diff --git a/README.md b/README.md
index d4f4ccf..5bc3b07 100644
--- a/README.md
+++ b/README.md
@@ -1,9 +1,25 @@
-# Semantic-Aware Scene Recognition
+
+Semantic-Aware Scene Recognition
+
+
+
+
+ 
+
+
+ 
+
+ 
+
+
Official Pytorch Implementation of [Semantic-Aware Scene Recognition](https://arxiv.org/abs/1909.02410) by Alejandro López-Cifuentes, Marcos Escudero-Viñolo, Jesús Bescós and Álvaro García-Martín.
This paper is currently under Peer Review Revision in Elsevier Pattern Recognition Journal.
-
+
+ 
+
+
## Summary
This paper propose to improve scene recognition by using object information to focalize learning during the training process. The main contributions of the paper are threefold:
@@ -13,7 +29,9 @@ This paper propose to improve scene recognition by using object information to f
- We validate the effectiveness of the proposed method through experimental results on public scene recognition datasets such as ADE20K, MIT Indoor 67, SUN 397 and Places365 obtaining state-of-the-art results.
The propose CNN architecture is as follows:
-
+
+ 
+
## Results
### ADE20K Dataset
@@ -23,6 +41,7 @@ The propose CNN architecture is as follows:
| | ✓ | 50.60 | 60.45| 72.10 | 12.17 |
| **✓** | **✓** | **62.55** | **73.25** | **82.75** | **27.00** |
+
### MIT Indoor 67 Dataset
| Method | Backbone| Number of Parameters | Top@1 |
|--|:--:|:--:|:--:|
@@ -153,11 +172,15 @@ If you find this work useful, please consider citing:
```
@article{lopez2019semantic,
title={Semantic-Aware Scene Recognition},
- author={L{\'o}pez-Cifuentes, Alejandro and Escudero-Vi{\~n}olo, Marcos and Besc{\'o}s, Jes{\'u}s and Garc{\'\i}a, {\'A}lvaro},
+ author={L{\'o}pez-Cifuentes, Alejandro and Escudero-Vi{\~n}olo, Marcos and
+ Besc{\'o}s, Jes{\'u}s and Garc{\'\i}a, {\'A}lvaro},
journal={arXiv preprint arXiv:1909.02410},
year={2019}
}
```
## Acknowledgment
This study has been partially supported by the Spanish Government through its TEC2017-88169-R MobiNetVideo project.
-
+
+
+ 
+