A Task-Oriented Approach for Cost-Sensitive Recognition

@article{Mottaghi2016ATA,
  title={A Task-Oriented Approach for Cost-Sensitive Recognition},
  author={Roozbeh Mottaghi and Hannaneh Hajishirzi and Ali Farhadi},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={2203-2211}
}
With the recent progress in visual recognition, we have already started to see a surge of vision related real-world applications. These applications, unlike general scene understanding, are task oriented and require specific information from visual data. Considering the current growth in new sensory devices, feature designs, feature learning methods, and algorithms, the search in the space of features and models becomes combinatorial. In this paper, we propose a novel cost-sensitive task… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.

Who Let the Dogs Out? Modeling Dog Behavior from Visual Data

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

Holistic Scene Understanding for 3D Object Detection with RGBD Cameras

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

The Greedy Miser: Learning under Test-time Budgets

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Anytime Recognition of Objects and Scenes

VIEW 3 EXCERPTS

Decorrelating Semantic Visual Attributes by Resisting the Urge to Share

VIEW 1 EXCERPT

Dense Semantic Image Segmentation with Objects and Attributes

VIEW 1 EXCERPT