no code implementations • 1 May 2024 • Lucas-Andreï Thil, Mirela Popa, Gerasimos Spanakis
Supervised learning (SL) approaches have achieved impressive performance while utilizing significantly less training data compared to previous methods.
no code implementations • 29 May 2023 • Andreas Petridis, Mirela Popa, Filipa Peleja, Dario Dotti, Alberto de Santos
Then, other models knowing that there's a human and its composition (e. g. not always we have a full-body) finds the bounding boxes/regions of the image that very likely correspond to a bottom or a top.
1 code implementation • 9 Jun 2021 • Oliver Bensch, Mirela Popa, Constantin Spille
Therefore, natural language processing models have already been combined with computer vision models in the past, to benefit from e. g. positional information and to improve performance of these key information extraction models.
no code implementations • 15 Oct 2019 • Dario Dotti, Mirela Popa, Stylianos Asteriadis
Experiments on two public datasets demonstrate the effectiveness of jointly modeling the mutual Person-Context information, outperforming the state-of-the art-results for personality recognition in two different scenarios.