cross-modal-hasing-playground

This repository is no longer maintained.

Implementations of state-of-the-art cross-model hashing algorithms(back in 2019). The flickr dataset is used as an example to demonstrate how data is preprocessed. For further details, please check out papers list below and follow standard data processing pipeline, for image and text. The flickr.py can also be used a reference when cleaning the flickr dataset. Some algorithms below are Python wrapper based on the original matlab codes. For others, models are implemented and trained to our best knowledge.

Papers that have been implemented are as follows：

• IMH

  paper: https://dl.acm.org/citation.cfm?id=2465274

• LSSH

  paper: http://ise.thss.tsinghua.edu.cn/MIG/2014_Latent%20Semantic%20Sparse%20Hashing%20for%20Cross-Modal.pdf

• CMFH

  paper: http://ise.thss.tsinghua.edu.cn/MIG/CVPR2014%20Collective%20Matrix%20Factorization%20Hashing%20for%20Multimodal%20Data.pdf

• Corr-AE

  paper: https://people.cs.clemson.edu/~jzwang/1501863/mm2014/p7-feng.pdf

• DBRC

  paper: https://arxiv.org/pdf/1708.05127.pdf