{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:57:34Z","timestamp":1781150254155,"version":"3.54.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72471197"],"award-info":[{"award-number":["72471197"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Provincial Science and Technology Support Program","doi-asserted-by":"publisher","award":["MZGC20240146"],"award-info":[{"award-number":["MZGC20240146"]}],"id":[{"id":"10.13039\/100012542","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":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108982","type":"journal-article","created":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T16:30:43Z","timestamp":1776011443000},"page":"108982","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["V-Sparse: From temporal-spatial visual semantic compression to coarse-to-fine interaction for text-video retrieval"],"prefix":"10.1016","volume":"201","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1249-691X","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5811-649X","authenticated-orcid":false,"given":"Shibai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2613-2752","authenticated-orcid":false,"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6559-8310","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5039-1501","authenticated-orcid":false,"given":"Jiaxin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7194-3327","authenticated-orcid":false,"given":"Yee-Hong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108982_bib0001","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"5803","article-title":"Localizing moments in video with natural language","author":"Anne Hendricks","year":"2017"},{"issue":"7","key":"10.1016\/j.neunet.2026.108982_bib0002","doi-asserted-by":"crossref","first-page":"6559","DOI":"10.1109\/TCSVT.2024.3360530","article-title":"Multilevel semantic interaction alignment for video\u2013text cross-modal retrieval","volume":"34","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.108982_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106813","article-title":"Multi-modal graph aggregation transformer for image captioning","volume":"181","author":"Chen","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108982_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10638","article-title":"Fine-grained video-text retrieval with hierarchical graph reasoning","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.108982_bib0005","unstructured":"Cheng, X., Lin, H., Wu, X., Yang, F., & Shen, D. (2021). Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. arXiv: 2109.04290."},{"key":"10.1016\/j.neunet.2026.108982_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106211","article-title":"Structure-aware contrastive hashing for unsupervised cross-modal retrieval","volume":"174","author":"Cui","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108982_bib0007","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.knosys.2016.02.001","article-title":"Study on density peaks clustering based on k-nearest neighbors and principal component analysis","volume":"99","author":"Du","year":"2016","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108982_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3354","article-title":"Mdmmt: Multidomain multimodal transformer for video retrieval","author":"Dzabraev","year":"2021"},{"key":"10.1016\/j.neunet.2026.108982_bib0009","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"13723","article-title":"Uatvr: Uncertainty-adaptive text-video retrieval","author":"Fang","year":"2023"},{"issue":"3","key":"10.1016\/j.neunet.2026.108982_bib0010","doi-asserted-by":"crossref","first-page":"1438","DOI":"10.1109\/TCSVT.2022.3207910","article-title":"Temporal multimodal graph transformer with global-local alignment for video-text retrieval","volume":"33","author":"Feng","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.108982_bib0011","series-title":"Computer vision\u2013ECCV 2020: 16th European conference","first-page":"214","article-title":"Multi-modal transformer for video retrieval","author":"Gabeur","year":"2020"},{"key":"10.1016\/j.neunet.2026.108982_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5006","article-title":"X-Pool: Cross-modal language-video attention for text-video retrieval","author":"Gorti","year":"2022"},{"key":"10.1016\/j.neunet.2026.108982_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106200","article-title":"Hierarchical matching and reasoning for multi-query image retrieval","volume":"173","author":"Ji","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108982_bib0014","first-page":"30291","article-title":"Expectation-maximization contrastive learning for compact video-and-language representations","volume":"35","author":"Jin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108982_bib0015","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2472","article-title":"Video-text as game players: Hierarchical banzhaf interaction for cross-modal representation learning","author":"Jin","year":"2023"},{"key":"10.1016\/j.neunet.2026.108982_bib0016","series-title":"Proceedings of the thirty-second international joint conference on artificial intelligence, IJCAI-23","first-page":"938","article-title":"Text-video retrieval with disentangled conceptualization and set-to-set alignment","author":"Jin","year":"2023"},{"key":"10.1016\/j.neunet.2026.108982_bib0017","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2470","article-title":"Diffusionret: Generative text-video retrieval with diffusion model","author":"Jin","year":"2023"},{"key":"10.1016\/j.neunet.2026.108982_bib0018","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"706","article-title":"Dense-captioning