{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:19:47Z","timestamp":1779383987259,"version":"3.53.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076077"],"award-info":[{"award-number":["62076077"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017691","name":"Guangxi Key Research and Development Program","doi-asserted-by":"publisher","award":["2025FN9637998"],"award-info":[{"award-number":["2025FN9637998"]}],"id":[{"id":"10.13039\/501100017691","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":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113478","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:48:27Z","timestamp":1773272907000},"page":"113478","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DSTG-VS: Dynamic spatio-temporal graph network with global-local feature fusion for video summarization"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5801-4937","authenticated-orcid":false,"given":"Yujie","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0029-9235","authenticated-orcid":false,"given":"Haonan","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6042-8935","authenticated-orcid":false,"given":"Yingying","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2401-4859","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1571-4255","authenticated-orcid":false,"given":"Michael","family":"Meyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9121-8499","authenticated-orcid":false,"given":"Benying","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113478_bib0001","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"766","article-title":"Video summarization with long short-term memory","author":"Zhang","year":"2016"},{"key":"10.1016\/j.patcog.2026.113478_bib0002","series-title":"ACCV 2018 Workshops: 14th Asian Conference on Computer Vision","first-page":"39","article-title":"Summarizing videos with attention","author":"Fajtl","year":"2019"},{"key":"10.1016\/j.patcog.2026.113478_bib0003","doi-asserted-by":"crossref","first-page":"3013","DOI":"10.1109\/TIP.2023.3275069","article-title":"Video summarization with spatiotemporal vision transformer","volume":"32","author":"Hsu","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113478_bib0004","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"505","article-title":"Creating summaries from user videos","author":"Gygli","year":"2014"},{"key":"10.1016\/j.patcog.2026.113478_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2527","article-title":"VideoSAGE: video summarization with graph representation learning","author":"Chaves","year":"2024"},{"issue":"1","key":"10.1016\/j.patcog.2026.113478_bib0006","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.patrec.2010.08.004","article-title":"VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method","volume":"32","author":"De Avila","year":"2011","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2026.113478_bib0007","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"540","article-title":"Category-specific video summarization","author":"Potapov","year":"2014"},{"key":"10.1016\/j.patcog.2026.113478_bib0008","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"9143","article-title":"Cycle-SUM: cycle-consistent adversarial LSTM networks for unsupervised video summarization","volume":"33","author":"Yuan","year":"2019"},{"key":"10.1016\/j.patcog.2026.113478_bib0009","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1109\/LSP.2021.3066349","article-title":"Graph attention networks adjusted bi-LSTM for video summarization","volume":"28","author":"Zhong","year":"2021","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.patcog.2026.113478_bib0010","series-title":"Proceedings of the 2022 International Conference on Multimedia Retrieval","first-page":"407","article-title":"Summarizing videos using concentrated attention and considering the uniqueness and diversity of the video frames","author":"Apostolidis","year":"2022"},{"issue":"1","key":"10.1016\/j.patcog.2026.113478_bib0011","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113478_bib0012","doi-asserted-by":"crossref","first-page":"3017","DOI":"10.1109\/TIP.2022.3163855","article-title":"Relational reasoning over spatial-temporal graphs for video summarization","volume":"31","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113478_bib0013","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward","volume":"32","author":"Zhou","year":"2018"},{"key":"10.1016\/j.patcog.2026.113478_bib0014","unstructured":"B. Alkin, M. Beck, K. P\u00f6ppel, S. Hochreiter, J. Brandstetter, Vision-LSTM: xLSTM as generic vision backbone, 2024, arXiv: 2406.04303."},{"key":"10.1016\/j.patcog.2026.113478_bib0015","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5179","article-title":"TVSum: summarizing web videos using titles","author":"Song","year":"2015"},{"issue":"3","key":"10.1016\/j.patcog.2026.113478_bib0016","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1093\/biomet\/33.3.239","article-title":"The treatment of ties in ranking problems","volume":"33","author":"Kendall","year":"1945","journal-title":"Biometrika"},{"key":"10.1016\/j.patcog.2026.113478_bib0017","series-title":"CRC Standard Probability and Statistics Tables and Formulae","author":"Zwillinger","year":"1999"},{"key":"10.1016\/j.patcog.2026.113478_bib0018","series-title":"Proceedings of the Ieee Conference on Computer Vision and Pattern Recognition","first-page":"961","article-title":"ActivityNet: a large-scale video benchmark for human activity understanding","author":"Caba Heilbron","year":"2015"},{"key":"10.1016\/j.patcog.2026.113478_bib0019","series-title":"2021\u202fIEEE International Symposium on Multimedia (ISM)","first-page":"226","article-title":"Combining global and local attention with positional encoding for video summarization","author":"Apostolidis","year":"2021"},{"key":"10.1016\/j.patcog.2026.113478_bib0020","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"18981","article-title":"Video summarization with large language