Deep Attribute-aware Hashing for Cross Retrieval (2019–2022)

As the rapid proliferation of big multimedia data from heterogenous data sources, there is urgent need to enable retrieval experience across different media types and domains. This project aims to develop a deep attribute-aware hashing framework that embeds heterogeneous features into a shared Hamming space to achieve effective and efficient cross retrieval. This framework learns meaningful image attributes to positively bridge the modality gap and the domain gap when hash functions are learned. The success of this project will significantly advance the research of multimedia retrieval, and benefit a series of related research problems whenever heterogeneous multimedia data are involved in their applications.
Grant type:
ARC Discovery Projects
  • Associate Professor
    School of Information Technology and Electrical Engineering
    Faculty of Engineering, Architecture and Information Technology
Funded by:
Australian Research Council