@article {aGene-Molad, title = {AmodalAppleSize_RGB-D dataset: RGB-D images of apple trees annotated with modal and amodal segmentation masks for fruit detection, visibility and size estimation}, journal = {Data in Brief}, volume = {52}, year = {2024}, month = {02/2024}, abstract = {

The present dataset comprises a collection of RGB-D apple tree images that can be used to train and test computer vision-based fruit detection and sizing methods. This dataset encompasses two distinct sets of data obtained from a Fuji and an Elstar apple orchards. The Fuji apple orchard sub-set consists of 3925 RGB-D images containing a total of 15335 apples annotated with both modal and amodal apple segmentation masks. Modal masks denote the visible portions of the apples, whereas amodal masks encompass both visible and occluded apple regions. Notably, this dataset is the first public resource to incorporate on-tree fruit amodal masks. This pioneering inclusion addresses a critical gap in existing datasets, enabling the development of robust automatic fruit sizing methods and accurate fruit visibility estimation, particularly in the presence of partial occlusions. Besides the fruit segmentation masks, the dataset also includes the fruit size (calliper) ground truth for each annotated apple. The second sub- set comprises 2731 RGB-D images capturing five Elstar apple trees at four distinct growth stages. This sub-set includes mean diameter information for each tree at every growth stage and serves as a valuable resource for evaluating fruit sizing methods trained with the first sub-set. The present data was employed in the research papers titled "Looking behind occlusions: a study on amodal segmentation for robust on-tree apple fruit size estimation" [1] and {\textquotedblleft}Simultaneous fruit detection and size estimation using multitask deep neural networks{\textquotedblright} [2].

}, keywords = {Agricultural robotics, amodal segmentation, depth image, Fruit measurement, Fruit visibility, Instance Segmentation, modal segmentation, Yield prediction}, doi = {https://doi.org/10.1016/j.dib.2023.110000}, author = {Gen{\'e}-Mola, Jordi and Ferrer-Ferrer, M. and Hemming, J. and Dalfsen, P. and Hoog, D. and Sanz-Cortiella, R. and Rosell-Polo, Joan R. and Morros, J.R. and Ver{\'o}nica Vilaplana and Ruiz-Hidalgo, J. and Gregorio, Eduard} } @article {aCumplido-Mayoral22, title = {Biological Brain Age Prediction Using Machine Learning on Structural Neuroimaging Data: Multi-Cohort Validation Against Biomarkers of Alzheimer{\textquoteright}s Disease and Neurodegeneration stratified by sex}, journal = {eLife}, volume = {12}, year = {2023}, month = {04/2023}, abstract = {

Brain-age can be inferred from structural neuroimaging and compared to chronological age (brain-age delta) as a marker of biological brain aging. Accelerated aging has been found in neurodegenerative disorders like Alzheimer9s disease (AD), but its validation against markers of neurodegeneration and AD is lacking. Here, imaging-derived measures from the UK Biobank dataset (N=22,661) were used to predict brain-age in 2,314 cognitively unimpaired (CU) individuals at higher risk of AD and mild cognitive impaired (MCI) patients from four independent cohorts with available biomarker data: ALFA+, ADNI, EPAD and OASIS. Brain-age delta was associated with abnormal amyloid-β, more advanced stages (AT) of AD pathology and APOE-ε4 status. Brain-age delta was positively associated with plasma neurofilament light, a marker of neurodegeneration, and sex differences in the brain effects of this marker were found. These results validate brain-age delta as a non-invasive marker of biological brain aging related to markers of AD and neurodegeneration.

}, issn = {2050-084X}, doi = {https://doi.org/10.7554/eLife.81067}, author = {Irene Cumplido-Mayoral and Marina Garc{\'\i}a-Prat and Gregory Operto and Carles Falcon and Mahnaz Shekari and Raffaele Cacciaglia and Marta Mila-Aloma and Luigi Lorenzini and Carolina Minguillon and Jose Luis Molinuevo and Marc Suarez-Calvet and Ver{\'o}nica Vilaplana and Juan Domingo Gispert} } @conference {cCumplido-Mayoral23a, title = {Brain-age mediates the association between modifiable risk factors and cognitive decline early in the AD continuum}, booktitle = {Alzheimer{\textquoteright}s Association International Conference (AAIC)}, year = {2023}, month = {07/2023}, address = {Amsterdam, Netherlands}, author = {Irene Cumplido-Mayoral and Anna Brugulat-Serrat and Gonzalo S{\'a}nchez-Benavides and Armand Gonz{\'a}lez-Escalante and Federica Anastasi and Marta Mila-Aloma and Carles Falcon and Mahnaz Shekari and Raffaele Cacciaglia and Carolina Minguillon and Ver{\'o}nica Vilaplana and Juan D. Gispert} } @conference {cCumplido-Mayoral23, title = {Brain-age prediction and its associations with glial and synaptic CSF markers}, booktitle = {Alzheimer{\textquoteright}s Association International Conference}, year = {2023}, month = {07/2023}, address = {Amsterdam, Netherlands}, author = {Irene Cumplido-Mayoral and Marta Mila-Aloma and Carles Falcon and Raffaele Cacciaglia and Carolina Minguillon and Karine Fauria and Jose Luis Molinuevo and Ver{\'o}nica Vilaplana and Juan D. Gispert} } @phdthesis {dFernandez23, title = {Knowledge graph population from news streams}, volume = {Doctorate}, year = {2023}, month = {10/2023}, school = {Universitat Polit{\`e}cnica de Catalunya}, type = {Industrial}, address = {Barcelona, Catalonia}, abstract = {

Media producers publish large amounts of multimedia content online - both text, audio, image and video.\  As the online media market grows, the management and delivery of contents becomes a challenge. Semantic and linking technologies can be used to organize and exploit these contents through the use of knowledge graphs. This industrial doctorate dissertation addresses the problem of constructing knowledge resources and integrating them into a system used by media producers to manage and explore their contents. For that purpose, knowledge graphs and their maintenance through Information Extraction (IE) from news streams is studied. This thesis presents solutions for multimedia understanding and knowledge extraction from online news, and their exploitation in real product applications, and it is structured in three parts.

The first part consists on the construction of IE tools that will be used for knowledge graph population. For that, we built an holistic Entity Linking (EL) system capable of combining multimodal data inputs to extract a set of semantic entities that describe news content.\  The EL system is followed by a Relation Extraction (RE) model that predicts relations between pairs of entities with a novel method based on entity-type knowledge. The final system is capable of extracting triples describing the contents of a news article.

The second part focuses on the automatic construction of a news event knowledge graph. We present an online multilingual system for event detection and comprehension from media feeds, called VLX-Stories. The system retrieves information from news sites, aggregates them into events (event detection), and summarizes them by extracting semantic labels of its most relevant entities (event representation) in order to answer four Ws from journalism: who, what, when and where.\  This part of the thesis deals with the problems of Topic Detection and Tracking (TDT), topic modeling and event representation.

The third part of the thesis builds on top of the models developed in the two previous parts to populate a knowledge graph from aggregated news.
The system is completed with an emerging entity detection module, which detects mentions of novel people appearing on the news and creates new knowledge graph entities from them. Finally, data validation and triple classification tools are added to increase the quality of the knowledge graph population.

This dissertation addresses many general knowledge graph and information extraction problems, like knowledge dynamicity, self-learning, and quality assessment. Moreover, as an industrial work, we provide solutions that were deployed in production and verify our methods with real customers.

}, keywords = {Entity Linking, Information Extraction, Knowledge Graph Population, Named Entity Disambiguation, Named Entity Recognition, Natural Language Processing, Relation Extraction, Topic Detection and Tracking, Topic Modeling, Triple Validation}, author = {Fern{\`a}ndez, D{\`e}lia and Marqu{\'e}s, F. and Xavier Gir{\'o}-i-Nieto and Bou-Balust, Elisenda} } @article {aGene-Mola23, title = {Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation}, journal = {Computers and Electronics in Agriculture}, volume = {209}, year = {2023}, month = {04/2023}, abstract = {

The detection and sizing of fruits with computer vision methods is of interest because it provides relevant information to improve the management of orchard farming. However, the presence of partially occluded fruits limits the performance of existing methods, making reliable fruit sizing a challenging task. While previous fruit segmentation works limit segmentation to the visible region of fruits (known as modal segmentation), in this work we propose an amodal segmentation algorithm to predict the complete shape, which includes its visible and occluded regions. To do so, an end-to-end convolutional neural network (CNN) for simultaneous modal and amodal instance segmentation was implemented. The predicted amodal masks were used to estimate the fruit diameters in pixels. Modal masks were used to identify the visible region and measure the distance between the apples and the camera using the depth image. Finally, the fruit diameters in millimetres (mm) were computed by applying the pinhole camera model. The method was developed with a Fuji apple dataset consisting of 3925 RGB-D images acquired at different growth stages with a total of 15,335 annotated apples, and was subsequently tested in a case study to measure the diameter of Elstar apples at different growth stages. Fruit detection results showed an F1-score of 0.86 and the fruit diameter results reported a mean absolute error (MAE) of 4.5\ mm and R2\ =\ 0.80 irrespective of fruit visibility. Besides the diameter estimation, modal and amodal masks were used to automatically determine the percentage of visibility of measured apples. This feature was used as a confidence value, improving the diameter estimation to MAE\ =\ 2.93\ mm and R2\ =\ 0.91 when limiting the size estimation to fruits detected with a visibility higher than 60\%. The main advantages of the present methodology are its robustness for measuring partially occluded fruits and the capability to determine the visibility percentage. The main limitation is that depth images were generated by means of photogrammetry methods, which limits the efficiency of data acquisition. To overcome this limitation, future works should consider the use of commercial RGB-D sensors. The code and the dataset used to evaluate the method have been made publicly available at\ https://github.com/GRAP-UdL-AT/Amodal_Fruit_Sizing.

}, keywords = {deep learning, Fruit detection, Fruit measurement, Fruit visibility, Precision agriculture, Yield estimation}, issn = {ISSN 0168-1699}, doi = {https://doi.org/10.1016/j.compag.2023.107854}, url = {https://authors.elsevier.com/sd/article/S0168-1699(23)00242-9}, author = {Gen{\'e}-Mola, Jordi and Ferrer-Ferrer, M. and Gregorio, Eduard and Blok, P. M. and Hemming, J. and Morros, J.R. and Rosell-Polo, Joan R. and Ver{\'o}nica Vilaplana and Ruiz-Hidalgo, J.} } @conference {cLozano23, title = {Optical Phased Array Antenna Apodization for Lidar in Autonomous Vehicles}, booktitle = {XIII Reuni{\'o}n OptoElectr{\'o}nica}, year = {2023}, month = {06/2023}, publisher = {OPTOEL}, organization = {OPTOEL}, address = {Sevilla, Spain}, abstract = {

This paper presents the specific design of an Optical Phased Array antenna (OPA) to apodize the emission of a lidar in the context of a project where diverse optoelectronic sensors such as cameras, radars, and commercial lidars are used to provide data in order to fuse them and develop perception for robots as future autonomous vehicles. While mechanical based lidars are already commercially available, this work focuses on designing much more robust and potentially cheaper lidars based on photonic integrated circuits and energy optimization through the apodization of the emission of the OPA.

