# Multimodal Deep Quality Embedding Network for Affective Video Content Analysis

**Repository Path**: USTC_HISAI/MMDQEN

## Basic Information

- **Project Name**: Multimodal Deep Quality Embedding Network for Affective Video Content Analysis
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2021-07-09
- **Last Updated**: 2021-07-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# MMDQEN: Multimodal Deep Quality Embedding Network for Affective Video Content Analysis

This is our implementation of MMDQEN associated with the following papers:

 >**Affective video content analysis via multimodal deep quality embedding network,**  
 >Yaochen Zhu, Zhenzhong Chen, Feng Wu  
 >IEEE Trans. Affect. Compute, 2020.

 >**Multimodal deep denoise framework for affective video content analysis,**  
 >Yaochen Zhu, Zhenzhong Chen, Feng Wu  
 >ACM International Conference on Multimedia 2019.

## Environment

The codes are written in Python 3.6.5 with the following packages.  

- numpy == 1.16.3
- tensorflow-gpu == 1.13.1
- tensorflow-probability == 0.6.0

## Datasets

The original LIRIS-ACCEDE dataset can be accessed with this [URL](https://liris-accede.ec-lyon.fr).

## Examples to run the codes

- **Extract the multimodal feature as described in the paper**: 

- **Train the MMDQEN model via**: 
	
	```python train.py --affect {val, aro}```

For more advanced arguments, run the code with --help argument.
  

## If you find the codes useful, please cite:

	@inproceedings{zhu2019multimodal,
	  title={Multimodal deep denoise framework for affective video content analysis},
	  author={Zhu, Yaochen and Chen, Zhenzhong and Wu, Feng},
	  booktitle={Proceedings of the 27th ACM International Conference on Multimedia},
	  pages={130--138},
	  year={2019}
	}

	@article{zhu2020affective,
	  title={Affective video content analysis via multimodal deep quality embedding network},
	  author={Zhu, Yaochen and Chen, Zhenzhong and Wu, Feng},
	  journal={IEEE Transactions on Affective Computing},
	  year={2020},
	  publisher={IEEE}
	}