Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Berga, David"'
Autor:
Berga, David, Pereda, Alexandre, De Filippi, Eleonora, Nandi, Arijit, Febrer, Eulalia, Reverte, Marta, Russo, Lautaro
Esports gaming is an area in which videogame players need to cooperate and compete with each other, influencing their cognitive load, processing, stress, and social skills. Here it is unknown to which extent competitive videogame play using a desktop
Externí odkaz:
http://arxiv.org/abs/2302.14269
Autor:
Berga, David, Gallés, Pau, Takáts, Katalin, Mohedano, Eva, Riordan-Chen, Laura, Garcia-Moll, Clara, Vilaseca, David, Marín, Javier
Latest advances in Super-Resolution (SR) have been tested with general purpose images such as faces, landscapes and objects, mainly unused for the task of super-resolving Earth Observation (EO) images. In this research paper, we benchmark state-of-th
Externí odkaz:
http://arxiv.org/abs/2210.06618
Publikováno v:
2021
Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects. Neural networks for saliency estimation require ground truth saliency maps for training which are usually achieved via eyetracking experi
Externí odkaz:
http://arxiv.org/abs/2107.09628
Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification. In the current paper, we propose an approach which does not
Externí odkaz:
http://arxiv.org/abs/2007.12562
We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested classification accuracy and fo
Externí odkaz:
http://arxiv.org/abs/2007.06356
Autor:
Wang, Yaxing, Gonzalez-Garcia, Abel, Berga, David, Herranz, Luis, Khan, Fahad Shahbaz, van de Weijer, Joost
One of the attractive characteristics of deep neural networks is their ability to transfer knowledge obtained in one domain to other related domains. As a result, high-quality networks can be trained in domains with relatively little training data. T
Externí odkaz:
http://arxiv.org/abs/1912.05270
Publikováno v:
The IEEE International Conference on Computer Vision (ICCV) 2019
A benchmark of saliency models performance with a synthetic image dataset is provided. Model performance is evaluated through saliency metrics as well as the influence of model inspiration and consistency with human psychophysics. SID4VAM is composed
Externí odkaz:
http://arxiv.org/abs/1910.13066
Autor:
Berga, David, Otazu, Xavier
Previous studies suggested that lateral interactions of V1 cells are responsible, among other visual effects, of bottom-up visual attention (alternatively named visual salience or saliency). Our objective is to mimic these connections with a neurodyn
Externí odkaz:
http://arxiv.org/abs/1904.02741
In this study we provide the analysis of eye movement behavior elicited by low-level feature distinctiveness with a dataset of synthetically-generated image patterns. Design of visual stimuli was inspired by the ones used in previous psychophysical e
Externí odkaz:
http://arxiv.org/abs/1811.06458
Autor:
Berga, David, Otazu, Xavier
Lateral connections in the primary visual cortex (V1) have long been hypothesized to be responsible of several visual processing mechanisms such as brightness induction, chromatic induction, visual discomfort and bottom-up visual attention (also name
Externí odkaz:
http://arxiv.org/abs/1811.06308