24 citations · 28 across the 2 of their papers we have counts for
3 papers
cs.CL2017
Sequence to Sequence Networks for Roman-Urdu to Urdu Transliteration
Mehreen Alam, Sibt ul Hussain
Neural Machine Translation models have replaced the conventional phrase based statistical translation methods since the former takes a generic, scalable, data-driven approach rathe…
cs.MM2017★ 24 cited
End-to-end Trained CNN Encode-Decoder Networks for Image Steganography
Atique ur Rehman, Rafia Rahim, M Shahroz Nadeem +1
All the existing image steganography methods use manually crafted features to hide binary payloads into cover images. This leads to small payload capacity and image distortion. Her…
cs.CV2017★ 4 cited
Recovering Homography from Camera Captured Documents using Convolutional Neural Networks
Syed Ammar Abbas, Sibt ul Hussain
Removing perspective distortion from hand held camera captured document images is one of the primitive tasks in document analysis, but unfortunately, no such method exists that can…