• Computer Science
  • Published in ArXiv 2014

On Learning Where To Look

@article{Ranzato2014OnLW,
  title={On Learning Where To Look},
  author={Marc'Aurelio Ranzato},
  journal={ArXiv},
  year={2014},
  volume={abs/1405.5488}
}
Current automatic vision systems face two major challenges: scalability and extreme variability of appearance. First, the computational time required to process an image typically scales linearly with the number of pixels in the image, therefore limiting the resolution of input images to thumbnail size. Second, variability in appearance and pose of the objects constitute a major hurdle for robust recognition and detection. In this work, we propose a model that makes baby steps towards… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 38 CITATIONS

Conditional Dilated Attention Tracking Model - C-DATM

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Autonomous Curiosity for Real-Time Training Onboard Robotic Agents

  • 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2019
VIEW 1 EXCERPT
CITES METHODS

FocalNet - Foveal Attention for Post-processing DNN Outputs

  • 2019 International Joint Conference on Neural Networks (IJCNN)
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND

Learning to Learn in Simulation

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 17 REFERENCES

Context-Aware Saliency Detection

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 2012
VIEW 1 EXCERPT

Cascade object detection with deformable part models

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 1 EXCERPT

Robust classification of objects, faces, and flowers using natural image statistics

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 1 EXCERPT

Int

J. Elder, S. Prince, Y. Hou, M Sizintsev, E. Olevskiy
  • Journal of Computer Vision, 72:4766,
  • 2007
VIEW 1 EXCERPT