{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T13:52:16Z","timestamp":1791208336714,"version":"4.1.0"},"reference-count":24,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Array"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.array.2026.100963","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:28:18Z","timestamp":1780586898000},"page":"100963","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multimodal fusion with supervised sparse autoencoding for high-performance seal retrieval in digital heritage"],"prefix":"10.1016","volume":"30","author":[{"given":"Qiang","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5786-7594","authenticated-orcid":false,"given":"Hongyin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.array.2026.100963_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.119369","article-title":"Pre-training language model incorporating domain-specific heterogeneous knowledge into a unified representation","volume":"215","author":"Zhu","year":"2023","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.array.2026.100963_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2022.108445","article-title":"SwitchNet: A modular neural network for adaptive relation extraction","volume":"104","author":"Zhu","year":"2022","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.array.2026.100963_b3","series-title":"Proceedings of recSys","first-page":"1099","article-title":"The future is sparse: Embedding compression for scalable retrieval in recommender systems","author":"Kasalick\u00fd","year":"2025"},{"issue":"2","key":"10.1016\/j.array.2026.100963_b4","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int J Comput Vis"},{"issue":"10","key":"10.1016\/j.array.2026.100963_b5","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1109\/TPAMI.2005.188","article-title":"A performance evaluation of local descriptors","volume":"27","author":"Mikolajczyk","year":"2005","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.array.2026.100963_b6","series-title":"Image matching using SIFT, SURF, BRIEF and ORB: performance comparison for distorted images","author":"Karami","year":"2017"},{"key":"10.1016\/j.array.2026.100963_b7","series-title":"Proceedings of CVPR","first-page":"3304","article-title":"Aggregating local descriptors into a compact image representation","author":"J\u00e9gou","year":"2010"},{"key":"10.1016\/j.array.2026.100963_b8","series-title":"Proceedings of CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.array.2026.100963_b9","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans Mach Learn Res J"},{"key":"10.1016\/j.array.2026.100963_b10","article-title":"Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection","author":"Shen","year":"2025","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"12","key":"10.1016\/j.array.2026.100963_b11","doi-asserted-by":"crossref","first-page":"24330","DOI":"10.1109\/TITS.2022.3203715","article-title":"An anchor-free lightweight deep convolutional network for vehicle detection in aerial images","volume":"23","author":"Shen","year":"2022","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"10.1016\/j.array.2026.100963_b12","first-page":"1","article-title":"An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features","volume":"73","author":"Shen","year":"2024","journal-title":"IEEE Trans Instrum Meas"},{"key":"10.1016\/j.array.2026.100963_b13","first-page":"1","article-title":"Finger vein recognition algorithm based on lightweight deep convolutional neural network","volume":"71","author":"Shen","year":"2021","journal-title":"IEEE Trans Instrum Meas"},{"key":"10.1016\/j.array.2026.100963_b14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.array.2026.100963_b15","series-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"10.1016\/j.array.2026.100963_b16","article-title":"Unsupervised dense information retrieval with contrastive learning","volume":"2022","author":"Izacard","year":"2022","journal-title":"Trans Mach Learn Res"},{"key":"10.1016\/j.array.2026.100963_b17","series-title":"MultiContrievers: Analysis of dense retrieval representations","author":"Goldfarb-Tarrant","year":"2024"},{"key":"10.1016\/j.array.2026.100963_b18","series-title":"MetaAID: A flexible framework for developing metaverse applications via AI technology and human editing","author":"Zhu","year":"2022"},{"key":"10.1016\/j.array.2026.100963_b19","volume":"vol. 4","author":"Bishop","year":"2006"},{"key":"10.1016\/j.array.2026.100963_b20","article-title":"Autoencoder-based joint image compression and encryption","volume":"80","author":"Wang","year":"2024","journal-title":"J Inf Secur Appl"},{"key":"10.1016\/j.array.2026.100963_b21","series-title":"K-sparse autoencoders","author":"Makhzani","year":"2013"},{"key":"10.1016\/j.array.2026.100963_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128645","article-title":"A comprehensive survey on contrastive learning","volume":"610","author":"Hu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.array.2026.100963_b23","series-title":"Improving embedding with contrastive fine-tuning on small datasets with expert-augmented scores","author":"Lu","year":"2024"},{"key":"10.1016\/j.array.2026.100963_b24","series-title":"Proceedings of ECCV 2024 workshops","first-page":"399","article-title":"Embedding geometries of contrastive language-image pre-training","volume":"vol. 15639","author":"Chou","year":"2024"}],"container-title":["Array"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626002869?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626002869?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T12:58:12Z","timestamp":1791205092000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2590005626002869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":24,"alternative-id":["S2590005626002869"],"URL":"https:\/\/doi.org\/10.1016\/j.array.2026.100963","relation":{},"ISSN":["2590-0056"],"issn-type":[{"value":"2590-0056","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multimodal fusion with supervised sparse autoencoding for high-performance seal retrieval in digital heritage","name":"articletitle","label":"Article Title"},{"value":"Array","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.array.2026.100963","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"100963"}}