Model parallel transformers in JAX and Haiku

A first-of-its-kind acoustic simulation platform for audio-visual embodied AI research. It supports training and evaluating multiple tasks and applications.

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

End-to-End Learning of Motion Representation for Video Understanding

A pytorch implemention of "StyleNet: Generating Attractive Visual Captions with Styles"

VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

PaddlePaddle models for Youtube-8M Video Understanding Challenge

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

Using Semantic Compositional Networks for Video Captioning

The Theano code for the CVPR 2017 paper "Semantic Compositional Networks for Visual Captioning"

Recurrent Neural Network library for Torch7's nn

Simple tutorials using Google's TensorFlow Framework

code for Stacked attention networks for image question answering