From a5522d078413e340a2caa1ab0c86d76d2b7efa40 Mon Sep 17 00:00:00 2001 From: David Ding Date: Wed, 4 Aug 2021 16:45:11 +0100 Subject: [PATCH] Update paper title for ALOE. PiperOrigin-RevId: 388705574 --- object_attention_for_reasoning/README.md | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/object_attention_for_reasoning/README.md b/object_attention_for_reasoning/README.md index b62c2f5..e3f51d4 100644 --- a/object_attention_for_reasoning/README.md +++ b/object_attention_for_reasoning/README.md @@ -1,16 +1,15 @@ -Implementation of the object-based transformer model from -["Object-based attention for spatio-temporal reasoning"](https://arxiv.org/abs/2012.08508) +Implementation of the ALOE model +["Attention over learned object embeddings enables complex visual reasoning"](https://arxiv.org/abs/2012.08508) [1]. -This package includes source code for the transformer model, +This package includes source code for the ALOE transformer model, pre-trained model parameters for the CLEVRER task, and MONet [2] latent variables for all videos in the training and validation sets. It does not include the model training code. See Section 2 of [1] for details. -[1] David Ding, Felix Hill, Adam Santoro, Matt Botvinick. *Object-based -attention for spatio-temporal reasoning: Outperforming neuro-symbolic models -with flexible distributed architectures*. +[1] David Ding, Felix Hill, Adam Santoro, Malcolm Reynolds, Matt Botvinick. +*Attention over learned object embeddings enables complex visual reasoning*. arXiv preprint arXiv:2012.08508, 2020. [2] Chris P. Burgess, Loic Matthey, Nick Watters, Rishabh Kabra, Irina Higgins, @@ -43,10 +42,9 @@ answers should be correct. If you find the provided code useful, please cite this paper: ``` -@article{objectattention2020, - title={Object-based attention for spatio-temporal reasoning: Outperforming - neuro-symbolic models with flexible distributed architectures}, - author={David Ding and Felix Hill and Adam Santoro and Matt Botvinick}, +@article{aloe2020, + title={Attention over learned object embeddings enables complex visual reasoning}, + author={David Ding and Felix Hill and Adam Santoro and Malcolm Reynolds and Matt Botvinick}, journal={arXiv preprint arXiv:2012.08508}, year={2020} }