}, url = {https://www.optoel2023.es/94299/section/44205/optoel-2023.html}, author = {Jos{\'e} Lozano and Humberto Jim{\'e}nez and Sergio Torres and Pau Biosca and Bernat Fontanet and Jorge Pinazo and Adolfo Ler{\'\i}n and Federico Dios and Casas, J. and Jos{\'e} Antonio L{\'a}zaro} } @article {aFerrer-Ferrer, title = {Simultaneous Fruit Detection and Size Estimation Using Multitask Deep Neural Networks }, journal = {Biosystems Engineering}, volume = {233}, year = {2023}, month = {09/2023}, pages = {63-75}, abstract = {

The measurement of fruit size is of great interest to estimate the yield and predict the harvest resources in advance. This work proposes a novel technique for in-field apple detection and measurement based on Deep Neural Networks. The proposed\ \ framework was trained with RGB-D data and consists of an end-to-end multitask Deep Neural Network architecture 13 specifically designed to perform the following tasks: 1) detection and segmentation of each fruit from its surroundings; 2) estimation of the diameter of each detected fruit. The methodology was tested with a total of 15335 annotated apples at different growth stages, with diameters varying from 27 mm to 95 mm. Fruit detection results reported an F1-score for apple detection of 0.88 and a mean absolute error of diameter estimation of 5.64 mm. These are state-of-the-art results with the additional advantages of: a) using an end-to-end multitask trainable network; b) an efficient and fast inference speed; and c) being based on RGB-D data which can be acquired with affordable depth cameras. On the contrary, the main disadvantage is the need of annotating a large amount of data with fruit masks and diameter ground truth to train the model. Finally, a fruit visibility analysis showed an improvement in the prediction when limiting the measurement to apples above 65\% of visibility (mean absolute error of 5.09 mm). This suggests that future works should develop a method for automatically identifying the most visible apples and discard the prediction of highly occluded fruits.

}, keywords = {deep learning, Fruit measurement, Fruit visibility, Precision agriculture, Yield estimation}, doi = {https://doi.org/10.1016/j.biosystemseng.2023.07.010}, author = {Ferrer-Ferrer, M. and Ruiz-Hidalgo, J. and Gregorio, Eduard and Ver{\'o}nica Vilaplana and Morros, J.R. and Gen{\'e}-Mola, Jordi} } @conference {cCombaliae, title = {Artificial intelligence to predict positivity of sentinel lymph node biopsy in melanoma patients}, booktitle = {European Association of Dermato Oncology (EADO 2022)}, year = {2022}, month = {04/2022}, author = {Marc Combalia and Sebastian Podlipnik and Carlos Hernandez and Sergio Garc{\'\i}a and Joan Ficapal and Julio Burgos and Ver{\'o}nica Vilaplana and Josep Malvehy} } @conference {cCumplido-Mayoral, title = {Biological Brain Age Prediction Using Machine Learning on Structural Neuroimaging Data: Multi-Cohort Validation Against Biomarkers of Alzheimer{\textquoteright}s Disease and Neurodegeneration}, booktitle = {Alzheimer{\textquoteright}s Association International Conference}, year = {2022}, month = {07/2022}, author = {Irene Cumplido-Mayoral and Marina Garc{\'\i}a-Prat and Greg Operto and Carles Falcon and Mahnaz Shekari and Raffaele Cacciaglia and Marta Mila-Aloma and Marc Suarez Calvet and Ver{\'o}nica Vilaplana and Juan D. Gispert} } @article {aTemprana-Salvador22, title = {DigiPatICS: Digital Pathology Transformation of the Catalan Health Institute Network of 8 Hospitals - Planification, Implementation and Preliminary Results}, journal = {Diagnostics}, volume = {12}, year = {2022}, month = {03/2022}, chapter = {852}, abstract = {

Complete digital pathology transformation for primary histopathological diagnosis is a challenging yet rewarding endeavor. Its advantages are clear with more efficient workflows, but there are many technical and functional difficulties to be faced. The Catalan Health Institute (ICS) has started its DigiPatICS project, aiming to deploy digital pathology in an integrative, holistic, and comprehensive way within a network of 8 hospitals, over 168 pathologists, and over 1 million slides each year. We describe the bidding process and the careful planning that was required, followed by swift implementation in stages. The purpose of the DigiPatICS project is to increase patient safety and quality of care, improving diagnosis and the efficiency of processes in the pathological anatomy departments of the ICS through process improvement, digital pathology, and artificial intelligence tools.

}, keywords = {artificial intelligence, computational pathology, deep learning, digital pathology, implementation, LIS, primary diagnosis, telepathology, workflow}, doi = {10.3390/diagnostics12040852}, url = {https://www.mdpi.com/2075-4418/12/4/852}, author = {Jordi Temprana-Salvador and Pau L{\'o}pez-Garc{\'\i}a and Josep Castellv{\'\i} Vives and Llu{\'\i}s de Haro and Eudald Ballesta and Matias Rojas Abusleme and Miquel Arrufat and Ferran Marques and Casas, J. and Carlos Gallego and Laura Pons and Jos{\'e} Luis Mate and Pedro Luis Fern{\'a}ndez and Eugeni L{\'o}pez-Bonet and Ramon Bosch and Salom{\'e} Mart{\'\i}nez and Santiago Ram{\'o}n y Cajal and Xavier Matias-Guiu} } @article {aa, title = {QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation--Analysis of Ranking Metrics and Benchmarking Results}, journal = {Journal of Machine Learning for Biomedical Imaging}, year = {2022}, month = {08/2022}, abstract = {

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at:\ this https URL.

}, url = {https://www.melba-journal.org/papers/2022:026.html}, author = {Raghav Metha and Angelos Filos and Ujjwal Baid and Laura Mora and Ver{\'o}nica Vilaplana and Christos Davatzikos and Bjoern Menze and Spyridon Bakas and Yarin Gal and Tar Arbel} } @conference {cMayoral21a, title = {Brain structural alterations in cognitively unimpaired individuals with discordant amyloid-β PET and CSF Aβ42 status: findings using Machine Learning}, booktitle = {Alzheimer{\textquoteright}s Association International Conference}, year = {2021}, month = {07/2021}, author = {Irene Cumplido-Mayoral and Mahnaz Shekari and Gemma Salvad{\'o} and Greg Operto and Raffaele Cacciaglia and Carles Falcon and Aida Ni{\~n}erola Baiz{\'a}n and Andr{\'e}s Perissinotti and Carolina Minguillon and Karine Fauria and Ivonne Suridjan and Gwendlyn Kollmorgen and Jose Luis Molinuevo and Henrik Zetterberg and Kaj Blennow and Marc Suarez Calvet and Ver{\'o}nica Vilaplana and Juan D. Gispert} } @conference {cHernandez, title = {Implementation of personalized medicine in cutaneous melanoma patients aided by artificial intelligence}, booktitle = {10th World Congress of2 Melanoma / 17th EADO Congress}, year = {2021}, month = {04/2021}, author = {Carlos Hernandez and Anil Kiroglu and Sergio Garc{\'\i}a and Joan Ficapal and Julio Burgos and Sebastian Podlipnik and Neus Calbet and Susana Puig and Josep Malvehy and Ver{\'o}nica Vilaplana and Marc Combalia} } @conference {cMayoral21, title = {Machine learning on combined neuroimaging and plasma biomarkers for triaging participants of secondary prevention trials in Alzheimer{\textquoteright}s Disease}, booktitle = {Alzheimer{\textquoteright}s Association International Conference}, year = {2021}, month = {07/2021}, author = {Irene Cumplido-Mayoral and Gemma Salvad{\'o} and Mahnaz Shekari and Carles Falcon and Marta Mil{\`a} Alom{\`a} and Aida Ni{\~n}erola Baiz{\'a}n and Jose Luis Molinuevo and Henrik Zetterberg and Kaj Blennow and Marc Suarez Calvet and Ver{\'o}nica Vilaplana and Juan D. Gispert} } @conference {cPodlipnik21, title = {Personalized medicine in melanoma patients aided by artificial intelligence}, booktitle = {Clinical Translation of Medical Image Computing and Computer Assisted Interventions (CLINICCAI) Workshop at MICCAI}, year = {2021}, month = {09/2021}, abstract = {

The 8th Edition of the American Joint Committee on Cancer (AJCC) staging system1 is the current standard for classifying patients into prognostic and treatment groups. This classification is used to predict the evolution of the patient, and therefore treatment actions provided to the individual. However, patients at the same stage behave differently, indicating that the current classification system is often insufficient to provide a customized prognosis for each patient2. It is, therefore, necessary to improve patient classification into prognostic groups. Furthermore, patients{\textquoteright} systemic and surgical treatments often involve significant toxicities and morbidities that impact their quality of life (i.e., sentinel node biopsy is not needed for 80\% of the melanoma patients, 50\% of patients do not benefit from adjuvant treatment)3. Therefore, melanoma patients should benefit from a more precise risk estimation.

We create a survival dataset for melanoma risk estimation and train survival XGBoost algorithms4 to predict the mortality, relapse, and metastasis risk. We compare their performance to the AJCC 2018 risk stratification system. Furthermore, we train classifiers to predict the risk of a positive lymph node biopsy and distant metastasis on melanoma patients and compare the performance of the proposed system to the clinical practice.

