Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.

2.86% and 15.85% on CIFAR-10 and CIFAR-100

This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.

A Compositional Object-Based Approach to Learning Physical Dynamics

Real time face alignment

Training code for the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.

Torch Implementation of NIPS'16 paper: Perspective Transformer Nets

Torch implementation of the paper "Deep Pyramidal Residual Networks" (https://arxiv.org/abs/1610.02915).

3D ResNets for Action Recognition

This repository implements a demo of the Human pose estimation via Convolutional Part Heatmap Regression paper.

Implementation of "Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network" by Z.Laskar et al.

Semantic Similarity Measurement of Texts using Convolutional Neural Networks (He et al., EMNLP 2015)

Code for the paper entitled "Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods".

Video classification tools using 3D ResNet

An unofficial Torch implementation of InfoGAN

Temporal augmentation with two-stream ConvNet features on human action recognition

Autoencoder trained on ImageNet Using Torch 7

Kuang-Yu Chang, Kung-Hung Lu, and Chu-Song Chen, "Aesthetic Critiques Generation for Photos," International Conference on Computer Vision, ICCV 2017, October 2017.

Deep reinforcement learning package for torch7