Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model

@article{Gidaris2015ObjectDV,
  title={Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model},
  author={Spyros Gidaris and Nikos Komodakis},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={1134-1142}
}
We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. We exploit the above properties of our recognition module by integrating it on an iterative localization mechanism that alternates… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • we achieve mAP of 78.2% and 73.9% correspondingly, surpassing any other published work by a significant margin.
  • Our detection system achieves mAP of 78.2% and 73.9% on VOC2007 [6] and VOC2012 [7] detection challenges respectively, thus surpassing the previous state-of-art by a quite significant margin.

Citations

Publications citing this paper.
SHOWING 1-10 OF 286 CITATIONS, ESTIMATED 99% COVERAGE

Multi-region Two-Stream R-CNN for Action Detection

VIEW 17 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Object Detection Based on Region Decomposition and Assembly

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Character Recognition in Japanese Historical Documents via Adaptive Multi-Region Model

  • 2018 Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition (icIVPR)
  • 2018
VIEW 13 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Deep Learning Models for Context-Aware Object Detection

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

On The Stability of Video Detection and Tracking

VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Training Region-Based Object Detectors with Online Hard Example Mining

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Imbalance Problems in Object Detection: A Review

Kemal Oksuz, Baris Can Cam, Sinan Kalkan, Emre Akbas
  • ArXiv
  • 2019
VIEW 8 EXCERPTS
HIGHLY INFLUENCED

Recent progresses on object detection: a brief review

  • Multimedia Tools and Applications
  • 2019
VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 42 Highly Influenced Citations

  • Averaged 75 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 30 REFERENCES

The PASCAL Visual Object Classes Challenge

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Segmentation as selective search for object recognition

  • 2011 International Conference on Computer Vision
  • 2011
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Convolutional feature masking for joint object and stuff segmentation

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 1 EXCERPT