu/88u/dataset/oai-zenodo-org-3540900
0 http://data.europa.eu/88u/dataset/oai-zenodo-org-3540900
0 http://data.europa.eu/88u/dataset/oai-zenodo-org-3540900
0 http://data.europa.eu/88u/dataset/oai-zenodo-org-3540900
0 http://data.europa.eu/88u/dataset/oai-zenodo-org-3540900
0 http://data.europa.eu/88u/dataset/oai-zenodo-org-3540900

Tags

  • occlusion
  • deep-learning
  • object-recognition
  • recurrent-neural-networks
  • dataset
  • computer-vision
  • machine-learning

Topics

Categories