Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation

@article{Wu2016LearningAM,
  title={Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation},
  author={Tianfu Wu and B. Li and S. Zhu},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2016},
  volume={38},
  pages={1829-1843}
}
  • Tianfu Wu, B. Li, S. Zhu
  • Published 2016
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • This paper presents a method for learning an And-Or model to represent context and occlusion for car detection and viewpoint estimation. [...] Key Method The learning process consists of two stages in a weakly supervised way (i.e., only bounding boxes of single cars are annotated).Expand Abstract
    Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art
    • 199
    • Highly Influenced
    • PDF
    Are They Going to Cross? A Benchmark Dataset and Baseline for Pedestrian Crosswalk Behavior
    • 48
    • Highly Influenced
    Multi-Task Vehicle Detection With Region-of-Interest Voting
    • 39
    SINet: A Scale-Insensitive Convolutional Neural Network for Fast Vehicle Detection
    • 58
    • PDF
    Collaborative Deep Reinforcement Learning for Joint Object Search
    • 37
    • PDF
    Interpretable R-CNN
    • 14

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 84 REFERENCES
    Histograms of oriented gradients for human detection
    • 25,735
    • PDF
    ImageNet classification with deep convolutional neural networks
    • 52,343
    • PDF
    Robust Real-Time Face Detection
    • 9,463
    • PDF
    Are we ready for autonomous driving? The KITTI vision benchmark suite
    • 4,707
    • Highly Influential
    • PDF
    Pedestrian Detection: An Evaluation of the State of the Art
    • 2,340
    • PDF
    An HOG-LBP human detector with partial occlusion handling
    • 1,570
    • PDF
    Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model
    • 75
    • PDF