Posters

Universitat Pompeu Fabra (UPF)

P1.1: Amelia Jiménez-Sánchez, Diana Mateus, Sonja Kirchhoff, Chlodwig Kirchhoff, Peter Biberthaler, Nassir Navab, Miguel A. González Ballester, Gemma Piella, "Medical-based deep curriculum learning for improved fracture classification". MICCAI 2019.

P1.2: Adriana Fernandez-Lopez, Ali Karaali, Naomi Harte, Federico M. Sukno, "CoGANs for unsupervised visual speech adaptation to new speakers". (submitted to ICASSP 2020).

P1.3, Furkan Yesiler, Joan Serrà, Emilia Gómez, "Accurate and scalable version identification using musically-motivated embeddings". ArXiv 2019.

P1.4 Laura Aina, Carina Silberer, Ionut-Teodor Sorodoc, Matthijs Westera, Gemma Boleda, "What do entity-centric models learn? Insights from entity linking in multi-party dialogue". NAACL 2019.

P1.5 Roberto Dessi, Diane Bouchacourt, Davide Crepaldi, Marco Baroni, "Focus on what’s informative and ignore what’s not: communication strategies in a referential game". NeurIPS 2019 Workshop on Emergent Communication: Towards Natural Language.

P1.6 Andres Ferraro, Dmitry Bogdanov, Jay Ho Jeon, Jason Yoon, Xavier Serra, "Music auto-tagging using CNNs and Mel-spectrograms with reduced frequency and time resolution". ArXiv 2019.

P1.7 Guillermo Cámbara, Jordi Luque, Mireia Farrús, "Detection of speech events and speaker characteristics through photo-plethysmographic signal neural processing". ArXiv 2019.

Dolby Laboratories

P1.8 Jordi Pons and Xavier Serra, "musicnn: an open source, deep learning-based music tagger". Late-breaking/demo session of ISMIR 2019.

Univrses AB

P1.9 Lorenzo Andraghetti, Panteleimon Myriokefalitakis, Pier Luigi Dovesi, Belen Luque, Matteo Poggi, Alessandro Pieropan, Stefano Mattoccia, "Enhancing self-supervised monocular depth estimation with traditional visual odometry". 3DV 2019.

Crisalix

P1.10 Eduard Ramon, Guillermo Ruiz, Thomas Batard, Xavier Giró-i-Nieto, "Hyperparameter-free losses for model-based monocular reconstruction". ICCV 2019 Geometry Meets Deep Learning Workshop.

BBC Research & Development

P1.11 Marc Górriz, Marta Mrak, Alan F. Smeaton, Noel E. O'Connor, "End-to-end conditional GAN-based architectures for image colourisation". IEEE MMSP 2019 International Workshop on Multimedia Signal Processing.

Aalborg University

P1.12 Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson, Jesper Jensen, "Deep-learning-based audio-visual speech enhancement in presence of Lombard effect". ArXiv 2019. Also "On training targets and objective functions for deep-learning-based audio-visual speech enhancement". ICASSP2019.

Universitat Politècnica de Catalunya (UPC)

P2.1 Ignasi Mas, Veronica Vilaplana, Ramon Morros, "Picking groups instead of samples: a close look at static pool-based meta-active learning". ICCV 2019 Workshop on Multi-Discipline Approach for Learning Concepts - Zero-Shot, One-Shot, Few-Shot and Beyond.

P2.2 Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa, "From bilingual to multilingual neural machine translation by incremental training". ACL Student Research Workshop 2019.

P2.3 Jamie Arjona, MªPaz Linares, Josep Casanovas, Juan Jose Vazquez. "Improving parking availability information using deep learning techniques". Transportation Research Procedia (in press).

P2.4 Edgar Riba, Dmytro Mishkin, Daniel Ponsa, Ethan Rublee, Gary Bradski, "Kornia: an open source differentiable computer vision library for PyTorch". WACV 2020.

P2.5 Amanda Duarte, Francisco Roldan, Miquel Tubau, Janna Escur, Santiago Pascual, Amaia Salvador, Eva Mohedano, Kevin McGuinness, Jordi Torres, Xavier Giro-i-Nieto. "Wav2Pix: speech-conditioned face generation using generative adversarial networks". ICASSP 2019.

P2.6 Benet Oriol Sabat, Cristian Canton Ferrer, Xavier Giro-i-Nieto, "Hate speech in pixels: detection of offensive memes towards automatic moderation". NeurIPS AI for Social Good Workshop 2019.

P2.7 Alba Maria Hererra-Palacio, Carles Ventura, Carina Silberer, Ionut-Teodor Sorodoc, Gemma Boleda, Xavier Giro-i-Nieto, "Recurrent instance segmentation using sequences of referring expressions". NeurIPS 2019 Workshop on Visually Grounded Interaction and Language (ViGIL).

