Corpus ID: 2524048

ResearchDoom and CocoDoom: Learning Computer Vision with Games

@article{Mahendran2016ResearchDoomAC,
  title={ResearchDoom and CocoDoom: Learning Computer Vision with Games},
  author={Aravindh Mahendran and Hakan Bilen and Jo{\~a}o F. Henriques and Andrea Vedaldi},
  journal={ArXiv},
  year={2016},
  volume={abs/1610.02431}
}
  • Aravindh Mahendran, Hakan Bilen, +1 author Andrea Vedaldi
  • Published in ArXiv 2016
  • Computer Science
  • In this short note we introduce ResearchDoom, an implementation of the Doom first-person shooter that can extract detailed metadata from the game. We also introduce the CocoDoom dataset, a collection of pre-recorded data extracted from Doom gaming sessions along with annotations in the MS Coco format. ResearchDoom and CocoDoom can be used to train and evaluate a variety of computer vision methods such as object recognition, detection and segmentation at the level of instances and categories… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    5
    Twitter Mentions

    Figures and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 13 CITATIONS

    MapNet: An Allocentric Spatial Memory for Mapping Environments

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND

    Show, Attend, and Translate: Unsupervised Image Translation With Self-Regularization and Attention

    VIEW 1 EXCERPT
    CITES BACKGROUND

    The RobotriX: An Extremely Photorealistic and Very-Large-Scale Indoor Dataset of Sequences with Robot Trajectories and Interactions

    VIEW 1 EXCERPT
    CITES BACKGROUND

    ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond

    VIEW 1 EXCERPT
    CITES BACKGROUND

    State-of-the-Art and Open Challenges in RTS Game-AI and Starcraft

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-9 OF 9 REFERENCES

    Synthetic Data for Text Localisation in Natural Images

    VIEW 1 EXCERPT

    Riedmiller . Playing atari with deep reinforcement learning

    • Koray Kavukcuoglu Volodymyr Mnih, David Silver, Ioannis Antonoglou Alex Graves, Daan Wierstra
    • 2013

    Riedmiller . Playing atari with deep reinforcement learning

    • Koray Kavukcuoglu Volodymyr Mnih, David Silver, Ioannis Antonoglou Alex Graves, Daan Wierstra
    • 2013