This is the source code of our TMM 2019 paper "Multi-pathway Generative Adversarial Hashing for Unsupervised Cross-modal Retrieval", Please cite the following paper if you use our code.
Jian Zhang and Yuxin Peng, “Multi-pathway Generative Adversarial Hashing for Unsupervised Cross-modal Retrieval”, IEEE Transactions on Multimedia (TMM), DOI:10.1109/TMM.2019.2922128, 2019. [PDF]
For PKU-Xmeida dataset:
- Generate KNN graph by the codes under KNN directory: /xmedia/python/knn_5M.py
- Train the model by using the code under unsuper-pretrain-xm-5M: python train_argv.py hashdim gpuid
hashdim represents the length of hash codes, gpuid represts the index of gpu
You can download the data in /media from download Link pw:0q8o
For 2-media datasets codes, please refer to our AAAI paper.
Welcome to our Laboratory Homepage for more information about our papers, source codes, and datasets.