Universitat Oberta de Catalunya (UOC)

P2.8 Carles Ventura, Jordi Pont-Tuset, Sergi Caelles, Kevis-Kokitsi Maninis, Luc Van Gool, "Iterative deep learning for road topology extraction". BMVC 2018.

P2.9: Hassan Hayat, Carles Ventura and Agata Lapedrize, "On the use of interpretable CNN for personality trait recognition from audio". ACIA 2019.

P2.10 Cristina Bustos, Daniel Rhoads, Albert Solé-Ribalta, Agata Lapedriza, David Masip, Alex Arenas and Javier Borge-Holthoefer, "Deep learning urban hazards to improve pedestrian safety". Machine Learning and Modeling for Complex Systems - Satellite session at the Conference of Complex Systems 2019.

Universitat Pompeu Fabra

P2.11 Pritish Chandna, Merlijn Blaauw, Jordi Bonada, Emilia Gómez, "A vocoder based method for singing voice extraction". ICASSP 2019. Also "WGANSing: a multi-voice singing voice synthesizer based on the Wasserstein-GAN". EUSIPCO 2019.

University of Music and Performing Arts Vienna

P2.12 Francesc Lluís, Jordi Pons, Xavier Serra, "End-to-end music source separation: is it possible in the waveform domain?". INTERSPEECH 2019.

Universitat Autónoma de Barcelona (UAB)

P2.13 Javad Zolfaghari Bengar, Abel Gonzalez-Garcia, Gabriel Villalonga, Bogdan Raducanu, Hamed H. Aghdam, Mikhail Mozerov, Antonio M. Lopez, Joost van de Weijer, "Temporal Coherence for Active Learning in Videos". ICCV 2019 Workshop - CVRSUAD.

Universitat de Barcelona (UB)

P3.1 Víctor M. Campello, Carlos Martín-Isla, Cristian Izquierdo, Steffen E. Petersen, Miguel Ángel González Ballester, Karim Lekadir, "Multi-sequence and synthetic images for LGE-MRI segmentation". STACOM (MICCAI 2019).

P3.2 Kovatchev, V., Martí, M. A., Salamó, M., and Beltran, J., "Qualitative evaluation framework for paraphrase identification". RANLP 2019.

P3.3 Eduardo Aguilar, Petia Radeva, "Food recognition by integrating local and flat classifiers". IbPRIA 2019.

Universitat Autònoma de Barcelona (UAB)

P3.4 Lei Kang, J Ignacio Toledo, Pau Riba, Mauricio Villegas, Alicia Fornés, Marçal Rusiñol, "Unsupervised writer adaptation for synthetic-to-real handwritten word recognition". WACV 2020.

P3.5 Sounak Dey, Pau Riba, Anjan Dutta, Josep Llados, Yi-Zhe Song , "Doodle to search: practical zero-shot sketch-based image retrieval". CVPR 2019.

P3.6 Lluís Gómez, Andrés Mafla, Marçal Rusiñol, Dimosthenis Karatzas, "Single shot scene text retrieval and applications". ECCV 2018.

P3.7 Hassan A. Sial, Ramon Baldrich, and Maria Vanrell, "Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects". JOSA-A 2020.

La Salle - Universitat Ramon Llull

P3.8 Xavier Sevillano, Sofia Zahia, Maria Begoña García-Zapirain, Alejandro González, Paul J. Kim, Adel Elmaghraby, "Machine and deep learning for image-based pressure injury diagnosis and prognosis". Artificial Intelligence in Medicine 2019.

Purdue University

P3.9 Daniel Mas Montserrat, Carlos Bustamante, Alexander Ioannidis, "LAI-Net: local-ancestry inference with neural networks". Phd Thesis.

University of Amsterdam (UvA)

P3.10 Marco Del Tredici, Diego Marcheggiani, Sabine Schulte im Walde, Raquel Fernández, "You shall know a user by the company it keeps: dynamic representations for social media users in NLP", EMNLP 2019.

Barcelona Supercomputing Center (BSC)

P3.11 Jordi Armengol-Estapé, Felipe Soares, Montserrat Marimon, Martin Krallinger, "PharmacoNER tagger: a deep learning-based tool for automatically finding chemicals and drugs in Spanish medical texts". Genomics & Informatics 2019.

University of Groningen

P3.12 Estefanía Talavera, María Leyva-Vallina, Md. Mostafa Kamal Sarker, Domenec Puig, Nicolai Petkov, Petia Radeva, "Hierarchical approach to classify food scenes in egocentric photo-streams". Journal of Biomedical and Health Informatics 2019.