}, author = {Sebastian Podlipnik and Carlos Hernandez and Anil Kiroglu and Sergio Garc{\'\i}a and Joan Ficapal and Julio Burgos and Neus Calbet and Susana Puig and Josep Malvehy and Ver{\'o}nica Vilaplana and Marc Combalia} } @conference {cMayoral21b, title = {Prediction of amyloid pathology in cognitively unimpaired individuals using structural MRI}, booktitle = {Alzheimer{\textquoteright}s Association International Conference}, year = {2021}, month = {07/2021}, author = {Irene Cumplido-Mayoral and Silvia Ingala and Luigi Lorenzini and Alle Meije Wink and Sven Haller and Jose Luis Molinuevo and Robin Wolz and Alessandro Palombit and Adam J Schwarz and Ga{\"e}l Chetelat and Pierre Payoux and Pablo Martinez-Lage and Giovanni Frisoni and Nick C Fox and Craig W Ritchie and Joanna M Wardlaw and Adam Waldman and Frederik Barkhof and Ver{\'o}nica Vilaplana and Juan D. Gispert} } @article {aPuig-Sitjes21, title = {Real-time detection of overloads on the plasma-facing components of Wendelstein 7-X}, journal = {Applied sciences (Basel)}, volume = {11}, year = {2021}, month = {12/2021}, chapter = {1}, issn = {2076-3417}, doi = {10.3390/app112411969}, url = {http://hdl.handle.net/2117/361558}, author = {Puig-Sitjes, A. and Jakubowski, M. and Naujoks, D. and Gao, Y. and Drewelow, P. and Niemann, H. and Felinger, J. and Casas, J. and Salembier, P. and Clemente, R.} } @conference {cFernandezf, title = {Enhancing Online Knowledge Graph Population with Semantic Knowledge}, booktitle = {19th International Semantic Web Conference (ISWC)}, year = {2020}, month = {11/2020}, address = {Virtual}, abstract = {

Knowledge Graphs (KG) are becoming essential to organize, represent and store the world{\textquoteright}s knowledge, but they still rely heavily on humanly-curated structured data. Information Extraction (IE) tasks, like disambiguating entities and relations from unstructured text, are key to automate KG population. However, Natural Language Processing (NLP) methods alone can not guarantee the validity of the facts extracted and may introduce erroneous information into the KG.\ This work presents an end-to-end system that combines Semantic Knowledge and Validation techniques with NLP methods, to provide KG population of novel facts from clustered news events.\ The contributions of this paper are two-fold: First, we present a novel method for including entity-type knowledge into a Relation Extraction model, improving F1-Score over the baseline with TACRED and TypeRE datasets. Second, we increase the precision by adding data validation on top of the Relation Extraction method. These two contributions are combined in an industrial pipeline for automatic KG population over aggregated news, demonstrating increased data validity when performing online learning from unstructured web data. Finally, the TypeRE and AggregatedNewsRE datasets build to benchmark these results are also published to foster future research in this field.

}, keywords = {Data Validation, Knowledge Graph, Relation Extraction}, author = {Fern{\`a}ndez, D{\`e}lia and Rimmek, Joan Marco and Espadaler, Joan and Garolera, Blai and Barja, Adri{\`a} and Codina, Marc and Sastre, Marc and Xavier Gir{\'o}-i-Nieto and Riveiro, Juan Carlos and Bou-Balust, Elisenda} } @article {aCasamitjanab, title = {NeAT: a nonlinear analysis toolbox for neuroimaging}, journal = {Neuroinformatics}, year = {2020}, month = {03/2020}, abstract = {

NeAT is a modular, flexible and user-friendly neuroimaging analysis toolbox for modeling linear and nonlinear effects overcoming the limitations of the standard neuroimaging methods which are solely based on linear models. NeAT provides a wide range of statistical and machine learning non-linear methods for model estimation, several metrics based on curve fitting and complexity for model inference and a graphical user interface (GUI) for visualization of results. We illustrate its usefulness on two study cases where non-linear effects have been previously established. Firstly, we study the nonlinear effects of Alzheimer{\textquoteright}s disease on brain morphology (volume and cortical thickness). Secondly, we analyze the effect of the apolipoprotein APOE-ε4 genotype on brain aging and its interaction with age. NeAT is fully documented and publicly distributed at https://imatge-upc.github.io/neat-tool/.

}, keywords = {Alzheimer{\textquoteright}s disease, APOE, GAM, GLM, inference, neuroimaging, nonlinear., SVR}, doi = {10.1007/s12021-020-09456-w}, url = {https://link.springer.com/article/10.1007/s12021-020-09456-w}, author = {Adri{\`a} Casamitjana and Ver{\'o}nica Vilaplana and Santi Puch and Asier Aduriz and Carlos Lopez and G. Operto and R. Cacciaglia and C. Falcon and J.L. Molinuevo and Juan D. Gispert} } @conference {cPuig-Sitjes20, title = {Strategy for the real-time detection of thermal events on the plasma facing components of Wendelstein 7-X}, booktitle = {31st Symposium on Fusion Technology (SOFT2020)}, year = {2020}, month = {09/2020}, address = {Dubrovnik, Croatia}, abstract = {

Wendelstein 7-X (W7-X), the most advanced fusion experiment in the stellarator line, aims at demonstrating the feasibility of the stellarator concept as a future fusion power plant. It is planned to restart operation by the end of 2021 with a high heat flux divertor and water-cooled plasma facing components (PFCs) to demonstrate steady-state operation. With plasma energy limits starting at 1 GJ and gradually increasing to 18 GJ over several experimental campaigns, the PFCs have to be protected from overheating. For that, a fully autonomous system is required in order to prevent damage to the plasma facing components due to thermal events.
During the last experimental campaign, when W7-X was equipped with inertially cooled test divertor units, extensive experience was gained with the preliminary design of the thermal event detection system. By then, the system was not yet real-time capable and it was not fully automated, requiring manual supervision between discharges. This experience, however, allowed to prove the validity of some design concepts and to define the new strategy towards the protection of the machine in steady-state operation, when the system will be connected to the Interlock System and the feedback control.
In this work, the design of the real-time thermal event detection system for W7-X for steady-state operation is presented. The system is based on the thermography and video diagnostics to monitor the divertor units, the baffles, and the wall heat-shields and panels. It will be implemented on a real-time system and integrated in CoDaC{\textquoteright}s safety infrastructure. The system relies on computer vision and machine learning techniques to perform a spatio-temporal analysis to detect and classify the thermal events and to perform a risk evaluation. The results and the main conclusions drawn from the analysis of the data from the past campaign are reported.

}, url = {http://hdl.handle.net/21.11116/0000-0007-7FF5-7}, author = {Puig-Sitjes, A. and Jakubowski, M. and Fellinger, J. and Drewelow, P. and Gao, Y. and Niemann, H. and Sunn-Pedersen, T. and K{\"o}nig, R. and Naujoks, D. and Winter, A. and Laqua, H. and Dumke, S. and Moncada, V. and Belafdil, C. and Mitteau, R. and Aumeunier, M.-H. and Pisano, F. and Aymerich, E. and Cannas, B. and Kocsis, G. and Szepesi, T. and Cseh, G. and Szabolics, T. and Casas, J. and Morros, J.R. and Salembier, P. and Clemente, R. and Cobos, M. and I. Caminal and Palacios Corral, A. and Moreno Punzano, A. and Quiceno Lopera, S.} } @article {aWang19, title = {Benchmark on Automatic 6-month-old Infant Brain Segmentation Algorithms: The iSeg-2017 Challenge}, journal = {IEEE Transactions on Medical Imaging}, year = {2019}, month = {2019/2/27}, abstract = {

Accurate segmentation of infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is an indispensable foundation for early studying of brain growth patterns and morphological changes in neurodevelopmental disorders. Nevertheless, in the isointense phase (approximately 6-9 months of age), due to inherent myelination and maturation process, WM and GM exhibit similar levels of intensity in both T1-weighted (T1w) and T2-weighted (T2w) MR images, making tissue segmentation very challenging. Despite many efforts were devoted to brain segmentation, only few studies have focused on the segmentation of 6-month infant brain images. With the idea of boosting methodological development in the community, iSeg-2017 challenge (http://iseg2017.web.unc.edu) provides a set of 6-month infant subjects with manual labels for training and testing the participating methods. Among the 21 automatic segmentation methods participating in iSeg-2017, we review the 8 top-ranked teams, in terms of Dice ratio, modified Hausdorff distance and average surface distance, and introduce their pipelines, implementations, as well as source codes. We further discuss limitations and possible future directions. We hope the dataset in iSeg-2017 and this review article could provide insights into methodological development for the community.

}, doi = {10.1109/TMI.2019.2901712}, author = {Li Wang and Dong Nie and Guannan Li and Elodie Puybareau and Jose Dolz and Qian Zhang and Fan Wang and Jing Xia and Zhengwang Wu and Jiawei Chen and Kim-HanThung and Toan Duc Bui and Jitae Shin and Guodong Zeng and Guoyan Zheng and Vladimir S. Fonov and Andrew Doyle and Yongchao Xu and Pim Moeskops and Josien Pluim and Christian Desrosiers and Ismail Ben Ayed and Gerard Sanroma and Oualid Benkarim and Adri{\`a} Casamitjana and Ver{\'o}nica Vilaplana and Weili Lin and Gang Li and Dinggang Shen} } @conference {cCasamitjana19, title = {Detection of Amyloid Positive Cognitively unimpaired individuals using voxel-based machine learning on structural longitudinal brain MRI}, booktitle = {Alzheimer{\textquoteright}s Association International Conference}, year = {2019}, month = {07/2019}, author = {Adri{\`a} Casamitjana and P. Petrone and C. Falcon and M. Artigues and G. Operto and R. Cacciaglia and J.L. Molinuevo and Ver{\'o}nica Vilaplana and J.D. Gispert} } @article {aCasamitjana19, title = {Detection of Amyloid-Positive Cognitively Unimpaired Individuals Using Voxel-Based Machine Learning on Structural Longitudinal Brain MRI}, journal = {Alzheimer{\textquoteright}s \& Dementia}, volume = {15}, year = {2019}, month = {07/2019}, chapter = {752}, abstract = {

Magnetic resonance imaging (MRI) has unveiled specific AD alterations at different stages of the AD pathophysiologic continuum that constitutes what has been established as the {\textquoteleft}AD signature{\textquoteright}. To what extent MRI can detect amyloid-related cerebral changes from structural MRI in unimpaired individuals is still an area open for exploration.

}, issn = {1552-5260}, doi = {10.1016/j.jalz.2019.06.2796}, author = {Adri{\`a} Casamitjana and P. Petrone and C. Falcon and M. Artigues and G. Operto and R. Cacciaglia and J.L. Molinuevo and Ver{\'o}nica Vilaplana and J.D. Gispert} } @article {aPetrone, title = {Prediction of amyloid pathology in cognitively unimpaired individuals using voxelwise analysis of longitudinal structural brain MRI}, journal = {Alzheimer{\textquoteright}s Research \& Therapy}, volume = {11}, year = {2019}, month = {12/2019}, abstract = {

Background: Magnetic resonance imaging (MRI) has unveiled specific alterations at different stages of Alzheimer{\textquoteright}s disease (AD) pathophysiologic continuum constituting what has been established as {\textquoteleft}AD signature{\textquoteright}. To what extent MRI can detect amyloid-related cerebral changes from structural MRI in cognitively unimpaired individuals is still an area open for exploration.

