{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T14:55:57Z","timestamp":1772636157728,"version":"3.50.1"},"reference-count":50,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korea Internet Security Agency (KISA) Grant funded by Korea Government"},{"name":"Research Development for Right to be forgotten in Video Contents provided by Limited Online Service Providers","award":["RS-2022-IS000004"],"award-info":[{"award-number":["RS-2022-IS000004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\n                    Deep hashing has emerged as an efficient and robust solution for image retrieval through representation learning. However, convolutional neural network (CNN)-based hashing methods are constrained by their reliance on grid structures, limiting their capacity to model complex or unstructured data relationships. This article proposes a novel deep hashing model, Hashing by Autoencoder with graph convolutional networks (HAGCN), that integrates transfer learning\u2013based visual embeddings, obtained\n                    <jats:italic>via<\/jats:italic>\n                    an autoencoder, with graph convolutional networks (GCNs). The model dynamically constructs local subgraphs from the output of a transfer model, enabling the learning of both global and local structural relationships through the graph Laplacian. A GCN layer is employed to effectively capture local topologies in unstructured data, enhancing both representation quality and learning efficiency through parameter sharing and transfer learning. Experiments conducted on the evaluation datasets demonstrate that the proposed method outperforms existing CNN-based and GCN-based deep hashing approaches. Furthermore, the analysis of various GCN filters under the proposed framework offers valuable insights into filter selection for deep hashing. In terms of average performance improvement compared to the comparison models, HAGCN shows an increase of about 7.4% compared to the minimum performance and about 2.7% compared to the maximum performance. Ultimately, GCN filters contribute to structural preservation and improved expressiveness, while the combination of dynamic graph construction and transfer learning facilitates the generation of compact, robust hash codes from high-dimensional image data.\n                  <\/jats:p>","DOI":"10.7717\/peerj-cs.3644","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:27:58Z","timestamp":1772612878000},"page":"e3644","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing deep hashing with graph filters and autoencoder-based embeddings"],"prefix":"10.7717","volume":"12","author":[{"given":"Sooin","family":"Kim","sequence":"first","affiliation":[{"name":"Department of AI-based Convergence, Dankook University, Yongin-si, Gyeonggi-do, Republic of South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungtae","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Arkansas State University, Jonesboro, AR, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seonghyun","family":"Min","sequence":"additional","affiliation":[{"name":"Research and Development Center, AIDEEP Company Ltd., Gwacheon-si, Gyeonggi-do, Republic of South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wongyum","family":"Kim","sequence":"additional","affiliation":[{"name":"Research and Development Center, AIDEEP Company Ltd., Gwacheon-si, Gyeonggi-do, Republic of South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Doosung","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Software Science, Dankook University, Yongin-si, Gyeonggi-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Arkansas State University, Jonesboro, AR, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"issue":"4","key":"10.7717\/peerj-cs.3644\/ref-1","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1109\/tbdata.2023.3338951","article-title":"Proxy-based graph convolutional hashing for cross-modal retrieval","volume":"10","author":"Bai","year":"2024","journal-title":"IEEE Transactions on Big Data"},{"key":"10.7717\/peerj-cs.3644\/ref-2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-45468-4","volume-title":"Deep learning\u2014foundations and concepts","author":"Bishop","year":"2024"},{"key":"10.7717\/peerj-cs.3644\/ref-3","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna","year":"2014"},{"key":"10.7717\/peerj-cs.3644\/ref-4","first-page":"5608","article-title":"HashNet: deep learning to hash by continuation","author":"Cao","year":"2017"},{"key":"10.7717\/peerj-cs.3644\/ref-5","first-page":"132","article-title":"Deep clustering for unsupervised learning of visual features","author":"Caron","year":"2018"},{"key":"10.7717\/peerj-cs.3644\/ref-6","first-page":"9630","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.7717\/peerj-cs.3644\/ref-7","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531405","article-title":"TransHash: transformer-based hamming hashing for efficient image