Time filter

Source Type

Carneiro G.,University of Adelaide | Nascimento J.C.,Institute Sistemas e Robotica
Proceedings of the IEEE International Conference on Computer Vision | Year: 2011

Recently, there has been an increasing interest in the investigation of statistical pattern recognition models for the fully automatic segmentation of the left ventricle (LV) of the heart from ultrasound data. The main vulnerability of these models resides in the need of large manually annotated training sets for the parameter estimation procedure. The issue is that these training sets need to be annotated by clinicians, which makes this training set acquisition process quite expensive. Therefore, reducing the dependence on large training sets is important for a more extensive exploration of statistical models in the LV segmentation problem. In this paper, we present a novel incremental on-line semi-supervised learning model that reduces the need of large training sets for estimating the parameters of statistical models. Compared to other semi-supervised techniques, our method yields an on-line incremental re-training and segmentation instead of the off-line incremental re-training and segmentation more commonly found in the literature. Another innovation of our approach is that we use a statistical model based on deep learning architectures, which are easily adapted to this on-line incremental learning framework. We show that our fully automatic LV segmentation method achieves state-of-the-art accuracy with training sets containing less than twenty annotated images. © 2011 IEEE.


Martins A.F.T.,Carnegie Mellon University | Martins A.F.T.,Telecommunications Institute of Portugal | Smith N.A.,Carnegie Mellon University | Aguiar P.M.Q.,Institute Sistemas e Robotica | Figueiredo M.A.T.,Telecommunications Institute of Portugal
EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference | Year: 2011

Dual decomposition has been recently proposed as a way of combining complementary models, with a boost in predictive power. However, in cases where lightweight decompositions are not readily available (e.g., due to the presence of rich features or logical constraints), the original subgradient algorithm is inefficient. We sidestep that difficulty by adopting an augmented Lagrangian method that accelerates model consensus by regularizing towards the averaged votes. We show how first-order logical constraints can be handled efficiently, even though the corresponding subproblems are no longer combinatorial, and report experiments in dependency parsing, with state-of-the-art results. © 2011 Association for Computational Linguistics.


Luis M.,New University of Lisbon | Luis M.,Telecommunications Institute of Portugal | Furtado A.,New University of Lisbon | Furtado A.,Telecommunications Institute of Portugal | And 5 more authors.
IEEE Communications Letters | Year: 2013

Most of the models intended to describe the throughput of Primary (PUs) and Secondary (SUs) users of Cognitive Radio Networks (CRNs) assume that PUs only change their activity state (ON/OFF) in the beginning of each SU's operation cycle, admitting that PUs are synchronized with SU's operation cycle. This letter characterizes a more realistic scenario where PUs can randomly change their activity state during the SU's operation cycle. We derive an analytical model for the PU's throughput and its validation is assessed through simulation results. The analysis shows that assuming synchronized PUs leads to an undervaluation of the interference caused to PUs, and the interference decreases as more SU's operation cycles are performed per ON/OFF PU's activity state. © 1997-2012 IEEE.


Nascimento J.C.,Institute Sistemas e Robotica
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference | Year: 2010

We propose a improved Gradient Vector Flow (iGVF) for active contour detection. The algorithm herein proposed allows to surpass the problems of the GVF, which occur in noisy images with cluttered background. We experimentally illustrate that the proposed modified version of the GVF algorithm has a better performance in noisy images. The main difference concerns the use of more robust and informative features (edge segments) which significantly reduce the influence of noise. Experiments with real data from several image modalities are presented to illustrate the performance of the proposed approach.


Martins A.F.T.,Carnegie Mellon University | Martins A.F.T.,Telecommunications Institute of Portugal | Smith N.A.,Carnegie Mellon University | Aguiar P.M.Q.,Institute Sistemas e Robotica | Figueiredo M.A.T.,Telecommunications Institute of Portugal
EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference | Year: 2011

Linear models have enjoyed great success in structured prediction in NLP. While a lot of progress has been made on efficient training with several loss functions, the problem of endowing learners with a mechanism for feature selection is still unsolved. Common approaches employ ad hoc filtering or L 1-regularization; both ignore the structure of the feature space, preventing practicioners from encoding structural prior knowledge. We fill this gap by adopting regularizers that promote structured sparsity, along with efficient algorithms to handle them. Experiments on three tasks (chunking, entity recognition, and dependency parsing) show gains in performance, compactness, and model interpretability. © 2011 Association for Computational Linguistics.


