End-to-End People Detection in Crowded Scenes

@article{Stewart2016EndtoEndPD,
  title={End-to-End People Detection in Crowded Scenes},
  author={R. Stewart and M. Andriluka and A. Ng},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={2325-2333}
}
  • R. Stewart, M. Andriluka, A. Ng
  • Published 2016
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Current people detectors operate either by scanning an image in a sliding window fashion or by classifying a discrete set of proposals. [...] Key Method Because we generate predictions jointly, common post-processing steps such as nonmaximum suppression are unnecessary. We use a recurrent LSTM layer for sequence generation and train our model end-to-end with a new loss function that operates on sets of detections. We demonstrate the effectiveness of our approach on the challenging task of detecting people in…Expand Abstract
    Convolutional Pose Machines
    • 1,421
    • PDF
    Switching Convolutional Neural Network for Crowd Counting
    • 361
    • PDF
    Relation Networks for Object Detection
    • 333
    • PDF
    MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
    • 334
    • Highly Influenced
    • PDF
    End-to-End Instance Segmentation with Recurrent Attention
    • 171
    • PDF
    Recurrent Instance Segmentation
    • 226
    • PDF
    Semantic Instance Segmentation with a Discriminative Loss Function
    • 178
    • PDF
    Learning Non-maximum Suppression
    • 136
    • PDF
    End-to-end crowd counting via joint learning local and global count
    • 96

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 36 REFERENCES
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,479
    • Highly Influential
    • PDF
    Going deeper with convolutions
    • 20,004
    • PDF
    Long Short-Term Memory
    • 31,027
    • PDF
    Sequence to Sequence Learning with Neural Networks
    • 10,542
    • Highly Influential
    • PDF
    Caffe: Convolutional Architecture for Fast Feature Embedding
    • 12,121
    • PDF
    ImageNet: A large-scale hierarchical image database
    • 12,320
    • PDF
    Selective Search for Object Recognition
    • 3,584
    • PDF