retrieval","author":"Chen","year":"2021"},{"issue":"2","key":"10.7717\/peerj-cs.3644\/ref-8","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s00466-023-02291-1","article-title":"A continuous convolutional trainable filter for modelling unstructured data","volume":"72","author":"Coscia","year":"2023","journal-title":"Computational Mechanics"},{"key":"10.7717\/peerj-cs.3644\/ref-9","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems,","author":"Defferrard","year":"2016"},{"key":"10.7717\/peerj-cs.3644\/ref-10","doi-asserted-by":"crossref","DOI":"10.1109\/ICME52920.2022.9859900","article-title":"Vision transformer hashing for image retrieval","author":"Dubey","year":"2022"},{"key":"10.7717\/peerj-cs.3644\/ref-11","article-title":"Deep polarized network for supervised learning of accurate binary hashing codes","author":"Fan","year":"2021"},{"issue":"5","key":"10.7717\/peerj-cs.3644\/ref-12","doi-asserted-by":"publisher","first-page":"107865","DOI":"10.1016\/j.compbiomed.2023.107865","article-title":"Graph-guided deep hashing networks for similar patient retrieval","volume":"169","author":"Gu","year":"2024","journal-title":"Computers in Biology and Medicine"},{"issue":"11","key":"10.7717\/peerj-cs.3644\/ref-13","doi-asserted-by":"publisher","first-page":"7050","DOI":"10.1109\/tcsvt.2023.3268091","article-title":"Deep learning-based image retrieval with unsupervised double bit hashing","volume":"33","author":"Guo","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.7717\/peerj-cs.3644\/ref-14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1709.05584","article-title":"Representation learning on graphs: methods and applications","author":"Hamilton","year":"2017"},{"issue":"1","key":"10.7717\/peerj-cs.3644\/ref-15","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/tpami.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.3644\/ref-16","first-page":"1","article-title":"Transformer-based deep hashing method for multi-scale feature fusion","author":"He","year":"2023"},{"key":"10.7717\/peerj-cs.3644\/ref-17","first-page":"7264","article-title":"Convolutional neural networks on graphs with Chebyshev approximation, revisited","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems,","author":"He","year":"2022"},{"key":"10.7717\/peerj-cs.3644\/ref-18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.08942","article-title":"A survey on locality sensitive hashing algorithms and their applications","author":"Jafari","year":"2021"},{"issue":"1","key":"10.7717\/peerj-cs.3644\/ref-19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3633518","article-title":"A survey on graph representation learning methods","volume":"15","author":"Khoshraftar","year":"2024","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"10.7717\/peerj-cs.3644\/ref-20","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.7717\/peerj-cs.3644\/ref-21","author":"Leskovec","year":"2017","journal-title":"GraphSAGE: inductive representation learning on large graphs"},{"issue":"1","key":"10.7717\/peerj-cs.3644\/ref-22","doi-asserted-by":"publisher","first-page":"8490364","DOI":"10.1155\/2019\/8490364","article-title":"Triplet deep hashing with joint supervised loss based on deep neural networks","volume":"2019","author":"Li","year":"2019","journal-title":"Computational Intelligence and Neuroscience"},{"issue":"2","key":"10.7717\/peerj-cs.3644\/ref-23","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.32604\/csse.2023.034757","article-title":"ViT2CMH: vision transformer cross-modal hashing for fine-grained vision-text retrieval","volume":"46","author":"Li","year":"2023","journal-title":"Computer Systems Science and Engineering"},{"key":"10.7717\/peerj-cs.3644\/ref-24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096443","article-title":"Semantic centralized contrastive learning for unsupervised hashing","author":"Liang","year":"2023"},{"key":"10.7717\/peerj-cs.3644\/ref-25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1901.01484","article-title":"LanczosNet: multi-scale deep graph convolutional networks","author":"Liao","year":"2019"},{"issue":"7","key":"10.7717\/peerj-cs.3644\/ref-26","doi-asserted-by":"publisher","first-page":"7488","DOI":"10.1609\/aaai.v36i7.20713","article-title":"Deep unsupervised hashing with latent semantic components","volume":"36","author":"Lin","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3644\/ref-27","first-page":"2064","article-title":"Deep supervised hashing for fast image retrieval","author":"Liu","year":"2016"},{"issue":"6","key":"10.7717\/peerj-cs.3644\/ref-28","doi-asserted-by":"publisher","first-page":"5977","DOI":"10.1109\/tkde.2022.3158317","article-title":"HS-GCN: hamming spatial graph convolutional networks for recommendation","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"1","key":"10.7717\/peerj-cs.3644\/ref-29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3532624","article-title":"A survey on deep hashing