/PedesFormer-Transformer-Networks-For-Pedestrian-Detection

Transformer Networks for Pedestrian Detection

Primary LanguagePythonApache License 2.0Apache-2.0

PedesFormer

PedesFormer is a MMDetection and SwinTransformer based repository. Focused on adavancement of reseach on pedestrian detection using transformer networks.

Pretrained Models

Details and Pre-trained models are coming soon.

Please cite the following works

CVPR2021

@InProceedings{Hasan_2021_CVPR,
    author    = {Hasan, Irtiza and Liao, Shengcai and Li, Jinpeng and Akram, Saad Ullah and Shao, Ling},
    title     = {Generalizable Pedestrian Detection: The Elephant in the Room},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {11328-11337}
}

[ArXiv2021]

@InProceedings{Hasan_2021_Arxiv,
    author    = {Hasan, Irtiza and Liao, Shengcai and Li, Jinpeng and Akram, Saad Ullah and Shao, Ling},
    title     = {Pedestrian Detection: Domain Generalization,CNNs, Transformers and Beyond},
    booktitle = {ArXiv},
    month     = {November},
    year      = {2021},
    pages     = {11328-11337}
}