{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T12:04:51Z","timestamp":1777377891918,"version":"3.51.4"},"reference-count":61,"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":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"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.2026.100814","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:43:59Z","timestamp":1776444239000},"page":"100814","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Deep video summarization using a Correlation Attention model"],"prefix":"10.1016","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4816-0428","authenticated-orcid":false,"given":"Hari","family":"K.C.","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2225-2578","authenticated-orcid":false,"given":"Sushil","family":"Shrestha","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1357-0531","authenticated-orcid":false,"given":"Manish","family":"Pokharel","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.array.2026.100814_b1","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1080\/19312458.2020.1810648","article-title":"Automated visual content analysis (AVCA) in communication research: A protocol for large scale image classification with pre-trained computer vision models","volume":"14","author":"Araujo","year":"2020","journal-title":"Commun Methods Meas"},{"key":"10.1016\/j.array.2026.100814_b2","doi-asserted-by":"crossref","first-page":"535","DOI":"10.25518\/0037-9565.6872","article-title":"New approach in video summarization based on color feature","volume":"86","author":"Sarmadi","year":"2017","journal-title":"Bull la Soci\u00e9t\u00e9 R. des Sci Li\u00e8ge"},{"key":"10.1016\/j.array.2026.100814_b3","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3090","article-title":"Video summarization by learning submodular mixtures of objectives","author":"Gygli","year":"2015"},{"key":"10.1016\/j.array.2026.100814_b4","series-title":"2019 IEEE winter conference on applications of computer vision","first-page":"666","article-title":"A framework towards domain specific video summarization","author":"Kaushal","year":"2019"},{"key":"10.1016\/j.array.2026.100814_b5","first-page":"693","article-title":"Hierarchical visual interface for educational video retrieval and summarization","volume":"vol. 12177","author":"Zhang","year":"2022"},{"key":"10.1016\/j.array.2026.100814_b6","series-title":"2018 IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7435","article-title":"Viewpoint-aware video summarization","author":"Kanehira","year":"2018"},{"key":"10.1016\/j.array.2026.100814_b7","series-title":"Proceedings of the European conference on computer vision","first-page":"347","article-title":"Video summarization using fully convolutional sequence networks","author":"Rochan","year":"2018"},{"key":"10.1016\/j.array.2026.100814_b8","series-title":"ICASSP 2023-2023 IEEE international conference on acoustics, speech and signal processing","first-page":"1","article-title":"Mhscnet: A multimodal hierarchical shot-aware convolutional network for video summarization","author":"Xu","year":"2023"},{"key":"10.1016\/j.array.2026.100814_b9","doi-asserted-by":"crossref","first-page":"103041","DOI":"10.1109\/ACCESS.2022.3209275","article-title":"LTC-SUM: Lightweight client-driven personalized video summarization framework using 2D CNN","volume":"10","author":"Mujtaba","year":"2022","journal-title":"IEEE Access"},{"issue":"8","key":"10.1016\/j.array.2026.100814_b10","doi-asserted-by":"crossref","first-page":"5181","DOI":"10.1109\/TNNLS.2021.3119969","article-title":"AudioVisual video summarization","volume":"34","author":"Zhao","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10.1016\/j.array.2026.100814_b11","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"202","article-title":"Unsupervised video summarization with adversarial lstm networks","author":"Mahasseni","year":"2017"},{"issue":"1","key":"10.1016\/j.array.2026.100814_b12","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1109\/TCSVT.2022.3197819","article-title":"Unsupervised video summarization via deep reinforcement learning with shot-level semantics","volume":"33","author":"Yuan","year":"2022","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"10.1016\/j.array.2026.100814_b13","series-title":"Query-conditioned three-player adversarial network for video