Image-to-image translation with conditional adversarial nets

3.8% and 18.3% on CIFAR-10 and CIFAR-100

Sequence-to-sequence model with LSTM encoder/decoders and attention

Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)

Multi-Scale Dense Networks for Resource Efficient Image Classification （ICLR 2018 Oral）

Spatio-temporal video autoencoder with convolutional LSTMs

[ECCV 2018] Video Object Detection with an Aligned Spatial-Temporal Memory