{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T18:38:37Z","timestamp":1792521517558,"version":"4.5.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007219","name":"Shanghai Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["25ZR1402184"],"award-info":[{"award-number":["25ZR1402184"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52501420"],"award-info":[{"award-number":["52501420"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61873160"],"award-info":[{"award-number":["61873160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109541","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T23:37:38Z","timestamp":1787614658000},"page":"109541","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Semantic manifold-aware cross-modal similarity learning"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7979-540X","authenticated-orcid":false,"given":"Liqi","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dezhi","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongqing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109541_bib0001","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2018"},{"key":"10.1016\/j.neunet.2026.109541_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108980","article-title":"Caan: Context-aware attention network for visual question answering","volume":"132","author":"Chen","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109541_bib0003","doi-asserted-by":"crossref","first-page":"8933","DOI":"10.1109\/TMM.2023.3243665","article-title":"Inter-intra modal representation augmentation with DCT-transformer adversarial network for image-text matching","volume":"25","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109541_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12655","article-title":"Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.109541_bib0005","series-title":"International conference on machine learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.109541_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8415","article-title":"Probabilistic embeddings for cross-modal retrieval","author":"Chun","year":"2021"},{"key":"10.1016\/j.neunet.2026.109541_bib0007","unstructured":"Oord, A. v. d., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv: 1807.03748."},{"key":"10.1016\/j.neunet.2026.109541_bib0008","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1218","article-title":"Similarity reasoning and filtration for image-text matching","volume":"Vol. 35","author":"Diao","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2026.109541_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104357","article-title":"Clip-based knowledge projector for image\u2013text matching","volume":"63","author":"Dong","year":"2026","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.neunet.2026.109541_bib0010","unstructured":"Faghri, F., Fleet, D. J., Kiros, J. R., & Fidler, S. (2017). VSE++: Improving visual-semantic embeddings with hard negatives. arXiv: 1707.05612."},{"key":"10.1016\/j.neunet.2026.109541_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111020","article-title":"Collaborative graph neural networks for augmented graphs: A local-to-global perspective","volume":"158","author":"Guo","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109541_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.neunet.2026.109541_bib0013","unstructured":"Honnibal, M. (2017). spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. (To appear)."},{"issue":"6","key":"10.1016\/j.neunet.2026.109541_bib0014","doi-asserted-by":"crossref","first-page":"7833","DOI":"10.1109\/TCSVT.2026.3657433","article-title":"AITQE: An adaptive image-text quality enhancer for scalable mllm pretraining","volume":"36","author":"Huang","year":"2026","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109541_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102084","article-title":"Global-local fusion based on adversarial sample generation for image-text matching","volume":"103","author":"Huang","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109541_bib0016","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"17449","article-title":"Enhance vision-language alignment with noise","volume":"Vol. 39","author":"Huang","year":"2025"},{"key":"10.1016\/j.neunet.2026.109541_bib0017","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"Karpathy","year":"2015"},{"key":"10.1016\/j.neunet.2026.109541_bib0018","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume":"27","author":"Karpathy","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109541_bib0019","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","volume":"30","author":"Kendall","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109541_bib0020","unstructured":"Kiros, R., Salakhutdinov, R., & Zemel, R. S. (2014). Unifying visual-semantic embeddings with multimodal neural language models. arXiv: 1411.2539."},{"issue":"1","key":"10.1016\/j.neunet.2026.109541_bib0021","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109541_bib0022","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"Lee","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2026.109541_bib0023","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1007\/s13042-025-02818-3","article-title":"Neighborhood-interference independent graph mechanisms for image-text matching","volume":"17","author":"Li","year":"2026","journal-title":"International Journal of Machine Learning and Cybernetics"},{"key":"10.1016\/j.neunet.2026.109541_bib0024","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"924","article-title":"Your negative may not be true negative: Boosting image-text matching with false negative elimination","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.109541_bib0025","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"10313","article-title":"Relation-aware graph attention network for visual question answering","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2026.109541_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126943","article-title":"Progressive semantic aggregation and structured cognitive enhancement for image\u2013text matching","volume":"274","author":"Li","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109541_bib0027","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"2389","article-title":"Multi-modal inductive framework for text-video retrieval","author":"Li","year":"2024"},{"issue":"2","key":"10.1016\/j.neunet.2026.109541_bib0028","doi-asserted-by":"crossref","first-page":"1921","DOI":"10.1109\/TCSVT.2024.3480949","article-title":"Selectively hard negative mining for alleviating gradient vanishing in image-text matching","volume":"35","author":"Li","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"7","key":"10.1016\/j.neunet.2026.109541_bib0029","doi-asserted-by":"crossref","first-page":"6590","DOI":"10.1109\/TCSVT.2024.3369656","article-title":"Improving image-text matching with bidirectional consistency of cross-modal alignment","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109541_bib0030","series-title":"European conference on computer vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.109541_bib0031","series-title":"Proceedings of the 27th ACM international conference on multimedia","first-page":"3","article-title":"Focus