Posters

Note: a global program view can be found here. The program is still subject to minor modifications.

Poster Sessions

Posters: Lunch (14:00-15:30)

Sala Àgora

Vision

  1. Bernat Català i Ulied (La Salle) - Application of Deep Learning techniques(GAN) for the generation of images from pictures of people (BSc)

  2. Bhalaji Nagarajan (UB) - Learning Multi-Subset of Classes for Fine-Grained Food Recognition (ACMM w)

  3. Marcelo Sánchez Ortega (UPF) - Photorealistic Wrinkle removal (ACCV w)

  4. Maider Abad (UOC) - Reducing the learning domain by using image processing to diagnose COVID-19 from X-ray images (CCIA)

  5. Thanasis Zoumpekas (UB) - Deep Learning on Temporal 3D Point Clouds (PhD)


Med Vision and Life Sciences

  1. David Anglada Rotger (UPC) - Color Deconvolution applied to Domain Adaptation in HER2 histopathological images (MSc)

  2. Carlos Hernández Pérez (UPC) - Contrastive and attention-based multiple instance learning for the prediction of sentinel lymph node status from histopathologies of primary melanoma tumours (MICCAI w)

  3. Álvaro Heredia Lidón (La Salle) - Deep learning applied to the normalisation and processing of 3d MRI heads (PhD thesis)

  4. Albert Dominguez Mantes (EPFL) - Improving image-based spatial transcriptomics by jointly learning gene detection and linking (PhD thesis)

  5. Mireia Masias (UPF) - Predicting structural brain trajectories with discrete optimal transport normalizing flows (PhD thesis)

  6. Joaquín Justel Pizarro (UB) - Deep learning for identification of biological forms (PhD)

  7. Maria Perera Baro (Standford) - Generative moment matching networks for genotype simulation (EMBC)

  8. Javier Garcia (Sycai) - Benchmarking of DL architectures and uncertainy computation for pancretic cystic lesions segmentation on CT scan images


NLP & Speech

  1. Javier Ferrando (UPC) - Measuring the Mixing of Contextual Information in the Transformer (EMNLP)

  2. Ona de Gibert Bonet (BSC) - Unsupervised Machine Translation in Real-World Scenarios (LREC)

  3. Ioannis Tsiamas (UPC) - Efficient Speech Translation with Dynamic Latent Perceivers (Preprint)


Machine Learning & Reinforcement Learning

  1. Sergio Calo (UPF) - A novel message passing approach to spatial air quality prediction in urban areas (MSc)

  2. Daniel Bonet-Solà (La Salle) - Automatic detection of noise sources in citizen-science project 'Sons al Balcó' (PhD)

  3. Chiara Mastrogiuseppe (UPF) - Controlling Chaos in a Recurrent Neural Network with a Maximising Action Entropy Agent (PhD)

  4. Jorge Ramírez-Ruiz (UPF) - Seeking entropy: Complex behavior from intrinsic motivation to occupy action-state path space (PhD thesis)


Multimodal

  1. Alvaro Budria (UPC-IRI) - Topic Detection in Continuous Sign Language Videos (CVPR w)

  2. Rubèn Pérez Tito (UAB-CVC) - OCR-IDL: OCR Annotations for Industry Document Library Dataset (ECCV 2022)

Posters: Afternoon (18:00-19:30)

Sala Àgora

Vision

  1. Robert Benavente (CVC-UAB) - Super Resolution of Multiple Remote Sensing Images using 3D Residual in Residual Dense Blocks (CVPR w)

  2. Eduardo Aguilar (CVC-UAB) - Bayesian deep learning for semantic segmentation of food images (Journal)

  3. Pere Gilabert (UB) - Improving CCE video review time with a model based on frame similarity (MIDL)

  4. Agata Lapedriza (UOC) - Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents (PAMI)

  5. Pablo Arias (ENS Paris-Saclay) - Self-supervised super-resolution for multi-exposure push-frame satellites (CVPR)

  6. Felipe Perez Stoppa (La Salle) - Album cover art image generation with Generative Adversarial Networks (PhD)

  7. Mariona Carós (UB) - Object Segmentation of Cluttered Airborne LiDAR Point Clouds (CCIA)


Med Vision and Life Sciences

  1. Oscar Pina (UPC) - Self-supervised graph representations of WSIs (JMLR)

  2. Valentin Comte (UPF) - Unsupervised fetal brain MR segmentation using multi-atlas deep learning registration (NeurIPS)


NLP & Speech

  1. Kim Cheng Sheang (UPF) - Sentence Simplification Capabilities of Transfer-Based Models (AAAI)

  2. Maite Melero (BSC) - On the Multilingual Capabilities of Very Large-Scale English Language Models (LREC)

  3. Gerard I. Gállego (UPC) - On the Locality of Attention in Direct Speech Translation (ACL SRW)

  4. Gerard Sant (UPC-BSC) - Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation (NAACL)


Machine Learning

  1. Guillermo Torres (UAB-CVC) - Learning networks hyper-parameter using multi-objective optimization of statistical measures (SYNASC-DIPMAI)

  2. Paula Gómez (UB) - Contextual TV show recommendation (CCIA)

  3. Marina Estévez-Almenzar (UPF) - The Relevance of Non-Human Errors in Machine Learning (IJCAI w)

  4. David Bonet (UPC) - Channel Redundancy and Overlap in Convolutional Neural Networks with Channel-Wise NNK Graphs (ICASSP)


Multimodal

  1. Juan F. Montesinos (UPF) - VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices (Interspeech)

  2. Laia Tarrés (UPC) - Tackling Low-Resource Sign Language Translation: UPC at WMT-SLT 22 (EMNLP WMT-SLT)

  3. Oscar Mañas (MILA) - MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting (PhD)

  4. Carles Ventura (UOC) - Modeling Subjective Affect Annotations with Multi-Task Learning (Sensors Journal)

  5. Míriam Bellver Bueno (Amazon) - RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation (MTAP)