Introduction

This is the source code of our TCSVT 2020 paper "Reinforced Cross-Media Correlation Learning by Context-Aware Bidirectional Translation". Please cite the following paper if you use our code.

Yuxin Peng and Jinwei Qi, "Reinforced Cross-Media Correlation Learning by Context-Aware Bidirectional Translation", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 30, No. 6, pp. 1718-1731, Jun. 2020.(SCI, EI)

Dependency

This code is implemented with tensorflow (1.9.0).

Data Preparation

The input of the codes is the features extrected from the pre-trained model, which have been disscussed in our paper.

You can download the extrected features on XMediaNet dataset in this paper with the following lins:

https://pan.baidu.com/s/1Jy4dZhmWblKFZWw6Dcl6pg passwd: 4om4

Usage

Start training and tesing by executiving the following commands. This will train and test the model on XMediaNet datatset.

python train.py