your attention: A bidirectional focal attention network for image-text matching","author":"Liu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109541_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10921","article-title":"Graph structured network for image-text matching","author":"Liu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109541_bib0033","series-title":"European conference on computer vision","first-page":"852","article-title":"Visual relationship detection with language priors","author":"Lu","year":"2016"},{"key":"10.1016\/j.neunet.2026.109541_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19275","article-title":"Fine-grained image-text matching by cross-modal hard aligning network","author":"Pan","year":"2023"},{"key":"10.1016\/j.neunet.2026.109541_bib0035","series-title":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)","first-page":"1532","article-title":"Glove: Global vectors for word representation","author":"Pennington","year":"2014"},{"key":"10.1016\/j.neunet.2026.109541_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14354","article-title":"Composing object relations and attributes for image-text matching","author":"Pham","year":"2024"},{"key":"10.1016\/j.neunet.2026.109541_bib0037","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2641","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","author":"Plummer","year":"2015"},{"issue":"14","key":"10.1016\/j.neunet.2026.109541_bib0038","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adu4268","article-title":"An autonomous snapper featuring adaptive actuation and embodied intelligence","volume":"11","author":"Polat","year":"2025","journal-title":"Science Advances"},{"key":"10.1016\/j.neunet.2026.109541_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111503","article-title":"Mic: Image-text matching in circles with cross-modal generative knowledge enhancement","volume":"289","author":"Pu","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109541_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110900","article-title":"Gadnet: Improving image\u2013text matching via graph-based aggregation and disentanglement","volume":"157","author":"Pu","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109541_bib0041","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6450","article-title":"Softtriple loss: Deep metric learning without triplet sampling","author":"Qian","year":"2019"},{"key":"10.1016\/j.neunet.2026.109541_bib0042","series-title":"Proceedings of the 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.neunet.2026.109541_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.113009","article-title":"Fean: A fragments embedding and aligning network for image-text matching","volume":"163","author":"Tang","year":"2026","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109541_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5238","article-title":"Winoground: Probing vision and language models for visio-linguistic compositionality","author":"Thrush","year":"2022"},{"issue":"9","key":"10.1016\/j.neunet.2026.109541_bib0045","doi-asserted-by":"crossref","first-page":"8280","DOI":"10.1109\/TPAMI.2025.3580234","article-title":"Toward a holistic evaluation of robustness in clip models","volume":"47","author":"Tu","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109541_bib0046","unstructured":"Vilnis, L., & McCallum, A. (2014). Word representations via gaussian embedding. arXiv: 1412.6623."},{"key":"10.1016\/j.neunet.2026.109541_bib0047","series-title":"Proceedings of the IEEE 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"},{"issue":"9","key":"10.1016\/j.neunet.2026.109541_bib0048","doi-asserted-by":"crossref","first-page":"9502","DOI":"10.1109\/TCSVT.2025.3558996","article-title":"Matryoshka learning with metric transfer for image-text matching","volume":"35","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109541_bib0049","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"1508","article-title":"Cross-modal scene graph matching for relationship-aware image-text retrieval","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109541_bib0050","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"5764","article-title":"Camp: Cross-modal adaptive message passing for text-image retrieval","author":"Wang","year":"2019"},{"key":"10.1016\/j.neunet.2026.109541_bib0051","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13005","article-title":"Universal weighting metric learning for cross-modal matching","author":"Wei","year":"2020"},{"issue":"1","key":"10.1016\/j.neunet.2026.109541_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103154","article-title":"Unifying knowledge iterative dissemination and relational reconstruction network for image\u2013text matching","volume":"60","author":"Xie","year":"2023","journal-title":"Information Processing & Management"},{"issue":"10","key":"10.1016\/j.neunet.2026.109541_bib0053","doi-asserted-by":"crossref","first-page":"9678","DOI":"10.1109\/TCSVT.2024.3392619","article-title":"Reference-aware adaptive network for image-text matching","volume":"34","author":"Xiong","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109541_bib0054","unstructured":"Yao, L., Huang, R., Hou, L., Lu, G., Niu, M., Xu, H., Liang, X., Li, Z., Jiang, X., & Xu, C. (2021). Filip: Fine-grained interactive language-image pre-training. arXiv: 2111.07783."},{"key":"10.1016\/j.neunet.2026.109541_bib0055","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"9050","article-title":"Critic-V: VLM critics help catch VLM errors in multimodal reasoning","author":"Zhang","year":"2025"},{"key":"10.1016\/j.neunet.2026.109541_bib0056","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3262","article-title":"Show your faith: Cross-modal confidence-aware network for image-text matching","volume":"Vol. 36","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109541_bib0057","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15661","article-title":"Negative-aware attention framework for image-text matching","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109541_bib0058","series-title":"Proceedings of the 17th conference of the european chapter of the association for computational linguistics","first-page":"3445","article-title":"Improving cross-modal alignment for text-guided image inpainting","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neunet.2026.109541_bib0059","series-title":"Findings of the association for computational linguistics: EACL 2023","first-page":"2257","article-title":"Style-aware contrastive learning for multi-style image captioning","author":"Zhou","year":"2023"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009998?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009998?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T17:39:37Z","timestamp":1792517977000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026009998"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":59,"alternative-id":["S0893608026009998"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109541","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Semantic manifold-aware cross-modal similarity learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109541","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":"109541"}}