Show simple item record

dc.contributor.authorYu, Litao
dc.contributor.authorGao, Yongsheng
dc.contributor.authorZhou, Jun
dc.date.accessioned2019-05-29T12:59:48Z
dc.date.available2019-05-29T12:59:48Z
dc.date.issued2018
dc.identifier.isbn9781450356657
dc.identifier.doi10.1145/3240508.3240590
dc.identifier.urihttp://hdl.handle.net/10072/384219
dc.description.abstractProduct Quantisation (PQ) has been recognised as an effective encoding technique for scalable multimedia content analysis. In this paper, we propose a novel learning framework that enables an end-to-end encoding strategy from raw images to compact PQ codes. The system aims to learn both PQ encoding functions and codewords for content-based image retrieval. In detail, we first design a trainable encoding layer that is pluggable into neural networks, so the codewords can be trained in back-forward propagation. Then we integrate it into a Deep Convolutional Generative Adversarial Network (DC-GAN). In our proposed encoding framework, the raw images are directly encoded by passing through the convolutional and encoding layers, and the generator aims to use the codewords as constrained inputs to generate full image representations that are visually similar to the original images. By taking the advantages of the generative adversarial model, our proposed system can produce high-quality PQ codewords and encoding functions for scalable multimedia retrieval tasks. Experiments show that the proposed architecture GA-PQ outperforms the state-of-the-art encoding techniques on three public image datasets.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherACM Press
dc.relation.ispartofconferencename2018 ACM Multimedia Conference
dc.relation.ispartofconferencetitle2018 ACM Multimedia Conference on Multimedia Conference - MM '18
dc.relation.ispartofdatefrom2018-10-22
dc.relation.ispartofdateto2018-10-26
dc.relation.ispartoflocationSeoul, Korea
dc.relation.ispartofpagefrom861
dc.relation.ispartofpageto869
dc.subject.fieldofresearchArtificial intelligence
dc.subject.fieldofresearchcode4602
dc.titleGenerative Adversarial Product Quantisation
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.hasfulltextNo Full Text
gro.griffith.authorZhou, Jun
gro.griffith.authorGao, Yongsheng


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record