{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:27:36Z","timestamp":1793608056767,"version":"4.5.0"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100011332","name":"University of Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011332","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":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109724","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T06:48:16Z","timestamp":1791442096000},"page":"109724","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["JTCSE: Joint tensor-modulus constraints and cross-attention for unsupervised contrastive learning of sentence embeddings"],"prefix":"10.1016","volume":"206","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1468-1750","authenticated-orcid":false,"given":"Tianyu","family":"Zong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5389-139X","authenticated-orcid":false,"given":"Bingkang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhu","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanxiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1530-7486","authenticated-orcid":false,"given":"Zhenghao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3994-1401","authenticated-orcid":false,"given":"Jungang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109724_bib0001","series-title":"Proc. semeval","first-page":"252","article-title":"SemEval-2015 task 2: Semantic textual similarity, English, Spanish and pilot on interpretability","author":"Agirre","year":"2015"},{"key":"10.1016\/j.neunet.2026.109724_bib0002","series-title":"Proc. semeval","first-page":"81","article-title":"SemEval-2014 task 10: Multilingual semantic textual similarity","author":"Agirre","year":"2014"},{"key":"10.1016\/j.neunet.2026.109724_bib0003","series-title":"Proc. semeval","first-page":"497","article-title":"SemEval-2016 task 1: Semantic textual similarity, monolingual and cross-lingual evaluation","author":"Agirre","year":"2016"},{"key":"10.1016\/j.neunet.2026.109724_bib0004","series-title":"Proc. SEM","first-page":"385","article-title":"SemEval-2012 task 6: A pilot on semantic textual similarity","author":"Agirre","year":"2012"},{"key":"10.1016\/j.neunet.2026.109724_bib0005","series-title":"Proc. SEM","first-page":"32","article-title":"*SEM 2013 shared task: Semantic textual similarity","author":"Agirre","year":"2013"},{"key":"10.1016\/j.neunet.2026.109724_bib0006","series-title":"International conference on learning representations","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","author":"Bardes","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0007","series-title":"Proc. semeval","first-page":"1","article-title":"SemEval-2017 task 1: Semantic textual similarity multilingual and crosslingual focused evaluation","author":"Cer","year":"2017"},{"key":"10.1016\/j.neunet.2026.109724_bib0008","series-title":"Proc. ICLR","article-title":"SimCLR: A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.109724_bib0009","series-title":"Proc. semeval","first-page":"1094","article-title":"SemEval-2022 task 8: Multilingual news article similarity","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0010","series-title":"Proc. NAACL","first-page":"4207","article-title":"DiffCSE: Difference-based contrastive learning for sentence embeddings","author":"Chuang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0011","series-title":"Proc. ACL workshop blackboxNLP","first-page":"276","article-title":"What does BERT look at? An analysis of BERT\u2019s attention","author":"Clark","year":"2019"},{"key":"10.1016\/j.neunet.2026.109724_bib0012","series-title":"Proc. ICLR","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020"},{"key":"10.1016\/j.neunet.2026.109724_bib0013","series-title":"Proc. LREC","article-title":"SentEval: An evaluation toolkit for universal sentence representations","author":"Conneau","year":"2018"},{"key":"10.1016\/j.neunet.2026.109724_bib0014","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"12043","article-title":"Grounded entity-landmark adaptive pre-training for vision-and-language navigation","author":"Cui","year":"2023"},{"key":"10.1016\/j.neunet.2026.109724_bib0015","series-title":"Proc. NAACL-HLT","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neunet.2026.109724_bib0016","series-title":"Proc. EMNLP","first-page":"6894","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","author":"Gao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109724_bib0017","series-title":"Proc. AAAI","first-page":"12863","article-title":"Instance smoothed contrastive learning for unsupervised sentence embedding","author":"He","year":"2023"},{"key":"10.1016\/j.neunet.2026.109724_bib0018","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"9726","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.neunet.2026.109724_bib0019","series-title":"Proc. ICML","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.neunet.2026.109724_bib0020","series-title":"Proc. ACL","first-page":"1234","article-title":"PromptBERT: Improving BERT sentence embeddings with prompt-based fine-tuning","author":"Jiang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0021","series-title":"Proc. EMNLP","first-page":"3021","article-title":"Improved universal sentence embeddings with prompt-based