Publications

Learning representational invariance instead of categorization . Alex Hernandez-Garcia, Peter König, 2019 . International Conference on Computer Vision (ICCV), Workshop on pre-registration in Computer Vision paper

Global visual salience of competing stimuli . Alex Hernandez-Garcia, Ricardo Ramos Gameiro, Alessandro Grillini, Peter König, 2019 . PsyArXiv:z7qp5 paper

Learning robust visual representations using data augmentation invariance . Alex Hernandez-Garcia, Peter König, Tim C. Kietzmann, 2019 . arXiv:1906.04547 paper

Data augmentation instead of explicit regularization . Alex Hernandez-Garcia, Peter König, 2018 . arXiv:1806.03852 paper

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT . Alex Hernandez-Garcia, Johannes Mehrer, Nikolaus Kriegeskorte, Peter König, Tim C. Kietzmann, 2018 . Cognitive Computational Neuroscience (CCN) paper

Do deep nets really need weight decay and dropout? . Alex Hernandez-Garcia, Peter König, 2018 . arXiv:1802.07042 paper

Further advantages of data augmentation on convolutional neural networks . Alex Hernandez-Garcia, Peter König, 2018 . International Conference on Artificial Neural Networks (ICANN) Best Paper Award paper

Emotion and attention: predicting electrodermal activity through video visual descriptors . Alex Hernandez-Garcia, Fernando Fernández-Martínez, Fernando Díaz de María, 2017 . Int. Workshop on Affective Computing and Emotion Recognition (ACER) paper

Exploiting visual saliency for assessing the impact of car commercials upon viewers . Fernando Fernández-Martínez, Alex Hernandez-Garcia, Miguel Ángel Fernández-Torres, Iván González-Díaz, Álvaro García-Faura, Fernando Díaz de María, 2017 . Multimedia Tools and Applications paper

Comparing visual descriptors and automatic rating strategies for video aesthetics prediction . Alex Hernandez-Garcia, Fernando Fernández-Martínez, Fernando Díaz de María, 2016 . Journal of Signal Processing: Image Communication paper

Succeeding metadata based annotation scheme and visual tips for the automatic assessment of video aesthetic quality in car commercials . Fernando Fernández-Martínez, Alex Hernandez-Garcia, Fernando Díaz de María, 2015 . Internation Journal Expert Systems with Applications paper

Combining audio-visual features for viewers’ perception classification of Youtube car commercials . Fernando Fernández-Martínez, Alex Hernandez-Garcia, Ascensión Gallardo-Antolín, Fernando Díaz de María, 2014 . Speech, Language and Audio in Multimedia (SLAM) paper

Talks

Learning representational invariance instead of categorization. International Conference on Computer Vision (ICCV), Workshop on pre-registration in Computer Vision, Seoul (Republic of Korea). November 2019 link video

Data augmentation for improved regularization and invariance learning. Department of Brain and Cognitive Engineering, Korea University, Seoul (Republic of Korea). November 2019

Learning robust visual representations using data augmentation invariance. Computational Cognition, Osnabrück (Germany). October 2019 link video

More than more data: undervalued advantages of data augmentation for deep learning and computational neuroscience. Neural Information Processing Group, University of Tübingen, Tübingen (Germany). July 2019 link

Data augmentation: an alternative to explicit regularization and other undervalued advantages. Berlin Machine Learning Meetup, Berlin (Germany). July 2019 link

Data augmentation: undervalued advantages for deep learning and computational neuroscience. Cognitive Neuroscience Center, University Medical Center Groningen, Groningen (Netherlands). June 2019

On the advantages of data augmentation for deep learning and computational neuroscience. Neural Dynamics of Visual Cognition Lab, Freie Universität Berlin, Berlin (Germany). February 2019

Data augmentation as a biologically plausible alternative to explicit regularization in CNNs. Institute of Informatics and Telecommunications, NCSR Demokritos, Athens (Greece). October 2018 link

Data augmentation instead of explicit regularization. Group of Multimedia Processing, University Carlos III of Madrid, Madrid (Spain). May 2018

Data augmentation instead of explicit regularization. Deep Learning Meetup, Berlin (Germany). December 2017