Pau Rodriguez

Pau Rodriguez

Auto-generated profile, based on publicly available information

Pau Rodriguez

Element AI

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 February 2017 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
PRPau Rodriguez
Pau Rodriguez
GCGuillem Cucurull
Guillem Cucurull
JGJordi Gonzalez
Jordi Gonzalez
JGJosep M. Gonfaus
Josep M. Gonfaus
KNKamal Nasrollahi
Kamal Nasrollahi
FRF. Xavier Roca
F. Xavier Roca
Pain is an unpleasant feeling that has been shown to be an important factor for the recovery of patients. Since this is costly in human resources and difficult to do objectively, there is the need for automatic systems to measure it. In this paper, contrary to current state-of-the-art techniques in pain assessment, which are based on facial features only, we suggest that the performance can be enhanced by feeding the raw frames to deep learning models, outperforming the latest state-of-the-art results while also directly facing the problem of imbalanced data. As a baseline, our approach first uses convolutional neural networks (CNNs) to learn facial features from VGG_Faces, which are then linked to a long short-term memory to exploit the temporal relation between video frames. We further compare the performances of using the so popular schema based on the canonically normalized appearance versus taking into account the whole image. As a result, we outperform current state-of-the-art area under the curve performance in the UNBC-McMaster Shoulder Pain Expression Archive Database. In addition, to evaluate the generalization properties of our proposed methodology on facial motion recognition, we also report competitive results in the Cohn Kanade+ facial expression database.

13 November 2020
Verified
Book Chapter
Closed access
PDF file
PRPau Rodríguez
Pau Rodríguez
ILIssam Laradji
Issam Laradji
ADAlexandre Drouin
Alexandre Drouin
ALAlexandre Lacoste
Alexandre Lacoste

17 August 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
GHGabriel Huang
Gabriel Huang
ILIssam Laradji
Issam Laradji
DVDavid Vazquez
David Vazquez
SLSimon Lacoste-Julien
Simon Lacoste-Julien
PRPau Rodriguez
Pau Rodriguez
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel (unseen) object classes with little data, it still requires prior training on many labeled examples of base (seen) classes. On the other hand, self-supervised methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection. Combining few-shot and self-supervised object detection is a promising research direction. In this survey, we review and characterize the most recent approaches on few-shot and self-supervised object detection. Then, we give our main takeaways and discuss future research directions. Project page: https://gabrielhuang.github.io/fsod-survey/

15 July 2019 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
PRPau Rodriguez
Pau Rodriguez
DVDiego Velazquez
Diego Velazquez
GCGuillem Cucurull
Guillem Cucurull
JGJosep M. Gonfaus
Josep M. Gonfaus
FRF. Xavier Roca
F. Xavier Roca
JGJordi Gonzalez
Jordi Gonzalez
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 of samples of the same class can be more different than those from different classes. This issue is mainly due to changes in deformation, pose, and the presence of clutter. In the literature, attention has been one of the most successful strategies to handle the aforementioned problems. Attention has been typically implemented in neural networks by selecting the most informative regions of the image that improve classification. In contrast, in this paper, attention is not applied at the image level but to the convolutional feature activations. In essence, with our approach, the neural model learns to attend to lower-level feature activations without requiring part annotations and uses those activations to update and rectify the output likelihood distribution. The proposed mechanism is modular, architecture-independent and efficient in terms of both parameters and computation required. Experiments demonstrate that well-known networks such as Wide Residual Networks and ResNeXt, when augmented with our approach, systematically improve their classification accuracy and become more robust to changes in deformation and pose and to the presence of clutter. As a result, our proposal reaches state-of-the-art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford Dogs, and UEC-Food100 while obtaining competitive performance in ImageNet, CIFAR-100, CUB200 Birds, and Stanford Cars. In addition, we analyze the different components of our model, showing that the proposed attention modules succeed in finding the most discriminative regions of the image. Finally, as a proof of concept, we demonstrate that with only local predictions, an augmented neural network can successfully classify an image before reaching any fully connected layer, thus reducing the computational amount up to 10%.

1 February 2022 in Artificial Intelligence
Verified
Journal Article
Closed access
VLVincenzo Lomonaco
Vincenzo Lomonaco
LPLorenzo Pellegrini
Lorenzo Pellegrini
PRPau Rodriguez
Pau Rodriguez
MCMassimo Caccia
Massimo Caccia
QSQi She
Qi She
DMDavide Maltoni
Davide Maltoni

18 May 2022 in IEEE Access
Verified
Journal Article
Open access
PBParichehr Behjati
Parichehr Behjati
PRPau Rodriguez
Pau Rodriguez
CTCarles Fernandez Tena
Carles Fernandez Tena
AMArmin Mehri
Armin Mehri
FRF. Xavier Roca
F. Xavier Roca
JGJordi Gonzalez
Jordi Gonzalez
Recently, deep convolutional neural networks (CNNs) have provided outstanding performance in single image super-resolution (SISR). Despite their remarkable performance, the lack of high-frequency information in the recovered images remains a core problem. Moreover, as the networks increase in depth and width, deep CNN-based SR methods are faced with the challenge of computational complexity in practice. A promising and under-explored solution is to adapt the amount of compute based on the different frequency bands of the input. To this end, we present a novel Frequency-based Enhancement Block (FEB) which explicitly enhances the information of high frequencies while forwarding low-frequencies to the output. In particular, this block efficiently decomposes features into low- and high-frequency and assigns more computation to high-frequency ones. Thus, it can help the network generate more discriminative representations by explicitly recovering finer details. Our FEB design is simple and generic and can be used as a direct replacement of commonly used SR blocks with no need to change network architectures. We experimentally show that when replacing SR blocks with FEB we consistently improve the reconstruction error, while reducing the number of parameters in the model. Moreover, we propose a lightweight SR model — Frequency-based Enhancement Network (FENet) — based on FEB that matches the performance of larger models. Extensive experiments demonstrate that our proposal performs favorably against the state-of-the-art SR algorithms in terms of visual quality, memory footprint, and inference time. The code is available at https://github.com/pbehjatii/FENet