events in videos","author":"Krishna","year":"2017"},{"key":"10.1016\/j.neunet.2026.108982_bib0019","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7331","article-title":"Less is more: Clipbert for video-and-language learning via sparse sampling","author":"Lei","year":"2021"},{"key":"10.1016\/j.neunet.2026.108982_bib0020","series-title":"Proceedings of the thirty-fourth international joint conference on artificial intelligence, IJCAI-25","first-page":"5779","article-title":"DUQ: Dual uncertainty quantification for text-video retrieval","author":"Liu","year":"2025"},{"key":"10.1016\/j.neunet.2026.108982_bib0021","unstructured":"Liu, Y., Albanie, S., Nagrani, A., & Zisserman, A. (2026). Use what you have: Video retrieval using representations from collaborative experts. arXiv: 1907.13487."},{"key":"10.1016\/j.neunet.2026.108982_bib0022","series-title":"European conference on computer vision","first-page":"319","article-title":"Ts2-Net: Token shift and selection transformer for text-video retrieval","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108982_bib0023","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","article-title":"Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning","volume":"508","author":"Luo","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108982_bib0024","unstructured":"Patrick, M., Huang, P.-Y., Asano, Y., Metze, F., Hauptmann, A., Henriques, J., & Vedaldi, A. (2020). Support-set bottlenecks for video-text representation learning. arXiv: 2010.02824."},{"key":"10.1016\/j.neunet.2026.108982_bib0025","series-title":"European conference on computer vision","first-page":"76","article-title":"Video question answering with iterative video-text co-tokenization","author":"Piergiovanni","year":"2022"},{"key":"10.1016\/j.neunet.2026.108982_bib0026","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2026.108982_bib0027","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3202","article-title":"A dataset for movie description","author":"Rohrbach","year":"2015"},{"key":"10.1016\/j.neunet.2026.108982_bib0028","series-title":"Computer vision\u2013ECCV 2016: 14th European conference","first-page":"510","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","author":"Sigurdsson","year":"2016"},{"key":"10.1016\/j.neunet.2026.108982_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16551","article-title":"Text is MASS: Modeling as stochastic embedding for text-video retrieval","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.108982_bib0030","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4581","article-title":"Vatex: A large-scale, high-quality multilingual dataset for video-and-language research","author":"Wang","year":"2019"},{"issue":"12","key":"10.1016\/j.neunet.2026.108982_bib0031","doi-asserted-by":"crossref","first-page":"8822","DOI":"10.1109\/TCSVT.2022.3195874","article-title":"A high-dimensional sparse hashing framework for cross-modal retrieval","volume":"32","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.108982_bib0032","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2816","article-title":"Unified coarse-to-fine alignment for video-text retrieval","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.108982_bib0033","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.neunet.2023.08.057","article-title":"A multi-scale self-supervised hypergraph contrastive learning framework for video question answering","volume":"168","author":"Wang","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108982_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10704","article-title":"Cap4video: What can auxiliary captions do for text-video retrieval?","author":"Wu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108982_bib0035","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"5288","article-title":"Msr-Vtt: A large video description dataset for bridging video and language","author":"Xu","year":"2016"},{"key":"10.1016\/j.neunet.2026.108982_bib0036","unstructured":"Xue, H., Sun, Y., Liu, B., Fu, J., Song, R., Li, H., & Luo, J. (2022). Clip-Vip: Adapting pre-trained image-text model to video-language representation alignment. arXiv: 2209.06430."},{"key":"10.1016\/j.neunet.2026.108982_bib0037","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"1686","article-title":"Just ask: Learning to answer questions from millions of narrated videos","author":"Yang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108982_bib0038","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"471","article-title":"A joint sequence fusion model for video question answering and retrieval","author":"Yu","year":"2018"},{"key":"10.1016\/j.neunet.2026.108982_bib0039","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11101","article-title":"Not all tokens are equal: Human-centric visual analysis via token clustering transformer","author":"Zeng","year":"2022"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004430?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004430?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:09:42Z","timestamp":1781147382000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004430"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":39,"alternative-id":["S0893608026004430"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108982","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"V-Sparse: From temporal-spatial visual semantic compression to coarse-to-fine interaction for text-video retrieval","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108982","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":"108982"}}