1. zip -s 0 CVPR2023-Anti_Spoof-Challenge-Release-Data-20230209.zip --out xxx.zip 2. unzip xxx.zip (get password through application, see details at https://github.com/deepinsight/insightface/tree/master/challenges/cvpr23-fas-wild) e.g : unzip -P password xxx.zip 3. Directory Structure: Data └── Train ├── living │ └── subject │ ├── imagename.jpg │ └── imagename.txt └── spoof └── PAs type └── subject ├── imagename.jpg └── imagename.txt 4. Bounding box and Landmarks description: - Produced by RetinaFace : https://github.com/deepinsight/insightface/tree/master/RetinaFace @inproceedings{Deng2020CVPR, title = {RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild}, author = {Deng, Jiankang and Guo, Jia and Ververas, Evangelos and Kotsia, Irene and Zafeiriou, Stefanos}, booktitle = {CVPR}, year = {2020} } - e.g: Train/spoof/2D-Display-Phone/000001/000001.txt 192 148 (bbox left top) 234 203 (bbox right bottom) 216 171 (landmark left eye) 230 168 (landmark right eye) 231 180 (landmark nose) 218 190 (landmark left mouth ) 229 188 (landmark right mouth ) ``` @misc{2023insightfacefaswild, title={InsightFace Wild Anti-Spoofing Dataset}, author={Dong Wang, Qiqi Shao, Haochi He, Zhian Chen, Jia Guo, Jiankang Deng, Jun Wan, Ajian Liu, Sergio Escalera, Hugo Jair Escalante, Isabelle Guyon, Zhen Lei, Chenxu Zhao, Shaopeng Tang }, howpublished = {\url{https://github.com/deepinsight/insightface/tree/master/challenges/cvpr23-fas-wild}}, year={2023} } ```