models","author":"Lee","year":"2025"},{"key":"10.1016\/j.patcog.2026.113478_bib0021","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3599","article-title":"V2Xum-LLM: cross-modal video summarization with temporal prompt instruction tuning","volume":"39","author":"Hua","year":"2025"},{"key":"10.1016\/j.patcog.2026.113478_bib0022","article-title":"Domain adaptive video summarization using generalized transformer","volume":"170","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113478_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123860","article-title":"Reconstructive network under contrastive graph rewards for video summarization","volume":"250","author":"Wu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113478_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108840","article-title":"Video summarization with a convolutional attentive adversarial network","volume":"131","author":"Liang","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113478_bib0025","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.patrec.2020.12.016","article-title":"Self-attention binary neural tree for video summarization","volume":"143","author":"Fu","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2026.113478_bib0026","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"1585","article-title":"Unsupervised video summarization via iterative training and simplified GAN","author":"Li","year":"2024"},{"key":"10.1016\/j.patcog.2026.113478_bib0027","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18847","article-title":"CSTA: CNN-based spatiotemporal attention for video summarization","author":"Son","year":"2024"},{"key":"10.1016\/j.patcog.2026.113478_bib0028","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.1109\/LSP.2023.3313091","article-title":"MAR-Net: motion-assisted reconstruction network for unsupervised video summarization","volume":"30","author":"Zhang","year":"2023","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.patcog.2026.113478_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107677","article-title":"Exploring global diverse attention via pairwise temporal relation for video summarization","volume":"111","author":"Li","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113478_bib0030","series-title":"2025 International Joint Conference on Neural Networks (IJCNN)","first-page":"1","article-title":"Global and local CNN attention mechanisms for video summarization","author":"Li","year":"2025"},{"key":"10.1016\/j.patcog.2026.113478_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119888","article-title":"Progressive reinforcement learning for video summarization","volume":"655","author":"Wang","year":"2024","journal-title":"Inf. Sci."},{"issue":"4","key":"10.1016\/j.patcog.2026.113478_bib0032","doi-asserted-by":"crossref","first-page":"2775","DOI":"10.1109\/TCSVT.2023.3312325","article-title":"VSS-Net: visual semantic self-mining network for video summarization","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113478_bib0033","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1109\/TIP.2020.3039886","article-title":"DSNet: a flexible detect-to-summarize network for video summarization","volume":"30","author":"Zhu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113478_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108312","article-title":"Learning multiscale hierarchical attention for video summarization","volume":"122","author":"Zhu","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113478_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123568","article-title":"Attention-guided multi-granularity fusion model for video summarization","volume":"249","author":"Zhang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113478_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109883","article-title":"Spatial\u2013temporal multi-scale interaction for few-shot video summarization","volume":"142","author":"Li","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113478_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121288","article-title":"Deep multi-scale pyramidal features network for supervised video summarization","volume":"237","author":"Khan","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113478_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111211","article-title":"Optimal features driven hybrid attention network for effective video summarization","volume":"158","author":"Khan","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113478_bib0039","doi-asserted-by":"crossref","first-page":"4170","DOI":"10.1109\/TIP.2023.3293762","article-title":"Semantic representation and attention alignment for graph information bottleneck in video summarization","volume":"32","author":"Zhong","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113478_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14867","article-title":"Align and attend: multimodal summarization with dual contrastive losses","author":"He","year":"2023"},{"key":"10.1016\/j.patcog.2026.113478_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111631","article-title":"Video summarization with temporal-channel visual transformer","volume":"165","author":"Tian","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113478_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110917","article-title":"Lightweight transformer-driven multi-scale trapezoidal attention network for saliency detection","volume":"155","author":"Usman","year":"2025","journal-title":"Eng. Appl. Artif. Intell."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004449?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004449?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:53:48Z","timestamp":1779382428000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":42,"alternative-id":["S0031320326004449"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113478","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DSTG-VS: Dynamic spatio-temporal graph network with global-local feature fusion for video summarization","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113478","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":"113478"}}