no code implementations • 25 Jul 2021 • Thasin Abedin, Khondokar S. S. Prottoy, Ayana Moshruba, Safayat Bin Hakim
While the image network gets the visual features, the relative positions of hand keypoints are taken by the pose estimation network to obtain the additional features to deal with the complexity of the BdSL symbols.
1 code implementation • 15 Sep 2020 • Md. Mushfiqur Rahman, Thasin Abedin, Khondokar S. S. Prottoy, Ayana Moshruba, Fazlul Hasan Siddiqui
As there are no exclusive metrics for evaluating video captioning models, we emphasize both quantitative and qualitative analysis of our model.