contrastive learning and energy-based learning","author":"Jiang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0022","doi-asserted-by":"crossref","DOI":"10.1142\/S1752890924500235","article-title":"Machine learning coffee price predictions","author":"Jin","year":"2024","journal-title":"Journal of Uncertain Systems"},{"key":"10.1016\/j.neunet.2026.109724_bib0023","doi-asserted-by":"crossref","DOI":"10.1142\/S2424786325500033","article-title":"China commodity price index (CCPI) forecasting via the neural network","author":"Jin","year":"2025","journal-title":"International Journal of Financial Engineering"},{"key":"10.1016\/j.neunet.2026.109724_bib0024","doi-asserted-by":"crossref","DOI":"10.1142\/S1752890925500084","article-title":"High-frequency CSI300 spot and futures price predictions via the neural network","author":"Jin","year":"2025","journal-title":"Journal of Uncertain Systems"},{"key":"10.1016\/j.neunet.2026.109724_bib0025","doi-asserted-by":"crossref","DOI":"10.1007\/s11135-025-02080-3","article-title":"Predictions of residential property price indices for China via machine learning models","author":"Jin","year":"2025","journal-title":"Quality & Quantity"},{"key":"10.1016\/j.neunet.2026.109724_bib0026","doi-asserted-by":"crossref","DOI":"10.1142\/S308284142550008X","article-title":"A study of contemporaneous residential real estate price causation across major Jiangsu province cities: Methodology using vector error-correction models and directed acyclic graphs","author":"Jin","year":"2025","journal-title":"Economics Open"},{"key":"10.1016\/j.neunet.2026.109724_bib0027","unstructured":"Li, L. H., Yatskar, M., Yin, D., Hsieh, C.-J., & Chang, K.-W. (2019). VisualBERT: A simple and performant baseline for vision and language. https:\/\/arxiv.org\/abs\/1908.03557."},{"key":"10.1016\/j.neunet.2026.109724_bib0028","series-title":"Proc. IEEE ICME","first-page":"1","article-title":"CAT: Cross attention in vision transformer","author":"Lin","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0029","series-title":"Proc. ACL","first-page":"13785","article-title":"RankCSE: Unsupervised sentence representations learning via learning to rank","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109724_bib0030","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. https:\/\/arxiv.org\/abs\/1907.11692."},{"key":"10.1016\/j.neunet.2026.109724_bib0031","series-title":"Advances in neural information processing systems","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"(","author":"Lu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109724_bib0032","series-title":"Proc. LREC","first-page":"216","article-title":"A SICK cure for the evaluation of compositional distributional semantic models","author":"Marelli","year":"2014"},{"key":"10.1016\/j.neunet.2026.109724_bib0033","series-title":"Proc. EACL","first-page":"2006","article-title":"MTEB: Massive text embedding benchmark","author":"Muennighoff","year":"2023"},{"key":"10.1016\/j.neunet.2026.109724_bib0034","series-title":"Proc. ICML","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2026.109724_bib0035","doi-asserted-by":"crossref","unstructured":"Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using siamese BERT-networks. In Proc. EMNLP-IJCNLP (pp. 3982\u20133992). Hong Kong, China. 10.18653\/v1\/D19-1410.","DOI":"10.18653\/v1\/D19-1410"},{"issue":"1","key":"10.1016\/j.neunet.2026.109724_bib0036","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1109\/MCI.2012.2228600","article-title":"Ensemble methods: Foundations and algorithms [book review]","volume":"8","author":"Schwenker","year":"2013","journal-title":"IEEE Computational Intelligence Magazine"},{"key":"10.1016\/j.neunet.2026.109724_bib0037","series-title":"Proc. EMNLP-IJCNLP","first-page":"5099","article-title":"LXMERT: Learning cross-modality encoder representations from transformers","author":"Tan","year":"2019"},{"key":"10.1016\/j.neunet.2026.109724_bib0038","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2026.109724_bib0039","series-title":"Advances in neural information processing systems (NeurIPS)","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2026.109724_bib0040","series-title":"Proc. ICIC","first-page":"419","article-title":"SNCSE: Contrastive learning for unsupervised sentence embedding with soft negative samples","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109724_bib0041","series-title":"Proc. ICML","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109724_bib0042","series-title":"Proc. EMNLP-IJCNLP","first-page":"6381","article-title":"EDA: Easy data augmentation techniques for boosting performance on text classification tasks","author":"Wei","year":"2019"},{"key":"10.1016\/j.neunet.2026.109724_bib0043","series-title":"Proc. EMNLP","first-page":"12052","article-title":"PCL: Peer-contrastive learning with diverse augmentations for unsupervised sentence embeddings","author":"Wu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0044","series-title":"Findings of the association for computational linguistics: EMNLP","first-page":"3060","article-title":"InfoCSE: Information-aggregated contrastive learning of sentence embeddings","author":"Wu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0045","series-title":"Proc. COLING","first-page":"3898","article-title":"ESimCSE: