10 citations · 14 across the 2 of their papers we have counts for
3 papers
Multi-task Learning for Continuous Control
Himani Arora, Rajath Kumar, Jason Krone +1
Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the rei…
Lip2AudSpec: Speech reconstruction from silent lip movements video
Hassan Akbari, Himani Arora, Liangliang Cao +1
In this study, we propose a deep neural network for reconstructing intelligible speech from silent lip movement videos. We use auditory spectrogram as spectral representation of sp…
Computing Egomotion with Local Loop Closures for Egocentric Videos
Suvam Patra, Himanshu Aggarwal, Himani Arora +2
Finding the camera pose is an important step in many egocentric video applications. It has been widely reported that, state of the art SLAM algorithms fail on egocentric videos. In…