In this paper we develop a computer vision-based system to transfer human motion from one subject to another. Our system uses a network of eight calibrated and synchronized camera...
German K. M. Cheung, Simon Baker, Jessica K. Hodgi...
This is a high level computer vision paper, which employs concepts from Natural Language Understanding in solving the video retrieval problem. Our main contribution is the utiliza...
CrystalDome is an inexpensive alternative to a volumetric display based on video projector technology that supports omni-directional viewing (Figure 1). It can show mapped spheric...
We study video transcoding for accelerated channel changes in IPTV systems. Video transcoding at the Retransmission Server not only reduces the channel change latency, but also re...
Multi-task learning leverages shared information among data sets to improve the learning performance of individual tasks. The paper applies this framework for data where each task ...