Zobrazeno 1 - 10
of 107
pro vyhledávání: '"Baró, Xavier"'
Autor:
Egele, Romain, Junior, Julio C. S. Jacques, van Rijn, Jan N., Guyon, Isabelle, Baró, Xavier, Clapés, Albert, Balaprakash, Prasanna, Escalera, Sergio, Moeslund, Thomas, Wan, Jun
Machine learning is now used in many applications thanks to its ability to predict, generate, or discover patterns from large quantities of data. However, the process of collecting and transforming data for practical use is intricate. Even in today's
Externí odkaz:
http://arxiv.org/abs/2404.09703
Autor:
Bonafonte, Irene, Bustos, Cristina, Larrazolo, Abraham, Luna, Gilberto Lorenzo Martinez, Arenas, Adolfo Guzman, Baro, Xavier, Tourgeman, Isaac, Balcells, Mercedes, Lapedriza, Agata
The possibility of recognizing diverse aspects of human behavior and environmental context from passively captured data motivates its use for mental health assessment. In this paper, we analyze the contribution of different passively collected sensor
Externí odkaz:
http://arxiv.org/abs/2310.13607
Autor:
Escalera, Sergio, Soler, Marti, Ayache, Stephane, Guclu, Umut, Wan, Jun, Madadi, Meysam, Baro, Xavier, Escalante, Hugo Jair, Guyon, Isabelle
Publikováno v:
Inpainting and Denoising Challenges. The Springer Series on Challenges in Machine Learning. Springer, Cham. (2019)
Dealing with incomplete information is a well studied problem in the context of machine learning and computational intelligence. However, in the context of computer vision, the problem has only been studied in specific scenarios (e.g., certain types
Externí odkaz:
http://arxiv.org/abs/2106.13071
Autor:
Junior, Julio C. S. Jacques, Lapedriza, Agata, Palmero, Cristina, Baró, Xavier, Escalera, Sergio
This work revisits the ChaLearn First Impressions database, annotated for personality perception using pairwise comparisons via crowdsourcing. We analyse for the first time the original pairwise annotations, and reveal existing person perception bias
Externí odkaz:
http://arxiv.org/abs/2011.14906
While many individual tasks in the domain of human analysis have recently received an accuracy boost from deep learning approaches, multi-task learning has mostly been ignored due to a lack of data. New synthetic datasets are being released, filling
Externí odkaz:
http://arxiv.org/abs/1905.03003
Autor:
Junior, Julio C. S. Jacques, Ozcinar, Cagri, Marjanovic, Marina, Baró, Xavier, Anbarjafari, Gholamreza, Escalera, Sergio
Automatic age estimation from facial images represents an important task in computer vision. This paper analyses the effect of gender, age, ethnic, makeup and expression attributes of faces as sources of bias to improve deep apparent age prediction.
Externí odkaz:
http://arxiv.org/abs/1902.07653
Autor:
Madadi, Meysam, Avots, Egils, Escalera, Sergio, Gonzalez, Jordi, Baro, Xavier, Anbarjafari, Gholamreza
A new approach for 2D to 3D garment retexturing is proposed based on Gaussian mixture models and thin plate splines (TPS). An automatically segmented garment of an individual is matched to a new source garment and rendered, resulting in augmented ima
Externí odkaz:
http://arxiv.org/abs/1809.08064
Autor:
Junior, Julio C. S. Jacques, Güçlütürk, Yağmur, Pérez, Marc, Güçlü, Umut, Andujar, Carlos, Baró, Xavier, Escalante, Hugo Jair, Guyon, Isabelle, van Gerven, Marcel A. J., van Lier, Rob, Escalera, Sergio
Personality analysis has been widely studied in psychology, neuropsychology, and signal processing fields, among others. From the past few years, it also became an attractive research area in visual computing. From the computational point of view, by
Externí odkaz:
http://arxiv.org/abs/1804.08046
Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view inv
Externí odkaz:
http://arxiv.org/abs/1804.04419