1 code implementation • 27 Dec 2019 • Lourenço V. Pato, Renato Negrinho, Pedro M. Q. Aguiar
In this setting, we use a bidirectional RNN with attention for contextual rescoring and introduce a training target that uses the IoU with ground truth to maximize AP for the given set of detections.
1 code implementation • 8 May 2013 • João F. C. Mota, João M. F. Xavier, Pedro M. Q. Aguiar, Markus Püschel
Our contribution is a communication-efficient distributed algorithm that finds a vector $x^\star$ minimizing the sum of all the functions.
Optimization and Control Information Theory Information Theory
2 code implementations • NeurIPS 2020 • André F. T. Martins, António Farinhas, Marcos Treviso, Vlad Niculae, Pedro M. Q. Aguiar, Mário A. T. Figueiredo
Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e. g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation).
Ranked #36 on Visual Question Answering (VQA) on VQA v2 test-std
1 code implementation • 4 Aug 2021 • André F. T. Martins, Marcos Treviso, António Farinhas, Pedro M. Q. Aguiar, Mário A. T. Figueiredo, Mathieu Blondel, Vlad Niculae
In contrast, for finite domains, recent work on sparse alternatives to softmax (e. g., sparsemax, $\alpha$-entmax, and fusedmax), has led to distributions with varying support.
1 code implementation • 7 Sep 2021 • Manuel Madeira, Renato Negrinho, João Xavier, Pedro M. Q. Aguiar
First-order methods for stochastic optimization have undeniable relevance, in part due to their pivotal role in machine learning.
no code implementations • 7 Apr 2021 • António Farinhas, André F. T. Martins, Pedro M. Q. Aguiar
Visual attention mechanisms are a key component of neural network models for computer vision.