Posters Wed PM

Optimization

1. Konstantin Schürholt (HSG) - Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction (NeurIPS 2021)

Language & Vision

2. Lluís Gómez (CVC) - Is an image worth five sentences? A new look into semantics for image-text matching (WACV 2022)

3. Rubén Tito (CVC-UAB) - Document visual question answering (ICDAR 2021)

4. Carles Ventura (UOC) - SynthRef: generation of synthetic referring expressions for object segmentation (NAACL-W 2021)

Natural Language Processing

5. Andreas Kaltenbrunner (UPF) - Uncovering the limits of text-based emotion detection (EMNLP Findings 2021)

Genomics

6. Albert Domínguez (Stanford-UPC) - Neural ADMIXTURE: rapid population clustering with autoencoders (SMBE 2021)

7. Margarita Geleta (UPC/Stanford) - Deep variational autoencoders for population genetics (ASHG 2021)

(Will not present)

8. Carlos Mougan (Southampton) - Desiderata for explainable AI in statistical production systems of the European Central Bank (ECML-PKDD-W 2021)

9. Javier Ferrando (UPC) - Attention weights in transformer NMT fail aligning words between sequences but largely explain model predictions (EMNLP Findings 2021)

10. Juan Felipe Montesinos (UPF) - A cappella: audio-visual singing voice separation (BMVC 2021)