1. Network dissection: Quantifying interpretability of deep visual representations;Bau,2017
2. Quo vadis, action recognition? A new model and the kinetics dataset;Carreira,2017
3. ImageNet: A large-scale hierarchical image database;Deng,2009
4. A variational U-Net for conditional appearance and shape generation;Esser,2018
5. Fortuin, V., Hüser, M., Locatello, F., Strathmann, H., & Rätsch, G. (2019). SOM-VAE: Interpretable discrete representation learning on time series. In 7th international conference on learning representations , ICLR (pp. 18).