Method: Longitudinal 3D-T1 MRI scans were acquired from a subset of the ADNI cohort comprising 403 subjects: 79 controls (Ctrls), 50 preclinical AD (PreAD), 274 MCI and dementia due to AD (MCI/AD). Amyloid CSF was used as gold-standard measure with established cut-offs (\<192pg/mL) to establish diagnostic categories. Cognitively unimpaired individuals were defined as Ctrls if were amyloid negative and PreAD otherwise. The MCI/AD group was amyloid positive. Only subjects with the same diagnostic category at baseline and follow-up visits were considered for the study. Longitudinal morphometric analysis was performed using SPM12 to calculate Jacobian determinant maps. Statistical analysis was carried out on these jacobian maps to identify structural changes that were significantly different between diagnostic categories. A machine learning classifier was applied on Jacobian determinant maps to predict the presence of abnormal amyloid levels in cognitively unimpaired individuals. The performance of this classifier was evaluated using receiver operating characteristic curve analysis and as a function of the follow-up time between MRI scans. We applied a cost function to assess the benefit of using this classifier in the triaging of individuals in a clinical trial-recruitment setting.

Results: The optimal follow-up time for classification of Ctrls vs PreAD was Δt\>2.5 years and hence, only subjects within this temporal span are used for evaluation (15 Ctrls, 10 PreAD). The longitudinal voxel-based classifier achieved an AUC=0.87 (95\%CI:0.72-0.97). The brain regions that showed the highest discriminative power to detect amyloid abnormalities were the medial, inferior and lateral temporal lobes, precuneus, caudate heads, basal forebrain and lateral ventricles.

Conclusions: Our work supports that machine learning applied to longitudinal brain volumetric changes can be used to predict, with high precision, presence of amyloid abnormalities in cognitively unimpaired subjects. Used as a triaging method to identify a fixed number of amyloid positive individuals, this longitudinal voxelwise classifier is expected to avoid 55\% of unnecessary CSF and/or PET scans and reduce economic cost by 40\%.

}, doi = {https://doi.org/10.1186/s13195-019-0526-8}, url = {https://link.springer.com/article/10.1186/s13195-019-0526-8}, author = {Paula Petrone and Adri{\`a} Casamitjana and Carles Falcon and Miguel Artigues C{\`a}naves and G. Operto and R. Cacciaglia and Jose Luis Molinuevo and Ver{\'o}nica Vilaplana and Juan D. Gispert} } @conference {cFernandeze, title = {VLX-Stories: a Semantically Linked Event platform for media publishers}, booktitle = {Proceedings of the ISWC 2019 Satellite Tracks (Posters \& Demonstrations, Industry, and Outrageous Ideas) co-located with 18th International Semantic Web Conference (ISWC 2019)}, year = {2019}, month = {10/2019}, publisher = {CEUR Workshop Proceeedings}, organization = {CEUR Workshop Proceeedings}, address = {Auckland, New Zealand}, abstract = {

In this article we present a web platform used by media producers to monitor word events, detected by VLX-Stories.\ The event detector system retrieves multi-regional articles from news sites, aggregates them by topic, and summarizes them by extracting and structuring its most relevant entities in order to answer the journalism W{\textquoteright}s: who, what, when and where.\ The dashboard displays online detected events in a semantically linked space which allows navigation among trending news stories on distinct countries, categories and time.\ Moreover, detected events are linked to costumer contents, helping editorial process by providing real time access to breaking news related to their contents.\ (Demo paper)

}, url = {http://ceur-ws.org/Vol-2456/paper61.pdf}, author = {Fern{\`a}ndez, D{\`e}lia and Bou, Elisenda and Xavier Gir{\'o}-i-Nieto} } @conference {cFernandezd, title = {VLX-Stories: building an online Event Knowledge Base with Emerging Entity detection}, booktitle = {The Semantic Web {\textendash} ISWC 2019}, year = {2019}, month = {10/2019}, pages = {382-399}, publisher = {Springer, Cham}, organization = {Springer, Cham}, chapter = {24}, address = {Auckland, New Zealand}, abstract = {

We present an online multilingual system for event detection and comprehension from media feeds. The system retrieves information from news sites and social networks, aggregates them into events (event detection), and summarizes them by extracting semantic labels of its most relevant entities (event representation) in order to answer the journalism W{\textquoteright}s: who, what, when and where. The generated events populate VLX-Stories -an event Knowledge Base (KB)- transforming unstructured text data to a structured knowledge base representation.\ Our system exploits an external entity Knowledge Base (VLX-KG) to help populate VLX-Stories. At the same time, this external knowledge base can also be extended with a Dynamic Entity Linking (DEL) module, which detects Emerging Entities (EE) on unstructured data and adds them to VLX-KG.\ The system is currently used in production, detecting over 6000 monthly events from over 3500 news feeds from seven different countries and in three different languages.

}, keywords = {emerging entities, Entity Linking, event encoding, knowledge base population. knowledge graph, topic detection}, issn = {978-3-030-30796-7}, doi = {10.1007/978-3-030-30796-7_24}, url = {https://link.springer.com/chapter/10.1007/978-3-030-30796-7_24}, author = {Fern{\`a}ndez, D{\`e}lia and Bou, Elisenda and Xavier Gir{\'o}-i-Nieto} } @article {aPetrone18, title = {Characteristic Brain Volumetric Changes in the AD Preclinical Signature.}, journal = {Alzheimer{\textquoteright}s \& Dementia: The Journal of the Alzheimer{\textquoteright}s Association}, volume = {14}, year = {2018}, month = {07/2018}, pages = {P1235}, doi = {10.1016/j.jalz.2018.06.1737}, author = {P. Petrone and Adri{\`a} Casamitjana and C. Falcon and M. Artigues and G. Operto and S. Skouras and J.L. Molinuevo and Ver{\'o}nica Vilaplana and J.D. Gispert} } @conference {cPetrone, title = {Characteristic Brain Volumetric Changes in the AD Preclinical Signature}, booktitle = {Alzheimer{\textquoteright}s Association International Conference}, year = {2018}, month = {07/2018}, address = {Chicago, USA}, abstract = {

In the last decade, magnetic resonance imaging has unveiled specific AD alterations at different stages of the AD pathophysiologic continuum that conform what has been established as the AD signature. To which extent MRI can detect structural changes at the preclinical asymptomatic stage of AD - the preclinical AD signature- is still an area open for exploration. Our work supports the idea that there are brain volumetric changes specific to preclinical AD subjects and defines the preclinical AD signature based on longitudinal data. While some regions show a pattern of atrophy that overlaps with the AD signature, other specific regions exhibit changes that are unique to this early asymptomatic AD stage.

}, author = {P. Petrone and Adri{\`a} Casamitjana and C. Falcon and M. Artigues and G. Operto and S. Skouras and R. Cacciaglia and J.L. Molinuevo and Ver{\'o}nica Vilaplana and J.D. Gispert} } @conference {cFojo, title = {Comparing Fixed and Adaptive Computation Time for Recurrent Neural Network}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2018}, month = {02/2018}, address = {Vancouver, Canada}, abstract = {

Deep networks commonly perform better than shallow ones, but allocating the proper amount of computation for each particular input sample remains an open problem. This issue is particularly challenging in sequential tasks, where the required complexity may vary for different tokens in the input sequence. Adaptive Computation Time (ACT) was proposed as a method for dynamically adapting the computation at each step for Recurrent Neural Networks (RNN). ACT introduces two main modifications to the regular RNN formulation: (1) more than one RNN steps may be executed between an input sample is fed to the layer and and this layer generates an output,\  and (2) this number of steps is dynamically predicted depending on the input token and the hidden state of the network. In our work, we aim at gaining intuition about the contribution of these two factors to the overall performance boost observed when augmenting RNNs with ACT. We design a new baseline, Repeat-RNN, which performs a constant number of RNN state updates larger than one before generating an output. Surprisingly, such uniform distribution of the computational resources matches the performance of ACT in the studied tasks. We hope that this finding motivates new research efforts towards designing RNN architectures that are able to dynamically allocate computational resources.

Reproducing and Analyzing Adaptive Computation Time in PyTorch and TensorFlow from Universitat Polit{\`e}cnica de Catalunya
}, author = {Fojo, Daniel and V{\'\i}ctor Campos and Xavier Gir{\'o}-i-Nieto} } @conference {cFernandezc, title = {Linking Media: adopting Semantic Technologies for multimodal media connection}, booktitle = {International Semantic Web Conference - ISWC (Industry Track)}, year = {2018}, month = {08/2018}, address = {Monterey, CA, USA}, abstract = {

Today{\textquoteright}s media and news organizations are constantly generating large amounts of multimedia content, majorly delivered online. As the online media market grows, the management and delivery of contents is becoming a challenge.\ Computational approaches can help to overcome this challenge by governing different applications such as content creation, production, search, and its promotion and distribution to different audiences.\ In this abstract we present a success story of the adoption of semantic technologies on the aforementioned applications, which\ \ are built on top of a semantic tagging framework, based on a Knowledge Graph (KG).\ The presented pipeline combines multimodal inputs into a contextual entity linking module, which indexes documents and links them to trends and stories developing on the news.\ \ We will describe how documents are linked and provided to media producers through Vilynx{\textquoteright}s platform, which is currently indexing over 20k media documents a day.

}, keywords = {Knowledge graph; Linked data; Multimedia; Semantic web Linked data; Computational approach; Content creation; Knowledge graphs; Multimedia; Multimedia contents; Multimodal inputs; Semantic tagging; Semantic technologies; Semantic Web}, url = {http://ceur-ws.org/Vol-2180/}, author = {Fern{\`a}ndez, D{\`e}lia and Bou-Balust, Elisenda and Xavier Gir{\'o}-i-Nieto} } @article {aCasamitjana, title = {MRI-Based Screening of Preclinical Alzheimer{\textquoteright}s Disease for Prevention Clinical Trials}, journal = {Journal of Alzheimer{\textquoteright}s Disease}, volume = {64}, year = {2018}, month = {07/2018}, chapter = {1099}, abstract = {

The identification of healthy individuals harboring amyloid pathology constitutes one important challenge for secondary prevention clinical trials in Alzheimer{\textquoteright}s disease (AD). Consequently, noninvasive and cost-efficient techniques to detect preclinical AD constitute an unmet need of critical importance. In this manuscript, we apply machine learning to structural MRI (T1 and DTI) of 96 cognitively normal subjects to identify amyloid-positive ones. Models were trained on public ADNI data and validated on an independent local cohort. Used for subject classification in a simulated clinical trial setting, the proposed method is able to save 60\% unnecessary CSF/PET tests and to reduce 47\% of the cost of recruitment when used in a simulated clinical trial setting. This recruitment strategy capitalizes on already acquired MRIs to reduce the overall amount of invasive PET/CSF tests in prevention trials, demonstrating a potential value as a tool for AD screening. This protocol could foster the development of secondary prevention strategies for AD.

