Object Detection Networks on Convolutional Feature Maps

@article{Ren2015ObjectDN,
  title={Object Detection Networks on Convolutional Feature Maps},
  author={Shaoqing Ren and Kaiming He and Ross B. Girshick and Xiangyu Zhang and Jian Sun},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2015},
  volume={39},
  pages={1476-1481}
}
Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts leading to better deep convolutional architectures. The object classifier, however, has not received much attention and many recent systems (like SPPnet and Fast/Faster R-CNN) use simple multi-layer perceptrons. This paper demonstrates that carefully designing deep networks for object classification is just as important… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 136 CITATIONS

A Review of Object Detection Models based on Convolutional Neural Network

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

New Benchmark Datasets and a Character Identification System on TV Series

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Implicit Negative Sub-Categorization and Sink Diversion for Object Detection

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Weakly Supervised Learning of Deformable Part-Based Models for Object Detection via Region Proposals

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

People detection in crowded scenes via regional-based convolutional network

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Cascaded Regional Spatio-Temporal Feature-Routing Networks for Video Object Detection

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Object Detection With Deep Learning: A Review

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Feature Selective Networks for Object Detection

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 10 Highly Influenced Citations

  • Averaged 34 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

Edge Boxes: Locating Object Proposals from Edges

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

VIEW 10 EXCERPTS

Selective Search for Object Recognition

VIEW 18 EXCERPTS
HIGHLY INFLUENTIAL

Fully convolutional networks for semantic segmentation

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Deformable part models are convolutional neural networks

VIEW 8 EXCERPTS

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

VIEW 8 EXCERPTS

Diagnosing Error in Object Detectors

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Object Detection with Discriminatively Trained Part Based Models

VIEW 9 EXCERPTS