Nascimento J.C.,Institute Sistemas e Robotica | Marques J.S.,Institute Sistemas e Robotica | Figueiredo M.A.T.,Telecommunications Institute of Portugal
Proceedings - International Conference on Image Processing, ICIP | Year: 2010

We propose a method to classify human trajectories, modeled by a set of motion vector fields, each tailored to describe a specific motion regime. Trajectories are modeled as being composed of segments corresponding to different motion regimes, each generated by one of the underlying motion fields. Switching among the motion fields follows a probabilistic mechanism, described by a field of stochastic matrices. This yields a space-dependent motion model which can be estimated using an expectation-maximization (EM) algorithm. To address the model selection question (how many fields to use?), we adopt a discriminative criterion based on classification accuracy on a held out set. Experiments with real data (human trajectories in a shopping mall) illustrate the ability of the proposed approach to classify complex trajectories into high level classes (client versus non-client). © 2010 IEEE.


Nascimento J.C.,Institute Sistemas e Robotica | Marques J.S.,Institute Sistemas e Robotica | Marques J.S.,University of Lisbon
2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 | Year: 2010

We propose a improved Gradient Vector Flow (iGVF) for active contour detection. The algorithm herein proposed allows to surpass the problems of the GVF, which occur in noisy images with cluttered background. We experimentally illustrate that the proposed modified version of the GVF algorithm has a better performance in noisy images. The main difference concerns the use of more robust and informative features (edge segments) which significantly reduce the influence of noise. Experiments with real data from several image modalities are presented to illustrate the performance of the proposed approach. © 2010 IEEE.


Seabra J.C.,Institute Sistemas e Robotica | Sanches J.M.,Institute Sistemas e Robotica
2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings | Year: 2010

The information encoded in ultrasound speckle is often discarded but it is widely recognized that this phenomenon is dependent of the intrinsic acoustic properties of tissues. In this paper we propose a robust method to estimate the despeckled and speckle components from the ultrasound data with the purpose of tissue characterization. A de-speckling method, which can conveniently work with either Radio Frequency (RF) or B-mode data, contributes to an improvement on the visualization of anatomical details, while providing useful fields from where echogenicity and texture features can be extracted. The adequacy of the RF image retrieval and despeckling methods are tackled using both synthetic and real ultrasonic data. ©2010 IEEE.


Martins A.F.T.,Carnegie Mellon University | Smith N.A.,Carnegie Mellon University | Xing E.P.,Carnegie Mellon University | Aguiar P.M.Q.,Institute Sistemas e Robotica | And 3 more authors.
EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference | Year: 2010

We present a unified view of two state-of-the-art non-projective dependency parsers, both approximate: the loopy belief propagation parser of Smith and Eisner (2008) and the relaxed linear program of Martins et al. (2009). By representing the model assumptions with a factor graph, we shed light on the optimization problems tackled in each method. We also propose a new aggressive online algorithm to learn the model parameters, which makes use of the underlying variational representation. The algorithm does not require a learning rate parameter and provides a single framework for a wide family of convex loss functions, including CRFs and structured SVMs. Experiments show state-of-the-art performance for 14 languages. © 2010 Association for Computational Linguistics.


Afonso M.V.,Institute Sistemas e Robotica | Marques J.S.,Institute Sistemas e Robotica | Nascimento J.C.,Institute Sistemas e Robotica
ICPRAM 2012 - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods | Year: 2012

Multiple motion fields are an efficient way of summarising the movement of objects in a scene and allow an automatic classification of objects activities in the scene. However, their estimation relies on some kind of supervised learning e.g., using manually edited trajectories. This paper proposes an automatic method for the estimation of multiple motion fields. The proposed algorithm detects multiple moving objects and their velocities in a video sequence using optical flow. This leads to a sequence of centroids and corresponding velocity vectors. A matching algorithm is then applied to group the centroids into trajectories, each of them describing the movement of an object in the scene. The paper shows that motion fields can be reliably estimated from the detected trajectories leading to a fully automatic procedure for the estimation of multiple motion fields.

Loading Institute Sistemas e Robotica collaborators
Loading Institute Sistemas e Robotica collaborators