}, author = {Adri{\`a} Casamitjana and Paula Petrone and Alan Tucholka and Carles Falcon and Stavros Skouras and Jose Luis Molinuevo and Ver{\'o}nica Vilaplana and Juan D. Gispert} } @unpublished {xFernandezb, title = {Multimodal Knowledge Base Population from News Streams for Media Applications}, year = {2018}, month = {07/2018}, type = {Phd thesis proposal}, abstract = {

Media producers publish large amounts of multimedia content online - both text, audio\ and video. As the online media market grows, the management and delivery of contents\ is becoming a challenge. Semantic and Linking technologies can be used to organize and\ exploit this contents. This dissertation addresses the problem of integrating Semantic Web\ technologies and linking data technologies into Vilynx{\textquoteright}s platform, a system used by media\ producers to manage and explode its contents. For that purpose, Knowledge Graphs (KG)\ and its maintenance through multimodal Knowledge Base Population (KBP) from online\ data extracted from the Web is studied. The Web is a very large unstructured data source\ with millions of text, images, videos and audio. This thesis is willing to generate solutions\ to facilitate automatic learning from these multimodal data and use it in real product applications\ for media.

This thesis is going to be structured in three parts. The first part of the thesis will cover\ the construction of a multimodal KG, which will be the core of the system for knowledge\ extraction, standardization and contextualization.

The\ second part will consist on the construction of the tools that will be used for KBP. For\ that we will construct a multimodal semantic tagging framework, based on the previously\ mentioned KG. This block addresses some typical challenges of KBP and data mining, like:\ name entity recognition (NER), entity linking (EL), context set construction (CSC), structured\ data creation, standardization, entity matching and data fusion.

The third part will focus on the extraction of knowledge from the Web to populate the knowledge\ base. As the KG domain is media, we will populate the KG using events detected from\ news streams using a multilmodal perspective. To detect events we will construct a news\ aggregator system. This part will deal with the problems of Topic Detection and Tracking\ (TDT), Topic Modeling (TM) and multi-document summarization. From these data we will\ learn relations between world entities, that will populate our KG, dealing with the automatic\ detection and update of concepts and relations. Also social media information will be\ analyzed to understand trendiness and world interests.

}, keywords = {Entity Detection, Entity Linking, Knowledge Base Population, Knowledge Graph, Linked Technologies, Multi-document Summarization, multimedia, Multimodal Systems, Natural Language Processing, Semantic Web, Topic Detection and Tracking, Topic Modeling}, author = {Fern{\`a}ndez, D{\`e}lia and Bou-Balust, Elisenda and Xavier Gir{\'o}-i-Nieto} } @mastersthesis {xFojo, title = {Reproducing and Analyzing Adaptive Computation Time in PyTorch and TensorFlow}, year = {2018}, abstract = {

The complexity of solving a problem can differ greatly to the complexity of posing that problem. Building a Neural Network capable of dynamically adapting to the complexity of the inputs would be a great feat for the machine learning community. One of the most promising approaches is Adaptive Computation Time for Recurrent Neural Network (ACT) \parencite{act}. In this thesis, we implement ACT in two of the most used deep learning frameworks, PyTorch and TensorFlow. Both are open source and publicly available. We use this implementations to evaluate the capability of ACT to learn algorithms from examples. We compare ACT with a proposed baseline where each input data sample of the sequence is read a fixed amount of times, learned as a hyperparameter during training. Surprisingly, we do not observe any benefit from ACT when compared with this baseline solution, which opens new and unexpected directions for future research.

Reproducing and Analyzing Adaptive Computation Time in PyTorch and TensorFlow from Universitat Polit{\`e}cnica de Catalunya
}, author = {Fojo, Daniel}, editor = {V{\'\i}ctor Campos and Xavier Gir{\'o}-i-Nieto} } @conference {cFernandezb, title = {What is going on in the world? A display platform for media understanding}, booktitle = {IEEE Multimedia Information Processing and Retrieval (MIPR) Conference}, year = {2018}, month = {04/2018}, publisher = {IEEE}, organization = {IEEE}, address = {Miami, FL (USA)}, abstract = {

News broadcasters and on-line publishers daily generate a large amount of articles and videos describing events currently happening in the world. In this, work we present a system that automatically indexes videos from a library and links them to stories developing in the news. The user interface displays in an intuitive manner the links between\  videos and stories and allows navigation through related content by using associated tags. This interface is a powerful industrial tool for publishers to index, retrieve and visualize their video content. It helps them identify which topics require more attention or retrieve related content that{\textquoteright}s already been published about the stories.

}, doi = {https://doi.org/10.1109/MIPR.2018.00045}, url = {https://www.youtube.com/watch?v=eaXcB2X-5xY}, author = {Fern{\`a}ndez, D{\`e}lia and David Varas and Bou, Elisenda and Xavier Gir{\'o}-i-Nieto} } @mastersthesis {xGorriz, title = {Active Deep Learning for Medical Imaging Segmentation}, year = {2017}, abstract = {

Grade: A (9.7/10)

This thesis proposes a novel active learning framework capable to train e ectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our approach tries to apply in segmentation existing active learning techniques, which is becoming an important topic today because of the many problems caused by the lack of large amounts of data. We explore di erent strategies to study the image information and introduce a previously used cost-e ective active learning method based on the selection of high con dence predictions to assign automatically pseudo-labels with the aim of reducing the manual annotations. First, we made a simple application for handwritten digit classi cation to get started to the methodology and then we test the system with a medical image database for the treatment of melanoma skin cancer. Finally, we compared the traditional training methods with our active learning proposals, specifying the conditions and parameters required for it to be optimal.

Active Deep Learning for Medical Imaging from Xavier Giro-i-Nieto
}, url = {http://hdl.handle.net/2117/109304}, author = {G{\'o}rriz, Marc}, editor = {Xavier Gir{\'o}-i-Nieto and Carlier, Axel and Faure, Emmanuel} } @conference {cGorriz, title = {Active Deep Learning for Medical Imaging Segmentation}, booktitle = {Medical Image meets NIPS 2017 Workshop}, year = {2017}, month = {11/2017}, abstract = {

We propose a novel Active Learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our contribution is a practical Cost-Effective Active Learning approach using Dropout at test time as Monte Carlo sampling to model the pixel-wise uncertainty and to analyze the image information to improve the training performance.

Active Deep Learning for Medical Imaging from Xavier Giro-i-Nieto
}, author = {G{\'o}rriz, Marc and Xavier Gir{\'o}-i-Nieto and Carlier, Axel and Faure, Emmanuel} } @conference {cGorriza, title = {Cost-Effective Active Learning for Melanoma Segmentation}, booktitle = {ML4H: Machine Learning for Health Workshop at NIPS 2017}, year = {2017}, month = {11/2017}, address = {Long Beach, CA, USA}, abstract = {

We propose a novel Active Learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our contribution is a practical Cost-Effective Active Learning approach using Dropout at test time as Monte Carlo sampling to model the pixel-wise uncertainty and to analyze the image information to improve the training performance.

Active Deep Learning for Medical Imaging from Xavier Giro-i-Nieto
}, url = {https://arxiv.org/abs/1711.09168}, author = {G{\'o}rriz, Marc and Xavier Gir{\'o}-i-Nieto and Carlier, Axel and Faure, Emmanuel} } @article {aFrias-Velazquez, title = {Hierarchical stack filtering: a bitplane-based algorithm for massively parallel processors}, journal = {Journal of Real-Time Image Processing}, year = {2017}, month = {03/2017}, abstract = {

Full version available at http://rdcu.be/p6w1

With the development of novel parallel architectures for image processing, the implementation of well-known image operators needs to be reformulated to take advantage of the so-called massive parallelism. In this work, we propose a general algorithm that implements a large class of nonlinear filters, called stack filters, with a 2D-array processor. The proposed method consists of decomposing an image into bitplanes with the bitwise decomposition, and then process every bitplane hierarchically. The filtered image is reconstructed by simply stacking the filtered bitplanes according to their order of significance. Owing to its hierarchical structure, our algorithm allows us to trade-off between image quality and processing time, and to significantly reduce the computation time of low-entropy images. Also, experimental tests show that the processing time of our method is substantially lower than that of classical methods when using large structuring elements. All these features are of interest to a variety of real-time applications based on morphological operations such as video segmentation and video enhancement.\ 

}, keywords = {Array processors, Bitwise decomposition, Morphological operators, Smart camera, Stack filters}, url = {http://rdcu.be/p6w1}, author = {Frias-Velazquez, A. and Morros, J.R. and Garc{\'\i}a, M. and Philips, Wilfried} } @article {aPetrone17, title = {Magnetic Resonance Imaging as a valuable tool for Alzheimer{\textquoteright}s disease screening}, journal = {Alzheimer{\textquoteright}s \& Dementia: The Journal of the Alzheimer{\textquoteright}s Association}, volume = {13}, year = {2017}, month = {07/2017}, pages = {P1245}, doi = {10.1016/j.jalz.2017.07.457}, url = {https://doi.org/10.1016/j.jalz.2017.07.457}, author = {P. Petrone and Ver{\'o}nica Vilaplana and Adri{\`a} Casamitjana and D. Sanchez-Escobedo and A. Tucholka and R. Cacciaglia and G. Operto and S. Skouras and C. Falcon and J.L. Molinuevo and J.D. Gispert} } @conference {cPetrone17, title = {Magnetic Resonance Imaging as a valuable tool for Alzheimer{\textquoteright}s disease screening}, booktitle = {Alzheimer{\textquoteright}s Association International Conference, London, 2017}, year = {2017}, month = {07/2017}, author = {P. Petrone and Ver{\'o}nica Vilaplana and Adri{\`a} Casamitjana and A. Tucholka and C. Falcon and R. Cacciaglia and G. Operto and S. Skouras and J.L. Molinuevo and J.D. Gispert} } @conference {cFernandez, title = {More cat than cute? Interpretable Prediction of Adjective-Noun Pairs}, booktitle = {ACM Multimedia 2017 Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes}, year = {2017}, month = {10/2017}, publisher = {ACM SIGMM}, organization = {ACM SIGMM}, address = {Mountain View, CA (USA)}, abstract = {

The increasing availability of affect-rich multimedia resources has bolstered interest in understanding sentiment and emotions in and from visual content. Adjective-noun pairs (ANP) are a popular mid-level semantic construct for capturing affect via visually detectable concepts such as {\textquoteleft}{\textquoteleft}cute dog" or {\textquoteleft}{\textquoteleft}beautiful landscape". Current state-of-the-art methods approach ANP prediction by considering each of these compound concepts as individual tokens, ignoring the underlying relationships in ANPs. This work aims at disentangling the contributions of the {\textquoteleft}adjectives{\textquoteright} and {\textquoteleft}nouns{\textquoteright} in the visual prediction of ANPs. Two specialised classifiers, one trained for detecting adjectives and another for nouns, are fused to predict 553 different ANPs. The resulting ANP prediction model is more interpretable as it allows us to study contributions of the adjective and noun components.

