Dynamic Relevance: Vision-Based Focus of Attention Using Artificial Neural Networks. (Technical Note)

@article{Baluja1997DynamicRV,
  title={Dynamic Relevance: Vision-Based Focus of Attention Using Artificial Neural Networks. (Technical Note)},
  author={Shumeet Baluja and Dean Pomerleau},
  journal={Artif. Intell.},
  year={1997},
  volume={97},
  pages={381-395}
}
Abstract This paper presents a method for ascertaining the relevance of inputs in vision-based tasks by exploiting temporal coherence and predictability. In contrast to the tasks explored in many previous relevance experiments, the class of tasks examined in this study is one in which relevance is a time-varying function of the previous and current inputs. The method proposed in this paper dynamically allocates relevance to inputs by using expectations of their future values. As a model of the… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 20 CITATIONS

Active recognition through next view planning: a survey

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Estimation of source relevance and theory of belief functions

Active Vision: Directing Visual Attention

VIEW 1 EXCERPT
CITES METHODS

Attention links sensing to recognition

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 21 REFERENCES

Expectation-based selective attention

VIEW 12 EXCERPTS

Reliability estimation for neural network based autonomous driving

VIEW 8 EXCERPTS

Network Perception for Mobile Robot Guidance

  • D. Pomerleau.Neural
  • Kluwer Academic Publishing,
  • 1993
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Neural network-based face detection

VIEW 1 EXCERPT

Greedy Attribute Selection

VIEW 1 EXCERPT