This is the source code of our TCSVT 2019 paper "Zero-shot Cross-media Embedding Learning with Dual Adversarial Distribution Network", Please cite the following paper if you find our code useful.
Jingze Chi and Yuxin Peng, "Zero-shot Cross-media Embedding Learning with Dual Adversarial Distribution Network", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Feb. 2019. [PDF]
Our code is based on tensorflow 1.4, and tested on Ubuntu 16.04 LTS, python 2.7.
Data Preparation: We use PKU XMediaNet dataset as example, and the data should be put in ./data/. The data files can be download from the link and unzipped to the above path.
Run DADN.py to train models and calculate mAP.
If you are interested in cross-media retrieval, you can check our recently published overview paper on IEEE TCSVT:
Yuxin Peng, Xin Huang, and Yunzhen Zhao, "An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol.28, No.9, pp.2372-2385, 2018. [PDF]
Welcome to our Benchmark Website and Laboratory Homepage for more information about our papers, source codes, and datasets.