}, doi = {10.1145/3132515.3132520}, author = {Fern{\`a}ndez, D{\`e}lia and Woodward, Alejandro and V{\'\i}ctor Campos and Jou, Brendan and Xavier Gir{\'o}-i-Nieto and Chang, Shih-Fu} } @conference {cLe, title = {Towards large scale multimedia indexing: A case study on person discovery in broadcast news}, booktitle = {International Workshop on Content-Based Multimedia Indexing - CBMI 2017}, year = {2017}, month = {06/2017}, address = {Firenze, Italy}, abstract = {

The rapid growth of multimedia databases and the human interest in their peers make indices representing the location and identity of people in audio-visual documents essential for searching archives. Person discovery in the absence of prior identity knowledge requires accurate association of audio-visual cues and detected names. To this end, we present 3 different strategies to approach this problem: clustering-based naming, verification-based naming, and graph-based naming. Each of these strategies utilizes different recent advances in unsupervised face / speech representation, verification, and optimization. To have a better understanding of the approaches, this paper also provides a quantitative and qualitative comparative study of these approaches using the associated corpus of the Person Discovery challenge at MediaEval 2016. From the results of our experiments, we can observe the pros and cons of each approach, thus paving the way for future promising research directions.

}, author = {Nam Le and Herv{\'e} Bredin and Gabriel Sargent and Miquel India and Paula Lopez-Otero and Claude Barras and Camille Guinaudeau and Guillaume Gravier and Gabriel Barbosa da Fonseca and Izabela Lyon Freire and Zenilton Patroc{\'\i}nio Jr. and Silvio Jamil F. Guimaraes and Gerard Mart{\'\i} and Morros, J.R. and Javier Hernando and Laura Docio-Fernandez and Carmen Garcia-Mateo and Sylvain Meignier and Jean-Marc Odobez} } @conference {cFernandeza, title = {ViTS: Video Tagging System from Massive Web Multimedia Collections}, booktitle = {ICCV 2017 Workshop on Web-scale Vision and Social Media }, year = {2017}, month = {10/2017}, address = {Venice, Italy}, abstract = {

The popularization of multimedia content on the Web has arised the need to automatically understand, index and retrieve it. In this paper we present ViTS, an automatic Video Tagging System which learns from videos, their web context and comments shared on social networks. ViTS analyses massive multimedia collections by Internet crawling, and maintains a knowledge base that updates in real time with no need of human supervision. As a result, each video is indexed with a rich set of labels and linked with other related contents. ViTS is an industrial product under exploitation with a vocabulary of over 2.5M concepts, capable of indexing more than 150k videos per month. We compare the quality and completeness of our tags with respect to the ones in the YouTube-8M dataset, and we show how ViTS enhances the semantic annotation of the videos with a larger number of labels (10.04 tags/video), with an accuracy of 80,87\%.

}, author = {Fern{\`a}ndez, D{\`e}lia and David Varas and Espadaler, Joan and Ferreira, Jordi and Woodward, Alejandro and Rodr{\'\i}guez, David and Xavier Gir{\'o}-i-Nieto and Riveiro, Juan Carlos and Bou, Elisenda} } @conference {cPoignant16, title = {The CAMOMILE Collaborative Annotation Platform for Multi-modal, Multi-lingual and Multi-media Documents}, booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)}, year = {2016}, month = {05/2016}, address = {Portoro{\v z} (Slovenia)}, abstract = {

In this paper, we describe the organization and the implementation of the CAMOMILE collaborative annotation framework for multimodal, multimedia, multilingual (3M) data. Given the versatile nature of the analysis which can be performed on 3M data, the structure of the server was kept intentionally simple in order to preserve its genericity, relying on standard Web technologies. Layers of annotations, defined as data associated to a media fragment from the corpus, are stored in a database and can be managed through standard interfaces with authentication. Interfaces tailored specifically to the needed task can then be developed in an agile way, relying on simple but reliable services for the management of the centralized annotations. We then present our implementation of an active learning scenario for person annotation in video, relying on the CAMOMILE server; during a dry run experiment, the manual annotation of 716 speech segments was thus propagated to 3504 labeled tracks. The code of the CAMOMILE framework is distributed in open source.

}, keywords = {active learning, Annotation tool, collaborative annotation, multimedia, person annotation}, isbn = {978-2-9517408-9-1}, url = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/456_Paper.pdf}, author = {Johann Poignant and Mateusz Budnik and Herv{\'e} Bredin and Claude Barras and Mickael Stefas and Pierrick Bruneau and Gilles Adda and Laurent Besacier and Hazim Ekenel and Gil Francopoulo and Javier Hernando and Joseph Mariani and Morros, J.R. and Georges Qu{\'e}not and Sophie Rosset and Thomas Tamisier} } @mastersthesis {xFernandez, title = {Clustering and Prediction of Adjective-Noun Pairs for Affective Computing}, year = {2016}, abstract = {

Student: D{\`e}lia Fern{\`a}ndez

Advisors: V{\'\i}ctor Campos (UPC), Brendan Jou (Columbia University), Xavier Gir{\'o}-i-Nieto (UPC) and Shih-Fu Chang (Columbia University)

Grade: A+ (10.0/10.0) - Best Master Thesis award (Class 2016)

One of the main problems in visual affective computing is overcoming the affective gap between low-level visual features and the emotional content of the image. One rising method to capture visual affection is through the use of Adjective-Noun Pairs (ANP), a mid-level affect representation. This thesis addresses two challenges related to ANPs: representing ANPs in a structured ontology and improving ANP detectability. The first part develops two techniques to exploit relations between adjectives and nouns for automatic ANP clustering. The second part introduces and analyzes a novel deep neural network for ANP prediction. Based on the hypothesis of a different contribution of the adjective and the noun depending of the ANP, the novel network fuses the feature representations of adjectives and nouns from two independently trained convolutional neural networks.

}, author = {Fern{\`a}ndez, D{\`e}lia}, editor = {V{\'\i}ctor Campos and Jou, Brendan and Xavier Gir{\'o}-i-Nieto and Chang, Shih-Fu} } @unpublished {xFernandeza, title = {Is a {\textquotedblleft}happy dog{\textquotedblright} more {\textquotedblleft}happy{\textquotedblright} than {\textquotedblleft}dog{\textquotedblright}? - Adjective and Noun Contributions for Adjective-Noun Pair prediction}, journal = {NIPS Women in Machine Learning Workshop}, year = {2016}, month = {12/2016}, address = {Barcelona}, abstract = {

Computers are acquiring increasing ability to detect high level visual content such as objects in images, but often lack an affective comprehension of this content. Affective computing is useful for behavioral sciences, with applications in brand monitoring or advertisement effect. The main problem of the visual task of mapping affect or emotions to images is overcoming the affective gap between low-level features and the image emotional content.

One rising method to capture visual affections is through the use of Adjective-Noun Pair (ANP). ANPs were introduced as a mid-level affect representation to overcome the affective gap by combining nouns, which define the object content, and adjectives, which add a strong emotional bias, yielding concepts such as {\textquotedblleft}happy dog{\textquotedblright} or {\textquotedblleft}misty morning{\textquotedblright}.

Current state of the art methods approach ANP prediction by training visual classifiers on these pairs. In this work, we hypothesize that the visual contribution between nouns and adjectives differ between ANPs. We propose a feature-based intermediate representation for ANP prediction using specialized convolutional networks for adjectives and nouns separately. By fusing a representation from nouns and adjectives, the network learns how much the nouns and adjectives contribute to each ANP, which a single tower network does not allow.

The specialized noun and adjective networks follow an AlexNet-styled architecture. These networks are fused into an intermediate feature representation, and ANPs are then learned from it using a fully-connected network. We investigate noun and adjective contributions with two kinds of fusions. First fusion uses the output of the softmax layer: these are class-probability features, so all dimensions have class-correspondence to adjectives and nouns. Second fusion uses the fc7 layer output: these features contain visual information, allowing interpretation of adjective and noun visual relevance. For the feature contributions of each ANP, we compute a deep Taylor decomposition [1].

For experiments, we use a subset of 1,200 ANPs from the tag-based English-MVSO [2] dataset. ANPs are composed by the combination of 350 adjective and 617 nouns. With identical settings to the adjective and noun networks, an ANP classification network is trained end-to-end as the baseline. Using the fc7 features, we improve over the baseline in both top-1 and top-5 accuracy. Also, we observe adjective and nouns contribute differently between ANPs; e.g. for the ANP {\textquotedblleft}pregnant woman{\textquotedblright}, the adjective contributes the most, while for {\textquotedblleft}cute cat{\textquotedblright} the predominant contribution is in the noun. Using the probability features we find other insights, as nouns or adjectives co-occurring together, e.g. for {\textquotedblleft}happy halloween{\textquotedblright} the contribution is also high of the nouns {\textquotedblleft}blood{\textquotedblright} and {\textquotedblleft}cat{\textquotedblright}, and of the adjectives {\textquotedblleft}haunted{\textquotedblright} and {\textquotedblleft}dark{\textquotedblright}.\ 

Based on experiment results, we confirm our hypothesis of adjective and nouns contributing differently to ANP concepts. Furthermore, our architecture proves to outperform traditional methods by giving insights on the role of adjectives and nouns on the prediction.

[1] Montavon, Gr{\'e}goire, et al. "Deep Taylor Decomposition of Neural Networks." ICML Workshop on Visualization for Deep Learning, 2016.

[2] Jou, Brendan, et al. "Visual affect around the world: A large-scale multilingual visual sentiment ontology." ACMM, 2015.