methods","volume":"17","author":"Luo","year":"2023","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"10.7717\/peerj-cs.3644\/ref-30","doi-asserted-by":"publisher","first-page":"2810","DOI":"10.3390\/electronics11182810","article-title":"Transformer-based distillation hash learning for image retrieval","volume":"11","author":"Lv","year":"2022","journal-title":"Electronics"},{"issue":"4","key":"10.7717\/peerj-cs.3644\/ref-31","doi-asserted-by":"publisher","first-page":"30094","DOI":"10.1109\/access.2023.3259104","article-title":"RelaHash: deep hashing with relative position","volume":"11","author":"Minh","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3644\/ref-32","first-page":"2818","article-title":"Auto-encoding twin-bottleneck hashing","author":"Shen","year":"2020"},{"issue":"3","key":"10.7717\/peerj-cs.3644\/ref-33","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/msp.2012.2235192","article-title":"The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains","volume":"30","author":"Shuman","year":"2013","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.7717\/peerj-cs.3644\/ref-34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01424-7_27","article-title":"A survey on deep transfer learning","author":"Tan","year":"2018"},{"issue":"Nov","key":"10.7717\/peerj-cs.3644\/ref-35","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"10.7717\/peerj-cs.3644\/ref-36","first-page":"5385","article-title":"Deep hashing network for unsupervised domain adaptation","author":"Venkateswara","year":"2017"},{"key":"10.7717\/peerj-cs.3644\/ref-37","doi-asserted-by":"crossref","DOI":"10.1109\/MMSP53017.2021.9733464","article-title":"Deep image hashing based on twin-bottleneck hashing with variational autoencoders","author":"Verwilst","year":"2021"},{"key":"10.7717\/peerj-cs.3644\/ref-38","first-page":"2022","article-title":"Heterogeneous graph attention network","author":"Wang","year":"2019"},{"key":"10.7717\/peerj-cs.3644\/ref-39","article-title":"Contrastive quantization with code memory for unsupervised image retrieval","author":"Wang","year":"2021"},{"key":"10.7717\/peerj-cs.3644\/ref-40","article-title":"Spectral hashing","volume-title":"Advances in Neural Information Processing Systems","volume":"21","author":"Weiss","year":"2008"},{"issue":"1","key":"10.7717\/peerj-cs.3644\/ref-41","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/tnnls.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.7717\/peerj-cs.3644\/ref-42","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.7717\/peerj-cs.3644\/ref-43","first-page":"3238","article-title":"Semi-supervised deep hashing with a bipartite graph","author":"Yan","year":"2017"},{"key":"10.7717\/peerj-cs.3644\/ref-44","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2024.3489412","article-title":"Data-centric graph learning: a survey","author":"Yang","year":"2023"},{"issue":"14","key":"10.7717\/peerj-cs.3644\/ref-45","doi-asserted-by":"publisher","first-page":"2221","DOI":"10.3390\/math12142221","article-title":"DSCEH: dual-stream correlation-enhanced deep hashing for image retrieval","volume":"12","author":"Yang","year":"2024","journal-title":"Mathematics"},{"key":"10.7717\/peerj-cs.3644\/ref-46","first-page":"11863","article-title":"SimAM: a simple, parameter-free attention module for convolutional neural networks","author":"Yang","year":"2021"},{"key":"10.7717\/peerj-cs.3644\/ref-47","article-title":"GraphSAINT: graph sampling based inductive learning method","author":"Zeng","year":"2020"},{"issue":"7","key":"10.7717\/peerj-cs.3644\/ref-48","doi-asserted-by":"publisher","first-page":"109462","DOI":"10.1016\/j.patcog.2023.109462","article-title":"Deep collaborative graph hashing for discriminative image retrieval","volume":"139","author":"Zhang","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.7717\/peerj-cs.3644\/ref-49","doi-asserted-by":"crossref","DOI":"10.23919\/MVA51890.2021.9511401","article-title":"Semantic hierarchy preserving deep hashing for large-scale image retrieval","author":"Zhang","year":"2021"},{"issue":"4","key":"10.7717\/peerj-cs.3644\/ref-50","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1109\/tcyb.2018.2883970","article-title":"Graph convolutional network hashing","volume":"50","author":"Zhou","year":"2020","journal-title":"IEEE Transactions on Cybernetics"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3644.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3644.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3644.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3644.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:28:04Z","timestamp":1772612884000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3644"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":50,"alternative-id":["10.7717\/peerj-cs.3644"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3644","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"article-number":"e3644"}}