DESIRE

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

Keras version of Realtime Multi-Person Pose Estimation project

A deep neural network for face alignment

Simple baselines and RNNs for predicting human motion in tensorflow. Presented at CVPR 17.

Tensorflow Implementation of Knowledge-Guided CVAE for dialog generation ACL 2017. It is released by Tiancheng Zhao (Tony) from Dialog Research Center, LTI, CMU

Image Captions Generation with Spatial and Channel-wise Attention

Tensorflow implementation of conditional variational auto-encoder for MNIST

Learning cell communication from spatial graphs of cells

Conditional out-of-distribution prediction