We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
This paper presents a framework for view-invariant action recognition in image sequences. Feature-based human detection becomes extremely challenging when the agent is being observ...
Bhaskar Chakraborty, Marco Pedersoli, Jordi Gonz&a...
Counting (identical) objects in images is a simple yet fundamental recognition task that requires exhaustive human effort. Automation of this task would reduce the human load sign...
Takumi Kobayashi, Tadaaki Hosaka, Shu Mimura, Taka...
Conventional stereoscopic video content production requires use of dedicated stereo camera rigs which is both costly and lacking video editing flexibility. In this paper, we propo...
Jean-Yves Guillemaut, Muhammad Sarim, Adrian Hilto...
The integration of vision and natural languageprocessingincreasingly attracts attention in different areas of AI research. Up to now, however, there have only been a few attempts a...