Representation learning: A review and new perspectives, 2013. ,

DOI : 10.1109/tpami.2013.50

URL : http://www.cs.princeton.edu/courses/archive/spring13/cos598C/Representation Learning - A Review and New Perspectives.pdf

Discriminative learning for differing training and test distributions, ICML, 2009. ,

DOI : 10.1145/1273496.1273507

URL : http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2007/papers/303.pdf

, Learning disentangled representations from grouped observations. AAAI Conference on Artificial Intelligence, 2018.

Isolating sources of disentanglement in variational autoencoders, NeurIPS, 2018. ,

Infogan: Interpretable representation learning by information maximizing generative adversarial nets, NIPS, 2016. ,

Unsupervised learning of disentangled representations from video, NIPS, 2017. ,

Disentangling factors of variation via generative entangling, ICML, 2012. ,

Semantically decomposing the latent spaces of generative adversarial networks, 2018. ,

Adversarial feature learning, 2017. ,

, , 2017.

What the face reveals: Basic and applied studies of spontaneous expression using the Facial Action Coding System (FACS), 1997. ,

Dual swap disentangling, NeurIPS, pp.5898-5908, 2018. ,

Image-to-image translation for cross-domain disentanglement, 2018. ,

Generative adversarial nets, NIPS, 2014. ,

BetaVAE: Learning basic visual concepts with a constrained variational framework, 2017. ,

10} using a uniform distribution. Apply a dilation operation over the image using a squared kernel with pixel-size equal to the generated number, Generate a random integer in the range {1 ,

, Normalize the resulting vector as?c as? as?c = c/||c|| 1. Multiply the RGB components of all the pixels in the image by?cby? by?c

2017) are not accurate. As detailed in the original paper, the inter-observer agreement is significantly low for neutral images. In contrast, in our reference-set, each image was annotated in terms of "neutral" / "non-neutral" by two different annotators ,