}, author = {Fern{\`a}ndez, D{\`e}lia and V{\'\i}ctor Campos and Jou, Brendan and Xavier Gir{\'o}-i-Nieto and Chang, Shih-Fu} } @mastersthesis {xFerri16, title = {Object Tracking in Video with TensorFlow}, year = {2016}, abstract = {

[Project repo]

[Additional repo for setting up the environment]

}, author = {Ferri, Andrea}, editor = {Xavier Gir{\'o}-i-Nieto and Jordi Torres and Amaia Salvador} } @article {aSalembier, title = {Optimum Graph-Cuts for Pruning Binary Partition Trees of Polarimetric SAR images}, journal = {IEEE Transactions on Geoscience and Remote Sensing}, volume = {54}, year = {2016}, month = {05/2016}, pages = {5493 {\textendash} 5502}, abstract = {

This paper investigates several optimum graph-cuts techniques for pruning Binary Partition Trees (BPTs) and their usefulness for low-level processing of Polarimetric SAR (PolSAR) images. BPTs group pixels to form homogeneous regions, which are hierarchically structured by inclusion in a binary tree. They provide multiple resolutions of description and easy access to subsets of regions. Once constructed, BPTs can be used for a large number of applications. Many of these applications consist in populating the tree with a specific feature and in applying a graph-cut called pruning to extract a partition of the space. In this paper, different pruning examples involving the optimization of a global criterion are discussed and analyzed in the context of PolSAR images for segmentation. Through objective evaluation of the resulting partitions by means of Precision and Recall for boundaries curves, the best pruning technique is identified and the influence of the tree construction on the performances is assessed.\ 

}, author = {Salembier, P. and S. Foucher} } @mastersthesis {xBosch, title = {Region-oriented Convolutional Networks for Object Retrieval}, year = {2015}, abstract = {

Advisors: Amaia Salvador and\ Xavier Gir{\'o}-i-Nieto\ (UPC)\ 

Study program: Engineering on Audiovisual Systems (4 years) at Escola d{\textquoteright}Enginyeria de Terrassa\ (UPC)

Grade: A (9.6/10)

This thesis is framed in the computer vision field, addressing a challenge related to instance search. Instance search consists in searching for occurrences of a certain visual instance on a large collection of visual content, and generating a ranked list of results sorted according to their relevance to a user query. This thesis builds up on existing work presented at the TRECVID Instance Search Task in 2014, and explores the use of local deep learning features extracted from object proposals. The performance of different deep learning architectures (at both global and local scales) is evaluated, and a thorough comparison of them is performed. Secondly, this thesis presents the guidelines to follow in order to fine-tune a convolutional neural network for tasks such as image classification, object detection and semantic segmentation. It does so with the final purpose of fine tuning SDS, a CNN trained for both object detection and semantic segmentation, with the recently released Microsoft COCO dataset.

Region-oriented Convolutional Networks for Object Retrieval from Xavier Giro
}, author = {Fontdevila-Bosch, Eduard}, editor = {Amaia Salvador and Xavier Gir{\'o}-i-Nieto} } @article {aTochon15, title = {On the use of binary partition trees for the tree crown segmentation of tropical rainforest hyperspectral images}, journal = {Remote Sensing of Environment}, volume = {159}, year = {2015}, month = {03/2015}, pages = {318-331}, abstract = {

The segmentation of remotely sensed images acquired over tropical forests is of great interest for numerous ecological applications, such as forest inventories or conservation and management of ecosystems, for which species classification techniques and estimation of the number of individuals are highly valuable inputs. In this paper, we propose a method for hyperspectral image segmentation, based on the binary partition tree (BPT) algorithm, and we apply it to two sites located in Hawaiian and Panamean tropical rainforests. Different strategies combining spatial and spectral dimensionality reduction are compared prior to the construction of the BPT. Various superpixel generation methods including watershed transformation and mean shift clustering are applied to decrease spatial dimensionality and provide an initial segmentation map. Principal component analysis is performed to reduce the spectral dimensionality and different combinations of principal components are compared. A non-parametric region model based on histograms, combined with the diffusion distance to merge regions, is used to build the BPT. An adapted pruning strategy based on the size discontinuity of the merging regions is proposed and compared with an already existing pruning strategy. Finally, a set of criteria to assess the quality of the tree segmentation is introduced. The proposed method correctly segmented up to 68\% of the tree crowns and produced reasonable patterns of the segmented landscapes.

}, issn = {0034-4257}, author = {G. Tochon and J.B. F{\'e}eret and Valero, S. and R.E. Martin and D.E. Knapp and Salembier, P. and Chanussot, J. and G. Asner} } @conference {cSalembier14, title = {Low-level processing of PolSAR images with binary partition trees}, booktitle = {IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2014}, year = {2014}, month = {07/2014}, publisher = {IEEE}, organization = {IEEE}, address = {Quebec, Canada}, abstract = {

This paper discusses the interest of Binary Partition Trees (BPTs) and the usefulness of graph cuts for low-level processing of PolSAR images. BPTs group pixels to form homogeneous regions, which are hierarchically structured by inclusion in a tree. They provide multiple resolutions of description and easy access to subsets of regions. Once constructed, BPTs can be used for many applications including filtering, segmentation, classification and object detection. Many processing strategies consist in populating the tree with a specific feature and in applying a graph-cut called pruning. Different graph-cuts are discussed and analyzed in the context of PolSAR images for speckle filtering and segmentation.

}, author = {Salembier, P. and S. Foucher and L{\'o}pez-Mart{\'\i}nez, C.} } @mastersthesis {xFerrarons-Betrian, title = {Mobile Visual Search at Catchoom}, year = {2014}, abstract = {

Author: Miquel Ferrarons-Betrian

Advisors:\ Xavier Gir{\'o}-i-Nieto\ (UPC) and Tomasz Adamek\ (Catchoom)

Degree: Master in Computer Vision (1 year)

}, keywords = {feature selection, large-scale visual search, Mobile visual search, synthetic views matching, visual word}, author = {Ferrarons-Betrian, Miquel}, editor = {Adamek, Tomasz and Xavier Gir{\'o}-i-Nieto} } @article {aSalembier14, title = {Remote sensing image processing with graph cut of Binary Partition Trees}, journal = {Advances in computing science, control and communications}, volume = {69}, year = {2014}, month = {04/2014}, pages = {185-196}, issn = {1870-4069}, author = {Salembier, P. and S. Foucher} } @article {aMolina11 , title = {Real-time user independent hand gesture recognition from time-of-flight camera video using static and dynamic models}, journal = {Machine vision and applications}, volume = {24}, year = {2013}, month = {08/2011}, pages = {187{\textendash}204}, chapter = {187}, abstract = {

The use of hand gestures offers an alternative to the commonly used human computer interfaces, providing a more intuitive way of navigating among menus and multimedia applications. This paper presents a system for hand gesture recognition devoted to control windows applications. Starting from the images captured by a time-of-flight camera (a camera that produces images with an intensity level inversely proportional to the depth of the objects observed) the system performs hand segmentation as well as a low-level extraction of potentially relevant features which are related to the morphological representation of the hand silhouette. Classification based on these features discriminates between a set of possible static hand postures which results, combined with the estimated motion pattern of the hand, in the recognition of dynamic hand gestures. The whole system works in real-time, allowing practical interaction between user and application.

}, issn = {0932-8092}, doi = {10.1007/s00138-011-0364-6}, url = {http://www.springerlink.com/content/062m51v58073572h/fulltext.pdf}, author = {Molina, J. and Escudero-Vi{\~n}olo, M. and Signorelo, A. and M. Pard{\`a}s and Ferran, C. and Bescos, J. and Marqu{\'e}s, F. and Mart{\'\i}nez, J.} } @article {aTochon13, title = {Segmentation hyperspectrales de forets tropicales par arbres de partition binaires}, journal = {Revue fran{\c c}aise de photogramm{\'e}trie et de t{\'e}l{\'e}d{\'e}tection}, volume = {202}, year = {2013}, month = {May 2013}, pages = {55-65}, author = {G. Tochon and J.B. Feret and Valero, S. and R.E. Martin and R. Tupayachi and Chanussot, J. and Salembier, P. and G. Asner} } @inbook {bNavarro12, title = {Multi-view Body Tracking with a Detector-Driven Hierarchical Particle Filter}, booktitle = {Lecture Notes in Computer Science: Articulated Motion and Deformable Objects}, series = {Lecture Notes in Computer Science}, volume = {7378}, year = {2012}, pages = {82-91}, publisher = {Springer }, organization = {Springer }, address = {Berlin / Heidelberg}, abstract = {

In this paper we present a novel approach to markerless human motion capture that robustly integrates body part detections in multiple views. The proposed method fuses cues from multiple views to enhance the propagation and observation model of particle filtering methods aiming at human motion capture. We particularize our method to improve arm tracking in the publicly available IXMAS dataset. Our experiments show that the proposed method outperforms other state-of-the-art approaches.

}, isbn = {978-3-642-31566-4}, doi = {10.1007/978-3-642-31567-1_8}, author = {Navarro, Sergio and L{\'o}pez-M{\'e}ndez, A. and Alcoverro, M. and Casas, J.}, editor = {Perales, Francisco and Fisher, Robert and Moeslund, Thomas} } @conference {cJimenez12, title = {Registration of Multi-Modal Neuroimaging Datasets by Considering the Non-Overlapping Field of View into the NMI Calculation}, booktitle = {IEEE International Symposium on Biomedical Imaging, ISBI 2012}, year = {2012}, address = {Barcelona, Spain}, author = {Jim{\'e}nez, X and Figueiras, F and Marqu{\'e}s, F. and Salembier, P. and Herance, R and Rojas, S and Mill{\'a}n, O and Pareto, D and Domingo Gispert, J} } @conference {cFrias-Velazquez09, title = {Gray-scale erosion algorithm based on image bitwise decomposition: application to focal plane processors}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing 2009}, year = {2009}, pages = {845{\textendash}848}, doi = {10.1109/ICASSP.2009.4959716}, url = {http://hdl.handle.net/2117/9156}, author = {Frias-Velazquez, A. and Morros, J.R.} } @conference {cFrias-Velazquez09a, title = {Histogram computation based on image bitwise decomposition}, booktitle = {ICIP 2009}, year = {2009}, isbn = {978-1-4244-5653-6}, doi = {10.1109/ICIP.2009.5413981}, url = {http://hdl.handle.net/2117/9144}, author = {Frias-Velazquez, A. and Morros, J.R.} } @conference {cCabrera09, title = {LAVICAD: LAboratori VIrtual de Comunicacions Anal{\`o}giques i Digitals}, booktitle = {Jornada d{\textquoteright}Innovaci{\'o} Docent - RIMA (JID-RIMA)}, year = {2009}, month = {02/2009}, publisher = {UPCommons}, organization = {UPCommons}, address = {Barcelona, Catalonia}, abstract = {

Mitjan{\c c}ant el present ajut s{\textquoteright}ha ampliat l{\textquoteright}aplicaci{\'o} en xarxa LAVICAD (LAboratori VIrtual de COmunicacions Anal{\`o}giques i Digitals) que s{\textquoteright}ofereix de forma integrada dins de la plataforma d{\textquoteright}e-learning COM@WEB. LAVICAD {\'e}s una eina programada en Java i Matlab i est{\`a} formada per un conjunt de simuladors de la capa f{\'\i}sica de sistemes de comunicacions. Tots els simuladors es presenten en xarxa i es poden utilitzar pels estudiants des de qualsevol ordinador sense necessitat d{\textquoteright}instal{\textperiodcentered}laci{\'o} de cap tipus de software especial. Durant el curs 2007 2008 s{\textquoteright}han desenvolupat entre d{\textquoteright}altres dos l{\'\i}nies de treball. D{\textquoteright}una banda s{\textquoteright}ha programat l{\textquoteright}applet que emula la capa f{\'\i}sica de la televisi{\'o} digital terrestre, com a referent per a l{\textquoteright}ensenyament de sistemes de comunicacions avan{\c c}ats. D{\textquoteright}altra banda s{\textquoteright}ha treballat en la programaci{\'o} de noves funcionalitats de l{\textquoteright}eina LAVICAD, que permeten ajudar als professors en el seguiment i avaluaci{\'o} del treball continuat dels estudiants. En particular s{\textquoteright}ha programat la generaci{\'o} d{\textquoteright}una base de dades que cont{\'e} la informaci{\'o} dels usuaris que s{\textquoteright}han connectat i els resultats obtinguts a l{\textquoteright}executar un determinat simulador. Les dues l{\'\i}nies desenvolupades han de permetre durant l{\textquoteright}actual curs, consolidar l{\textquoteright}{\'u}s dels diferents simuladors per a la doc{\`e}ncia de les assignatures implicades al projecte.

