Spaces:
Configuration error
Configuration error
Upload README.md
Browse files
README.md
CHANGED
|
@@ -1,11 +1,64 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<div align="center">
|
| 2 |
+
<p align="center">
|
| 3 |
+
<img src="assets/img/web_teaser.png" width=500px/>
|
| 4 |
+
</p>
|
| 5 |
+
<h1 align="center">
|
| 6 |
+
</h1>
|
| 7 |
+
<h1 align="center">
|
| 8 |
+
Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
|
| 9 |
+
</h1>
|
| 10 |
+
|
| 11 |
+
[](#)
|
| 12 |
+
[](#)
|
| 13 |
+
[](https://affective-visual-dialog.github.io/)
|
| 14 |
+
|
| 15 |
+
</div>
|
| 16 |
+
|
| 17 |
+
## 📰 News
|
| 18 |
+
|
| 19 |
+
- **30/08/2023**: The preprint of our paper is now available on [arXiv](https://arxiv.org/abs/2308.16349).
|
| 20 |
+
|
| 21 |
+
## Summary
|
| 22 |
+
|
| 23 |
+
- [📰 News](#-news)
|
| 24 |
+
- [Summary](#summary)
|
| 25 |
+
- [📚 Introduction](#-introduction)
|
| 26 |
+
- [📊 Baselines](#-baselines)
|
| 27 |
+
- [Citation](#citation)
|
| 28 |
+
- [References](#references)
|
| 29 |
+
|
| 30 |
+
<br>
|
| 31 |
+
|
| 32 |
+
## 📚 Introduction
|
| 33 |
+
|
| 34 |
+
AffectVisDial is a large-scale dataset which consists of 50K 10-turn visually grounded dialogs as well as concluding emotion attributions and dialog-informed textual emotion explanations.
|
| 35 |
+
|
| 36 |
+
<br>
|
| 37 |
+
|
| 38 |
+
## 📊 Baselines
|
| 39 |
+
|
| 40 |
+
We provide baseline models explanation generation task:
|
| 41 |
+
- [GenLM](./baselines/GenLM/): BERT- and BART-based models [3, 4]
|
| 42 |
+
- [NLX-GPT](./baselines/nlx): NLX-GPT based model [1]
|
| 43 |
+
|
| 44 |
+
<br>
|
| 45 |
+
|
| 46 |
+
## Citation
|
| 47 |
+
|
| 48 |
+
If you use our dataset, please cite the two following references:
|
| 49 |
+
|
| 50 |
+
```bibtex
|
| 51 |
+
@article{haydarov2023affective,
|
| 52 |
+
title={Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations},
|
| 53 |
+
author={Haydarov, Kilichbek and Shen, Xiaoqian and Madasu, Avinash and Salem, Mahmoud and Li, Li-Jia and Elsayed, Gamaleldin and Elhoseiny, Mohamed},
|
| 54 |
+
journal={arXiv preprint arXiv:2308.16349},
|
| 55 |
+
year={2023}
|
| 56 |
+
}
|
| 57 |
+
```
|
| 58 |
+
</br>
|
| 59 |
+
|
| 60 |
+
## References
|
| 61 |
+
1. _[Sammani et al., 2022] - NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
|
| 62 |
+
2. _[Li et al., 2022]_ - BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
|
| 63 |
+
3. _[Lewis et al., 2019]_ - BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension.
|
| 64 |
+
4. _[Dewlin et al., 2018]_ - BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
|