Search Results - "Aguiar, Pedro M. Q."

D-ADMM: A Communication-Efficient Distributed Algorithm for Separable Optimization by Mota, J. F. C., Xavier, J. M. F., Aguiar, P. M. Q., Puschel, M.

“…We propose a distributed algorithm, named Distributed Alternating Direction Method of Multipliers (D-ADMM), for solving separable optimization problems in…”
Get full text

Revisiting Complex Moments for 2-D Shape Representation and Image Normalization by Crespo, J. B. F. P., Aguiar, P. M. Q.

“…When comparing 2-D shapes, a key issue is their normalization. Translation and scale are easily taken care of by removing the mean and normalizing the energy…”
Get full text

Distributed Basis Pursuit by Mota, J. F. C., Xavier, J. M. F., Aguiar, P. M. Q., Puschel, M.

“…We propose a distributed algorithm for solving the optimization problem Basis Pursuit (BP). BP finds the least ℓ 1 -norm solution of the underdetermined linear…”
Get full text

Connectivity-Enforcing Hough Transform for the Robust Extraction of Line Segments by Guerreiro, R. F. C., Aguiar, P. M. Q.

“…Global voting schemes based on the Hough transform (HT) have been widely used to robustly detect lines in images. However, since the votes do not take line…”
Get full text

Combining information theoretic kernels with generative embeddings for classification by Bicego, Manuele, Ulaş, Aydın, Castellani, Umberto, Perina, Alessandro, Murino, Vittorio, Martins, André F.T., Aguiar, Pedro M.Q., Figueiredo, Mário A.T.

“…Classical approaches to learn classifiers for structured objects (e.g., images, sequences) use generative models in a standard Bayesian framework. To exploit…”
Get full text

Multimodal Continuous Visual Attention Mechanisms by Farinhas, Antonio, Martins, Andre F. T., Aguiar, Pedro M. Q.

“…Visual attention mechanisms are a key component of neural network models for computer vision. By focusing on a discrete set of objects or image regions, these…”
Get full text

Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization by Pato, Lourenco V., Negrinho, Renato, Aguiar, Pedro M. Q.

“…The majority of current object detectors lack context: class predictions are made independently from other detections. We propose to incorporate context in…”
Get full text

Symmetric polynomials for 2D shape representation by Negrinho, Renato M. P., Aguiar, Pedro M. Q.

“…We discuss the usage of symmetric polynomials for representing 2D shapes in their most general form, i.e., arbitrary sets of unlabeled points in the plane…”
Get full text

On singular values of partially prescribed matrices by Aguiar, Pedro M.Q., Stošić, Marko, Xavier, João

“…In this paper we study singular values of a matrix whose one entry varies while all other entries are prescribed. In particular, we find the possible pth…”
Get full text

Extraction of line segments in cluttered images via multiscale edges by Guerreiro, Rui F. C., Aguiar, Pedro M. Q.

“…Current methods for line segment extraction often fail in challenging scenarios that abound in real-life images, e.g., those containing corrupted lines, of…”
Get full text

Figure-ground segmentation from occlusion by Aguiar, P.M.Q., Moura, J.M.F.

“…Layered video representations are increasingly popular; see for a recent review. Segmentation of moving objects is a key step for automating such…”
Get full text

Orientation in Manhattan: equiprojective classes and sequential estimation by Martins, A.T., Aguiar, P.M.Q., Figueiredo, M.A.T.

“…The problem of inferring 3D orientation of a camera from video sequences has been mostly addressed by first computing correspondences of image features. This…”
Get full text

Shape representation via elementary symmetric polynomials: A complete invariant inspired by the bispectrum by Negrinho, Renato M. P., Aguiar, Pedro M. Q.

“…We address the representation of two-dimensional shape in its most general form, i.e., arbitrary sets of points, that may arise in multiple situations, e.g.,…”
Get full text

Distributed Optimization With Local Domains: Applications in MPC and Network Flows by Mota, Joao F. C., Xavier, Joao M. F., Aguiar, Pedro M. Q., Puschel, Markus

“…We consider a network where each node has exclusive access to a local cost function. Our contribution is a communication-efficient distributed algorithm that…”
Get full text

Simultaneous registration and intensity normalization of SPECT perfusion images by Silveira, Margarida, Aguiar, Pedro M. Q.

“…The analysis of 3D SPECT brain images requires several pre-processing steps such as registration, intensity normalization and brain extraction. Usually,…”
Get full text

Connectivity-Enforcing Hough Transform for the Robust Extraction of Line Segments by Guerreiro, Rui F. C, Aguiar, Pedro M. Q

“…Global voting schemes based on the Hough transform (HT) have been widely used to robustly detect lines in images. However, since the votes do not take line…”
Get full text

Distributed Optimization With Local Domains: Applications in MPC and Network Flows by Mota, João F. C, Xavier, João M. F, Aguiar, Pedro M. Q, Püschel, Markus

“…In this paper we consider a network with $P$ nodes, where each node has exclusive access to a local cost function. Our contribution is a…”
Get full text

D-ADMM: A Communication-Efficient Distributed Algorithm For Separable Optimization by Mota, João F. C, Xavier, João M. F, Aguiar, Pedro M. Q, Püschel, Markus

“…IEEE Transactions on Signal Processing, Vol. 61, No. 10, pp. 2718-1723, 2013 We propose a distributed algorithm, named Distributed Alternating Direction Method…”
Get full text

Optimized filters for efficient multi-texture discrimination by Guerreiro, Rui F. C., Aguiar, Pedro M. Q.

“…When performing texture analysis via standard filter banks, good discrimination depends on the usage of a large number of filters. For example, when using the…”
Get full text

Distributed Basis Pursuit by Mota, João F. C, Xavier, João M. F, Aguiar, Pedro M. Q, Püschel, Markus

“…We propose a distributed algorithm for solving the optimization problem Basis Pursuit (BP). BP finds the least L1-norm solution of the underdetermined linear…”
Get full text