Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Feedforward style transfer

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

Neural model for converting Image-to-Markup (by Yuntian Deng yuntiandeng.com)

Code to test and use the model from "Stacked Hourglass Networks for Human Pose Estimation"

Spatio-temporal video autoencoder with convolutional LSTMs

BodyNet: Volumetric Inference of 3D Human Body Shapes, ECCV 2018

Code for Structured Attention Networks https://arxiv.org/abs/1702.00887

Code for "Learning Feature Pyramids for Human Pose Estimation" (ICCV 2017)

Code repository for Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

Activity Recognition Algorithms for the Charades Dataset

Code for "Multi-Context Attention for Human Pose Estimation " (CVPR 2017)

IPAM Tutorials on Theano/Torch

Training code for "Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose", CVPR 2017

Long-term Temporal Convolutions for Action Recognition, TPAMI 2018

Demo code for "Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose", CVPR 2017

Relative Camera Pose Estimation Using Convolutional Neural Networks

Code for training temporal fully-connected CRF models in Torch

Code for "Harvesting Multiple Views for Marker-less 3D Human Pose Annotations", CVPR 2017