Enhanced sample building method for contrastive learning of unsupervised sentence embedding","author":"Wu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0046","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.eswa.2017.01.054","article-title":"Composite quantile regression neural network with applications","volume":"76","author":"Xu","year":"2017","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"10.1016\/j.neunet.2026.109724_bib0047","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1093\/erae\/jby036","article-title":"Contemporaneous and granger causality among US corn cash and futures prices","volume":"46","author":"Xu","year":"2018","journal-title":"European Review of Agricultural Economics"},{"issue":"4","key":"10.1016\/j.neunet.2026.109724_bib0048","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1002\/ajae.12041","article-title":"Corn cash price forecasting","volume":"102","author":"Xu","year":"2020","journal-title":"American Journal of Agricultural Economics"},{"key":"10.1016\/j.neunet.2026.109724_bib0049","series-title":"Proc. ACL","first-page":"14507","article-title":"ManagerTower: Aggregating the insights of uni-modal experts for vision-language representation learning","author":"Xu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109724_bib0050","series-title":"Proc. AAAI","first-page":"10637","article-title":"BridgeTower: Building bridges between encoders in vision-language representation learning","author":"Xu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109724_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2021.106120","article-title":"Corn cash price forecasting with neural networks","volume":"184","author":"Xu","year":"2021","journal-title":"Computers and Electronics in Agriculture"},{"key":"10.1016\/j.neunet.2026.109724_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.mlwa.2021.100035","article-title":"Individual time series and composite forecasting of the Chinese stock index","volume":"5","author":"Xu","year":"2021","journal-title":"Machine Learning with Applications"},{"key":"10.1016\/j.neunet.2026.109724_bib0053","doi-asserted-by":"crossref","DOI":"10.1016\/j.dajour.2023.100229","article-title":"An integrated vector error correction and directed acyclic graph method for investigating contemporaneous causalities","volume":"7","author":"Xu","year":"2023","journal-title":"Decision Analytics Journal"},{"key":"10.1016\/j.neunet.2026.109724_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106870","article-title":"Price forecasts of ten steel products using Gaussian process regressions","volume":"126","author":"Xu","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109724_bib0055","series-title":"Proc. ACL\/IJCNLP","first-page":"5065","article-title":"ConSERT: A contrastive framework for self-supervised sentence representation transfer","author":"Yan","year":"2021"},{"key":"10.1016\/j.neunet.2026.109724_bib0056","series-title":"Proc. ICML","article-title":"Unveiling and harnessing hidden attention sinks: Enhancing large language models without training through attention calibration","author":"Yu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109724_bib0057","series-title":"International conference on machine learning","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021"},{"key":"10.1016\/j.neunet.2026.109724_bib0058","series-title":"Proc. EMNLP","first-page":"1601","article-title":"An unsupervised sentence embedding method by mutual information maximization","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109724_bib0059","series-title":"Proc. ACL","first-page":"4892","article-title":"A contrastive framework for learning sentence representations from pairwise and triple-wise perspective in angular space","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0060","series-title":"Proc. EMNLP","first-page":"3021","article-title":"When does contrastive learning preserve semantic similarity? A case study on sentence embeddings","author":"Zhuo","year":"2022"},{"key":"10.1016\/j.neunet.2026.109724_bib0061","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"26192","article-title":"TNCSE: Tensor norm constraints for unsupervised contrastive learning of sentence embeddings","author":"Zong","year":"2025"},{"key":"10.1016\/j.neunet.2026.109724_bib0062","series-title":"Proc. AAAI","first-page":"14074","article-title":"An ensemble distillation framework for sentence embeddings with multilingual round-trip translation","volume":"vol. 37","author":"Zong","year":"2023"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011792?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011792?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:42:50Z","timestamp":1793605370000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011792"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":62,"alternative-id":["S0893608026011792"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109724","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"JTCSE: Joint tensor-modulus constraints and cross-attention for unsupervised contrastive learning of sentence embeddings","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109724","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":"109724"}}