}, url = {http://hdl.handle.net/2099/7235}, author = {Cabrera, M. and Xavier Gir{\'o}-i-Nieto and Rey, F. and Gasull, A. and Casas, J. and Villares, J. and Fernandez, J. and Sala {\'A}lvarez, josep and Espinosa Fricke, Pedro and Fern{\'a}ndez, Carlos Marcos and Cort{\'e}s, S. and Farr{\'e}, Miquel {\`A}ngel} } @conference {cLuque06a, title = {Audio, Video and Multimodal Person Identification in a Smart Room}, booktitle = {CLEAR{\textquoteright}06 Evaluation Campaign and Workshop - Classification of Events, Activities and Relationships}, year = {2007}, pages = {258{\textendash}269}, isbn = {978-3-540-69567-7}, author = {Luque, J. and Morros, J.R. and Garde, A. and Anguita, J. and Farr{\'u}s, M. and Macho, D. and Marqu{\'e}s, F. and Mart{\'\i}nez, C. and Ver{\'o}nica Vilaplana and Hernando, J.} } @inbook {bLuque06, title = {Audio, Video and Multimodal Person Identification in a Smart Room}, booktitle = {Lecture notes in computer science - Multimodal Technologies for Perception of Humans}, volume = {4122}, year = {2006}, pages = {258{\textendash}269}, issn = {0302-9743}, doi = {10.1007/978-3-540-69568-4_23}, author = {Luque, J. and Morros, J.R. and Garde, A. and Anguita, J. and Farr{\'u}s, M. and Macho, D. and Marqu{\'e}s, F. and Mart{\'\i}nez, C. and Ver{\'o}nica Vilaplana and Hernando, J.} } @inbook {bFerran06, title = {BPT Enhancement based on Syntactic and Semantic criteria}, booktitle = {Semantic Multimedia}, volume = {4306}, year = {2006}, pages = {184{\textendash}198}, publisher = {Springer}, organization = {Springer}, address = {Berlin / Heidelberg}, abstract = {

This paper presents two enhancements for the creation and analysis of Binary Partition Trees (BPTs). Firstly, the classic creation of BPT based on colour is expanded to include syntactic criteria derived from human perception. Secondly, a method to include semantic information in the BPT analysis is shown thanks to the definition of the BPT Semantic Neighborhood and the introduction of Semantic Trees. Both techniques aim at bridging the semantic gap between signal and semantics following a bottom-up and a top-down approach, respectively.

}, isbn = {978-3-540-49335-8}, doi = {10.1007/11930334_15}, url = {http://www.springerlink.com/content/u7201mw06545w057/}, author = {Ferran, C. and Xavier Gir{\'o}-i-Nieto and Marqu{\'e}s, F. and Casas, J.} } @conference {cFerran06, title = {BPT Enhancement based on Syntactic and Semantic criteria}, booktitle = {1st International Conference on Semantic and Digital Media Technologies}, year = {2006}, pages = {184{\textendash}198}, isbn = {3-540-49335-2}, author = {Ferran, C. and Xavier Gir{\'o}-i-Nieto and Marqu{\'e}s, F. and Casas, J.} } @conference {cLuque06, title = {Multimodal Person Identification in a Smart Room}, booktitle = {IV Jornadas en Tecnolog{\'\i}a del Habla}, year = {2006}, pages = {327{\textendash}331}, isbn = {84-96214-82-6}, author = {Luque, J. and Morros, J.R. and Anguita, J. and Farr{\'u}s, M. and Macho, D. and Marqu{\'e}s, F. and Mart{\'\i}nez, C. and Ver{\'o}nica Vilaplana and Hernando, J.} } @conference {cSayrol05, title = {Development of a platform offering video copyright protection and security against illegal distribution}, booktitle = {Security, Steganography, and Watermarking of Multimedia Contents}, year = {2005}, pages = {76{\textendash}83}, isbn = {9963-607-06-3}, author = {Elisa Sayrol and Soriano, M. and Fernandez, M. and Casanelles, J. and Tom{\`a}s, J.} } @article {jFigueras05, title = {Las Mancomunidades en Espa{\~n}a}, journal = {Bolet{\'\i} de la Asociaci{\'o}n de Ge{\'o}grafos Espa{\~n}oles}, number = {39}, year = {2005}, pages = {151{\textendash}176}, issn = {0212-9426}, author = {Figueras, P. and Haas, C. and Capdevila, C. and Ver{\'o}nica Vilaplana} } @inbook {bSoriano05, title = {Multimedia Copyright Protection Platform Demonstrator}, booktitle = {Lecture notes in computer science}, volume = {3477}, year = {2005}, pages = {76{\textendash}83}, issn = {0302-9743}, url = {http://www.springerlink.com/(n0yw1g55rs45pg55g5zcinrm)/app/home/contribution.asp?referrer=parent\&backto=issue,32,34;journal,197,2212;linkingpublicationresults,1:105633,1}, author = {Soriano, M. and Fernandez, M. and Elisa Sayrol and Tom{\`a}s, J. and Casanelles, J. and Pegueroles, J. and Juan Hern{\'a}ndez Serrano} } @conference {cSoriano05, title = {Multimedia copyright protection platform demonstrator}, booktitle = {Third International Conference on Trust Management (iTrust{\textquoteright}05)}, year = {2005}, pages = {411{\textendash}414}, doi = {10.1007/11429760_32}, url = {http://dx.doi.org/10.1007/11429760_32}, author = {Soriano, M. and Fernandez, M. and Elisa Sayrol and Buliart, J. and Casanelles, J. and Pegueroles, J. and Juan Hern{\'a}ndez Serrano} } @conference {cFerran05, title = {Object representation using colour, shape and structure criteria in a Binary Partition Tree}, booktitle = {IEEE International Conference on Image Processing}, year = {2005}, isbn = {0-7803-9135-7}, author = {Ferran, C. and Casas, J.} } @conference {cFerran04, title = {Binary-Partition Tree creation using a quasi-inclusion criterion}, booktitle = {8th International Conference on Information Visualization (IV04)}, year = {2004}, pages = {259{\textendash}264}, isbn = {0-7695-2177-0}, author = {Ferran, C. and Casas, J.} } @inbook {bPardas04, title = {The InterFace Software Platform for Interactive Virtual Characters}, booktitle = {Mpeg-4 facial animation: the standard, implementation and applications}, year = {2004}, pages = {169{\textendash}183}, isbn = {0-470-84465-5}, author = {M. Pard{\`a}s and Pandzic, I. and Cannella, M. and Davoine, F. and Forchheimer, R. and Lavagetto, F. and Marriott, A. and Malassiotis, S.} } @conference {cCabrera04, title = {LaViCAD: LABORATORIO VIRTUAL DE COMUNICACIONES ANAL{\'O}GICAS Y DIGITALES}, booktitle = {4rt. Congr{\'e}s Internacional de Doc{\`e}ncia Unversit{\`a}ria i Innovaci{\'o}}, year = {2004}, pages = {1{\textendash}20}, isbn = {84-8458-240-X}, author = {Cabrera, M. and Fernandez, J. and Berzosa, C. and Francisco, V. and Gasull, A.} } @conference {cO{\textquoteright}Connor03, title = {Region and object segmentation algorithms in the QIMERA segmentation platform}, booktitle = {Third International Workshop on Content-Based Multimedia Indexing}, year = {2003}, pages = {95{\textendash}103}, isbn = {978-84-612-2373-2}, author = {O{\textquoteright}Connor, N. and Sav, S. and Adamek, T. and Mezaris, V. and Kompatsiaris, I. and Lui, T. and Izquierdo, E. and Ferran, C. and Casas, J.} } @conference {cGasull02, title = {Oil Spills Detection in SAR Images using Mathematical Morphology}, booktitle = {11th European Signal Processing Conference (EUSIPCO 2002)}, year = {2002}, pages = {25{\textendash}28}, author = {Gasull, A. and F{\'a}bregas, F.X. and Jim{\'e}nez, J. and Marqu{\'e}s, F. and Moreno, V. and Herrero, M.} } @conference {cSayrol01, title = {Color Inititialization for Lip Tracking}, booktitle = {International Conference on Augmented, Virtual Environments and 3D Imaging}, year = {2001}, pages = {351{\textendash}354}, author = {Elisa Sayrol and Fischi, O. and M. Pard{\`a}s} } @conference {cBroquetas00, title = {Detecci{\'o}n de vertidos de petr{\'o}leo en el mar a partir de im{\'a}genes SAR}, booktitle = {XV Simposium Nacional de la Uni{\'o}n Cient{\'\i}fica Internacional de Radio}, year = {2000}, pages = {327{\textendash}328}, isbn = {84-600-9597-5}, author = {Broquetas, A. and Toronjo, C. and Gasull, A. and F{\'a}bregas, F.X. and Moreno, V. and Herrero, M.} } @conference {cMarques95, title = {Coding of image partitions by morphological skeleton using overlapping structuring elements}, booktitle = {IEEE WORKSHOP ON NONLINEAR SIGNAL AND IMAGE PROCESSING}, year = {1995}, pages = {250{\textendash}253}, author = {Marqu{\'e}s, F. and Fioravanti, S. and Brigger, P.} } @conference {cOliveras91, title = {Tou - Brazo Robot Asistencial: Control Verbal}, booktitle = {2{\textordmasculine} Congreso de la Asociaci{\'o}n Espa{\~n}ola de Rob{\'o}tica}, year = {1991}, pages = {93{\textendash}100}, isbn = {0-7803-7043-0}, author = {Albert Oliveras and Fuertes, J. and Vill{\`a}, R.} }