activity
20172020
most citedEnd-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks

18 citations · 22 across the 2 of their papers we have counts for

collaborators

8 papers

eess.IV20204 cited

Hierarchical Residual Attention Network for Single Image Super-Resolution

Parichehr Behjati, Pau Rodriguez, Armin Mehri +3

Convolutional neural networks are the most successful models in single image super-resolution. Deeper networks, residual connections, and attention mechanisms have further improved…

eess.IV2020

OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network

Parichehr Behjati, Pau Rodriguez, Armin Mehri +3

Super-resolution (SR) has achieved great success due to the development of deep convolutional neural networks (CNNs). However, as the depth and width of the networks increase, CNN-…

cs.CV2019

Pay attention to the activations: a modular attention mechanism for fine-grained image recognition

Pau Rodríguez López, Diego Velazquez Dorta, Guillem Cucurull Preixens +3

Fine-grained image recognition is central to many multimedia tasks such as search, retrieval and captioning. Unfortunately, these tasks are still challenging since the appearance o…

cs.CV2018

From 2D to 3D Geodesic-based Garment Matching

Meysam Madadi, Egils Avots, Sergio Escalera +3

A new approach for 2D to 3D garment retexturing is proposed based on Gaussian mixture models and thin plate splines (TPS). An automatically segmented garment of an individual is ma…

cs.CV2018

Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery

Pau Rodríguez, Josep M. Gonfaus, Guillem Cucurull +2

We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature activations without requiri…

cs.CV2018

Beyond One-hot Encoding: lower dimensional target embedding

Pau Rodríguez, Miguel A. Bautista, Jordi Gonzàlez +1

Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, One-hot encoding is the most prevalent strategy due to its simplicity. However, thi…