State of the art in Gait recognition: Novel AutoEncoder framework, GaitNet

https://www.profillic.com/paper/arxiv:1909.03051

"With extensive experiments on CASIA-B, USF, and FVG datasets, our method demonstrates superior performance to the SOTA quantitatively, the ability of feature disentanglement qualitatively, and promising computational efficiency."
https://m.facebook.com/groups/1738168866424224?view=permalink&id=2414785935429177&sfnsn=mo
Posted by uniqueone
,
ICMYI: Breast Cancer Diagnosis with Transfer Learning and Global Pooling

https://www.profillic.com/paper/arxiv:1909.11839

(Breast cancer is one of the most common causes of cancer-related death in women worldwide)

(The proposed network architecture using a pre-trained Xception model yields 92.50% average classification accuracy)
https://www.facebook.com/groups/1738168866424224/permalink/2414747192099718/?sfnsn=mo
Posted by uniqueone
,
Modern problems require modern solutions: Protecting privacy using deepfakes

https://www.profillic.com/paper/arxiv:1909.04538
https://www.facebook.com/groups/1738168866424224/permalink/2415463898694714/?sfnsn=mo
Posted by uniqueone
,