summarization","author":"Zhang","year":"2018"},{"issue":"24","key":"10.1016\/j.array.2026.100814_b14","doi-asserted-by":"crossref","first-page":"35237","DOI":"10.1007\/s11042-019-08175-y","article-title":"Dilated temporal relational adversarial network for generic video summarization","volume":"78","author":"Zhang","year":"2019","journal-title":"Multimedia Tools Appl"},{"key":"10.1016\/j.array.2026.100814_b15","first-page":"12426","article-title":"Convolutional hierarchical attention network for query-focused video summarization","volume":"vol. 34","author":"Xiao","year":"2020"},{"key":"10.1016\/j.array.2026.100814_b16","series-title":"Proceedings of the Asian conference on computer vision","article-title":"Transforming multi-concept attention into video summarization","author":"Liu","year":"2020"},{"key":"10.1016\/j.array.2026.100814_b17","series-title":"Supervised video summarization via multiple feature sets with parallel attention","author":"Ghauri","year":"2021"},{"key":"10.1016\/j.array.2026.100814_b18","series-title":"Asian conference on computer vision","first-page":"39","article-title":"Summarizing videos with attention","author":"Fajtl","year":"2018"},{"key":"10.1016\/j.array.2026.100814_b19","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"339","article-title":"Multi-stream dynamic video summarization","author":"Elfeki","year":"2022"},{"key":"10.1016\/j.array.2026.100814_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2021.107618","article-title":"Deep hierarchical LSTM networks with attention for video summarization","volume":"97","author":"Lin","year":"2022","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.array.2026.100814_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.105667","article-title":"A review on video summarization techniques","volume":"118","author":"Meena","year":"2023","journal-title":"Eng Appl Artif Intell"},{"key":"10.1016\/j.array.2026.100814_b22","series-title":"Proceedings of the 25th ACM international conference on multimedia","first-page":"1164","article-title":"Elasticplay: Interactive video summarization with dynamic time budgets","author":"Jin","year":"2017"},{"key":"10.1016\/j.array.2026.100814_b23","series-title":"Proceedings of the workshop on new frontiers in summarization","first-page":"1","article-title":"Video highlights detection and summarization with lag-calibration based on concept-emotion mapping of crowdsourced time-sync comments","author":"Ping","year":"2017"},{"issue":"5","key":"10.1016\/j.array.2026.100814_b24","first-page":"34","article-title":"Two level key frame extraction for action recognition using content based adaptive threshold","volume":"12","author":"Jahagirdar","year":"2019","journal-title":"Int J Intell Eng Syst"},{"issue":"3","key":"10.1016\/j.array.2026.100814_b25","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s00530-019-00642-8","article-title":"Keyframe extraction using pearson correlation coefficient and color moments","volume":"26","author":"Bommisetty","year":"2020","journal-title":"Multimedia Syst"},{"issue":"11","key":"10.1016\/j.array.2026.100814_b26","doi-asserted-by":"crossref","first-page":"5260","DOI":"10.3390\/app11115260","article-title":"Multimodal summarization of user-generated videos","volume":"11","author":"Psallidas","year":"2021","journal-title":"Appl Sci"},{"key":"10.1016\/j.array.2026.100814_b27","series-title":"2017 international conference on new trends in computing sciences","first-page":"24","article-title":"CNN-based prediction of frame-level shot importance for video summarization","author":"Al Nahian","year":"2017"},{"key":"10.1016\/j.array.2026.100814_b28","series-title":"2019 IEEE winter conference on applications of computer vision","first-page":"754","article-title":"Video summarization via actionness ranking","author":"Elfeki","year":"2019"},{"key":"10.1016\/j.array.2026.100814_b29","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.jvcir.2018.12.009","article-title":"EVS-DK: Event video skimming using deep keyframe","volume":"58","author":"Kumar","year":"2019","journal-title":"J Vis Commun Image Represent"},{"key":"10.1016\/j.array.2026.100814_b30","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1016\/j.procs.2020.03.203","article-title":"Video summarization using highlight detection and pairwise deep ranking model","volume":"167","author":"Sridevi","year":"2020","journal-title":"Procedia