{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:57:39Z","timestamp":1780934259898,"version":"3.54.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002855","name":"MOST","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.113799","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T15:11:51Z","timestamp":1779203511000},"page":"113799","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["ScalarNet: Learning retrieval-optimized scalar embeddings for efficient image storage and search"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1884-8279","authenticated-orcid":false,"given":"Umali","family":"Leonard","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mtisunge Tupochere","family":"Malemia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113799_b1","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113799_b2","series-title":"Proceedings of the 10th ACM Conference on Recommender Systems","first-page":"191","article-title":"Deep neural networks for YouTube recommendations","author":"Covington","year":"2016"},{"issue":"7956","key":"10.1016\/j.patcog.2026.113799_b3","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.patcog.2026.113799_b4","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2026.113799_b5","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2026.113799_b6","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113799_b7","series-title":"Proceedings of the 2021 International Conference on Management of Data","first-page":"2614","article-title":"Milvus: A purpose-built vector data management system","author":"Wang","year":"2021"},{"issue":"03","key":"10.1016\/j.patcog.2026.113799_b8","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2021","journal-title":"IEEE Trans. Big Data"},{"issue":"4","key":"10.1016\/j.patcog.2026.113799_b9","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2018.2889473","article-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","volume":"42","author":"Malkov","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113799_b10","series-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","article-title":"DiskANN: fast accurate billion-point nearest neighbor search on a single node","author":"Subramanya","year":"2019"},{"issue":"9","key":"10.1016\/j.patcog.2026.113799_b11","doi-asserted-by":"crossref","DOI":"10.1145\/3555802","article-title":"Edge computing with artificial intelligence: A machine learning perspective","volume":"55","author":"Hua","year":"2023","journal-title":"ACM Comput. Surv."},{"issue":"1","key":"10.1016\/j.patcog.2026.113799_b12","doi-asserted-by":"crossref","first-page":"40008","DOI":"10.1038\/s41598-025-23582-y","article-title":"Deep learning based medical image compression using cross attention learning and wavelet transform","volume":"15","author":"Dai","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.patcog.2026.113799_b13","series-title":"2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"1735","article-title":"Dimensionality reduction by learning an invariant mapping","volume":"Vol. 2","author":"Hadsell","year":"2006"},{"key":"10.1016\/j.patcog.2026.113799_b14","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"815","article-title":"FaceNet: A unified embedding for face recognition and clustering","author":"Schroff","year":"2015"},{"key":"10.1016\/j.patcog.2026.113799_b15","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5022","article-title":"Multi-similarity loss with general pair weighting for deep metric learning","author":"Wang","year":"2019"},{"key":"10.1016\/j.patcog.2026.113799_b16","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4685","article-title":"ArcFace: Additive angular margin loss for deep face recognition","author":"Deng","year":"2019"},{"key":"10.1016\/j.patcog.2026.113799_b17","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.patcog.2026.113799_b18","series-title":"Wiley StatsRef: Statistics Reference Online","article-title":"Principal component analysis","author":"Jolliffe","year":"2014"},{"issue":"1","key":"10.1016\/j.patcog.2026.113799_b19","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","article-title":"Product quantization for nearest neighbor search","volume":"33","author":"J\u00e9gou","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113799_b20","series-title":"Proceedings of the 37th International Conference on Machine Learning","article-title":"Accelerating large-scale inference with anisotropic vector quantization","author":"Guo","year":"2020"},{"key":"10.1016\/j.patcog.2026.113799_b21","series-title":"Proceedings of the 1970 ACM SIGFIDET (Now SIGMOD) Workshop on Data Description, Access and Control","first-page":"107","article-title":"Organization and maintenance of large ordered indices","author":"Bayer","year":"1970"},{"key":"10.1016\/j.patcog.2026.113799_b22","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Supervised contrastive learning","author":"Khosla","year":"2020"},{"key":"10.1016\/j.patcog.2026.113799_b23","unstructured":"Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, A.Y. Ng, Reading digits in natural images with unsupervised feature learning, in: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Vol. 2011, 2011, p. 5."},{"issue":"41","key":"10.1016\/j.patcog.2026.113799_b24","article-title":"MedMNIST v2: A large-scale lightweight benchmark for 2D and 3D biomedical image classification","volume":"10","author":"Yang","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.patcog.2026.113799_b25","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5265","article-title":"CosFace: Large margin cosine loss for deep face recognition","author":"Wang","year":"2018"},{"key":"10.1016\/j.patcog.2026.113799_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109671","article-title":"Orthonormal product quantization network for scalable face image retrieval","volume":"141","author":"Zhang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113799_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110634","article-title":"Linear centroid encoder for supervised principal component analysis","volume":"155","author":"Ghosh","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113799_b28","doi-asserted-by":"crossref","unstructured":"K. Roth, O. Vinyals, Z. Akata, Non-isotropy regularization for proxy-based deep metric learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7420\u20137430.","DOI":"10.1109\/CVPR52688.2022.00727"},{"key":"10.1016\/j.patcog.2026.113799_b29","doi-asserted-by":"crossref","first-page":"10342","DOI":"10.1109\/TMM.2024.3407664","article-title":"Estimating the semantics via sector embedding for image-text retrieval","volume":"26","author":"Wang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113799_b30","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2830","article-title":"Multilateral semantic relations modeling for image text retrieval","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113799_b31","first-page":"1","article-title":"Distribution-to-points matching for image text retrieval","author":"Wang","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113799_b32","doi-asserted-by":"crossref","first-page":"2226","DOI":"10.1109\/TIP.2024.3374111","article-title":"Semantics disentangling for cross-modal retrieval","volume":"33","author":"Wang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"10.1016\/j.patcog.2026.113799_b33","doi-asserted-by":"crossref","DOI":"10.1145\/3532624","article-title":"A survey on deep hashing methods","volume":"17","author":"Luo","year":"2023","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.1016\/j.patcog.2026.113799_b34","series-title":"Proceedings of the 22nd International Conference on Neural Information Processing Systems","first-page":"1753","article-title":"Spectral hashing","author":"Weiss","year":"2008"},{"key":"10.1016\/j.patcog.2026.113799_b35","article-title":"LeanVec: Searching vectors faster by making them fit","author":"Tepper","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"issue":"3","key":"10.1016\/j.patcog.2026.113799_b36","doi-asserted-by":"crossref","DOI":"10.1145\/3654970","article-title":"RaBitQ: Quantizing high-dimensional vectors with a theoretical error bound for approximate nearest neighbor search","volume":"2","author":"Gao","year":"2024","journal-title":"Proc. ACM Manag. Data"},{"key":"10.1016\/j.patcog.2026.113799_b37","series-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","article-title":"Matryoshka representation learning","author":"Kusupati","year":"2022"},{"issue":"3","key":"10.1016\/j.patcog.2026.113799_b38","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1007\/s10044-023-01181-9","article-title":"Deep neural networks for rank-consistent ordinal regression based on conditional probabilities","volume":"26","author":"Shi","year":"2023","journal-title":"Pattern Anal. Appl."},{"issue":"29","key":"10.1016\/j.patcog.2026.113799_b39","doi-asserted-by":"crossref","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: Uniform manifold approximation and projection","volume":"3","author":"McInnes","year":"2018","journal-title":"J. Open Source Softw."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007648?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007648?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:57:58Z","timestamp":1780930678000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326007648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":39,"alternative-id":["S0031320326007648"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113799","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ScalarNet: Learning retrieval-optimized scalar embeddings for efficient image storage and search","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113799","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113799"}}