Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Barquero Germán"'
Autor:
Ponce, Pablo Ruiz, Barquero, German, Palmero, Cristina, Escalera, Sergio, Garcia-Rodriguez, Jose
Generating human-human motion interactions conditioned on textual descriptions is a very useful application in many areas such as robotics, gaming, animation, and the metaverse. Alongside this utility also comes a great difficulty in modeling the hig
Externí odkaz:
http://arxiv.org/abs/2404.09988
Conditional human motion generation is an important topic with many applications in virtual reality, gaming, and robotics. While prior works have focused on generating motion guided by text, music, or scenes, these typically result in isolated motion
Externí odkaz:
http://arxiv.org/abs/2402.15509
Autor:
Song, Siyang, Spitale, Micol, Luo, Cheng, Palmero, Cristina, Barquero, German, Zhu, Hengde, Escalera, Sergio, Valstar, Michel, Baur, Tobias, Ringeval, Fabien, Andre, Elisabeth, Gunes, Hatice
In dyadic interactions, humans communicate their intentions and state of mind using verbal and non-verbal cues, where multiple different facial reactions might be appropriate in response to a specific speaker behaviour. Then, how to develop a machine
Externí odkaz:
http://arxiv.org/abs/2401.05166
Autor:
Song, Siyang, Spitale, Micol, Luo, Cheng, Barquero, German, Palmero, Cristina, Escalera, Sergio, Valstar, Michel, Baur, Tobias, Ringeval, Fabien, Andre, Elisabeth, Gunes, Hatice
The Multi-modal Multiple Appropriate Facial Reaction Generation Challenge (REACT2023) is the first competition event focused on evaluating multimedia processing and machine learning techniques for generating human-appropriate facial reactions in vari
Externí odkaz:
http://arxiv.org/abs/2306.06583
Publikováno v:
Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023
Stochastic human motion prediction (HMP) has generally been tackled with generative adversarial networks and variational autoencoders. Most prior works aim at predicting highly diverse movements in terms of the skeleton joints' dispersion. This has l
Externí odkaz:
http://arxiv.org/abs/2211.14304
Autor:
Barquero, German, Núñez, Johnny, Xu, Zhen, Escalera, Sergio, Tu, Wei-Wei, Guyon, Isabelle, Palmero, Cristina
Publikováno v:
Proceedings of Machine Learning Research, 2022
Human behavior forecasting during human-human interactions is of utmost importance to provide robotic or virtual agents with social intelligence. This problem is especially challenging for scenarios that are highly driven by interpersonal dynamics. I
Externí odkaz:
http://arxiv.org/abs/2203.03245
Autor:
Barquero, German, Núñez, Johnny, Escalera, Sergio, Xu, Zhen, Tu, Wei-Wei, Guyon, Isabelle, Palmero, Cristina
Publikováno v:
Proceedings of Machine Learning Research, 2022
Non-verbal social human behavior forecasting has increasingly attracted the interest of the research community in recent years. Its direct applications to human-robot interaction and socially-aware human motion generation make it a very attractive fi
Externí odkaz:
http://arxiv.org/abs/2203.02480
Publikováno v:
IEEE Transactions on Biometrics, Behavior, and Identity Science, 2021
Most current multi-object trackers focus on short-term tracking, and are based on deep and complex systems that often cannot operate in real-time, making them impractical for video-surveillance. In this paper we present a long-term, multi-face tracki
Externí odkaz:
http://arxiv.org/abs/2107.13273
Most current multi-object trackers focus on short-term tracking, and are based on deep and complex systems that do not operate in real-time, often making them impractical for video-surveillance. In this paper, we present a long-term multi-face tracki
Externí odkaz:
http://arxiv.org/abs/2010.08675
Autor:
La Rosa, Francesco, Yu, Thomas, Barquero, Germán, Thiran, Jean-Philippe, Granziera, Cristina, Bach Cuadra, Meritxell
Publikováno v:
In Computers in Biology and Medicine May 2021 132