Debabrata Sengupta

Learn More
We present a novel approach to 2D and 3D human pose estimation in monocular images by building on and improving recent advances in this field. We take the full body pose as a combination of a 3D pose and a viewpoint and in this way define classes that are then learned by a classifier. Compared to part based approaches, our approach does not suffer from(More)
The problem we are investigating is sign language recognition through unsupervised feature learning. Being able to recognize sign language is an interesting machine learning problem while simultaneously being extremely useful for deaf people to interact with people who don't know how to understand American Sign Language (ASL). Our approach was to first(More)
In this work, we propose a control protocol for lightpath management in the optical layer of all-optical networks (AONs). AONs follow a layered structure, as used by various network standards, where each layer communicates with its peer through Protocol Data Units (PDUs). In the context of Open System Interconnection (OSI) Reference Model (RM), a new layer,(More)
  • 1