M. Q. Aguiar
ultimate goal of my research is to make computers extract high level content from images by seeking their simplest
interpretation. This lead me to the areas of image processing, computer
vision, machine learning, pattern recognition. Other (older) research
interests include statistical signal processing, stochastic processes,
nonlinear systems, automatic control.
Seeing without Looking: contextual
rescoring of object detections for AP maximization
L. Pato, R. Negrinho, and P. Aguiar, IEEE Conf. on Computer Vision and
Pattern Recognition, 2020.
Distributed basis pursuit IEEE SPS Young Author Best Paper Award
J. Mota, J.
Xavier, P. Aguiar, and M. Püschel, IEEE Trans. on Signal Processing, 60(4),
optimal solution to exploit rigidity when recovering structure from motion
P. Aguiar, J. Xavier, and M. Stosic, IEEE Int. Conf. on Image
Processing, 2008. DoCoMo USA Labs Innovative Paper Award
Manhattan: equiprojective classes and sequential estimation (movies)
A. Martins, P. Aguiar, and M. Figueiredo, IEEE Trans. on Pattern Analysis and
Machine Intelligence, 27(5), 2005.
Rank 1 weighted
factorization for 3D structure recovery
P. Aguiar and J.
Moura, IEEE Trans. on Pattern Analysis and Machine Intelligence, 25(9), 2003.
“I am an apostle of the now – the
Do today all you reasonably can. Do not attempt to see the end of the road.
Keep your ends or goals in mind, but direct your brains to the solving and
satisfactorily doing of all that your hands, or feet, find to do today.”
Percy Cerutty, Athletics, 1960.
"Invention is, in fact, a
cautious dipping into the negation that lies outside system
from a position firmly ensconced in system."
Glenn Gould, Royal Conservatory of Music, Toronto, 1964.