The Fastest Deformable Part Model for Object Detection

@article{Yan2014TheFD,
  title={The Fastest Deformable Part Model for Object Detection},
  author={Junjie Yan and Zhen Lei and Longyin Wen and Stan Z. Li},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={2497-2504}
}
This paper solves the speed bottleneck of deformable part model (DPM), while maintaining the accuracy in detection on challenging datasets. Three prohibitive steps in cascade version of DPM are accelerated, including 2D correlation between root filter and feature map, cascade part pruning and HOG feature extraction. For 2D correlation, the root filter is constrained to be low rank, so that 2D correlation can be calculated by more efficient linear combination of 1D correlations. A proximal… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 168 CITATIONS

Flexible 3D neighborhood cascade deformable part models for object detection

VIEW 18 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

A Region-based Fusion Scheme for Human Detection in Autonomous Navigation Applications

VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Adaptive cascade threshold learning from negative samples for deformable part models

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Face Detection Framework Based on Deep Cascaded Full Convolutional Neural Networks

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Single-Shot Scale-Aware Network for Real-Time Face Detection

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND

A Fast Face Detection Method via Convolutional Neural Network

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Low Power Hardware Implementation of Multi-Object DPM Detector for Autonomous Driving

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Tensor-based approach to accelerate deformable part models

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Fast and Accurate Unconstrained Face Detector

VIEW 9 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND

FILTER CITATIONS BY YEAR

2013
2020

CITATION STATISTICS

  • 26 Highly Influenced Citations

  • Averaged 30 Citations per year from 2017 through 2019

  • 4% Increase in citations per year in 2019 over 2018

References

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

Face detection, pose estimation, and landmark localization in the wild

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Pedestrian Detection: An Evaluation of the State of the Art

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Cascade object detection with deformable part models

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

The Pascal Visual Object Classes (VOC) Challenge

VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Fast Feature Pyramids for Object Detection

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Crosstalk Cascades for Frame-Rate Pedestrian Detection

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Exact Acceleration of Linear Object Detectors

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Rapid Deformable Object Detection using Dual-Tree Branch-and-Bound

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Object Detection with Discriminatively Trained Part Based Models

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL