From e4ac909df7eb0957d4974d52fc62b424304f512b Mon Sep 17 00:00:00 2001 From: Sebastian Borgeaud Date: Wed, 16 Oct 2019 18:01:10 +0100 Subject: [PATCH] Internal PiperOrigin-RevId: 275055018 --- transporter/README.md | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/transporter/README.md b/transporter/README.md index 67d3cf0..6ed3756 100644 --- a/transporter/README.md +++ b/transporter/README.md @@ -1,7 +1,9 @@ # Transporter - Unsupervised Learning of Object Keypoints for Perception and Control This directory contains a [Sonnet](https://sonnet.dev) implementation of -the Transporter architecture. +the Transporter architecture and a notebook explaining how the model can be used +for keypoint inference. To launch the notebook in Google colab, [click here](https://colab.research.google.com/github/deepmind/deepmind_research/blob/master/transporter/transporter_example.ipynb). + The Transporter is a neural network architecture for discovering concise geometric object representations in terms of keypoints or image-space @@ -13,6 +15,9 @@ across long time-horizons more accurately than recent similar methods. For details, see our paper [Unsupervised Learning of Object Keypoints for Perception and Control](https://arxiv.org/abs/1906.11883). +If you use the code here please cite this paper. +> Tejas Kulkarni, Ankush Gupta, Catalin Ionescu, Sebastian Borgeaud, Malcolm Reynolds, Andrew Zisserman, Volodymyr Mnih. *Unsupervised Learning of Object Keypoints for Perception and Control*. NeurIPS 2019. [\[arXiv\]](https://arxiv.org/abs/1906.11883). + ## Contributors * Tejas Kulkarni * Ankush Gupta @@ -23,3 +28,6 @@ paper [Unsupervised Learning of Object Keypoints for Perception and Control](htt * Volodymyr Mnih +## Disclaimer +This is not an official Google product. +