Comput Sci"},{"key":"10.1016\/j.array.2026.100814_b31","first-page":"8537","article-title":"Discriminative feature learning for unsupervised video summarization","volume":"vol. 33","author":"Jung","year":"2019"},{"key":"10.1016\/j.array.2026.100814_b32","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1410","article-title":"A memory network approach for story-based temporal summarization of 360 videos","author":"Lee","year":"2018"},{"key":"10.1016\/j.array.2026.100814_b33","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.sigpro.2018.01.028","article-title":"Hypergraph dominant set based multi-video summarization","volume":"148","author":"Ji","year":"2018","journal-title":"Signal Process"},{"key":"10.1016\/j.array.2026.100814_b34","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7596","article-title":"Rethinking the evaluation of video summaries","author":"Otani","year":"2019"},{"issue":"10","key":"10.1016\/j.array.2026.100814_b35","doi-asserted-by":"crossref","first-page":"2711","DOI":"10.1109\/TMM.2019.2959451","article-title":"Unsupervised video summarization with cycle-consistent adversarial LSTM networks","volume":"22","author":"Yuan","year":"2019","journal-title":"IEEE Trans Multimed"},{"issue":"7","key":"10.1016\/j.array.2026.100814_b36","doi-asserted-by":"crossref","first-page":"5778","DOI":"10.1109\/TIE.2019.2931283","article-title":"Meta learning for task-driven video summarization","volume":"67","author":"Li","year":"2019","journal-title":"IEEE Trans Ind Electron"},{"issue":"6","key":"10.1016\/j.array.2026.100814_b37","doi-asserted-by":"crossref","first-page":"1709","DOI":"10.1109\/TCSVT.2019.2904996","article-title":"Video summarization with attention-based encoder\u2013decoder networks","volume":"30","author":"Ji","year":"2019","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"10.1016\/j.array.2026.100814_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128945","article-title":"Graph convolutional network for fast video summarization in compressed domain","volume":"617","author":"Yeh","year":"2025","journal-title":"Neurocomputing","ISSN":"https:\/\/id.crossref.org\/issn\/0925-2312","issn-type":"print"},{"issue":"9","key":"10.1016\/j.array.2026.100814_b39","doi-asserted-by":"crossref","first-page":"6219","DOI":"10.1007\/s11042-024-19022-0","article-title":"A hybrid deep learning framework for daily living human activity recognition with cluster-based video summarization","volume":"84","author":"Hossain","year":"2025","journal-title":"Multimedia Tools Appl"},{"key":"10.1016\/j.array.2026.100814_b40","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","ISSN":"https:\/\/id.crossref.org\/issn\/0957-4174","issn-type":"print"},{"key":"10.1016\/j.array.2026.100814_b41","series-title":"Proceedings of the 2024 CHI conference on human factors in computing systems","first-page":"1","article-title":"Making short-form videos accessible with hierarchical video summaries","author":"Van Daele","year":"2024"},{"key":"10.1016\/j.array.2026.100814_b42","series-title":"Proceedings of the 28th ACM international conference on multimedia","first-page":"4023","article-title":"Query twice: Dual mixture attention meta learning for video summarization","author":"Wang","year":"2020"},{"key":"10.1016\/j.array.2026.100814_b43","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","ISSN":"https:\/\/id.crossref.org\/issn\/0957-4174","issn-type":"print"},{"key":"10.1016\/j.array.2026.100814_b44","series-title":"2021 IEEE international symposium on multimedia","first-page":"226","article-title":"Combining global and local attention with positional encoding for video summarization","author":"Apostolidis","year":"2021"},{"key":"10.1016\/j.array.2026.100814_b45","doi-asserted-by":"crossref","first-page":"43611","DOI":"10.1109\/ACCESS.2022.3163414","article-title":"Exploring global diversity and local context for video summarization","volume":"10","author":"Pan","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.array.2026.100814_b46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2021.09.015","article-title":"Video summarization with a dual-path attentive network","volume":"467","author":"Liang","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.array.2026.100814_b47","series-title":"Enhanced video summarization using BiLSTM encoder-decoder with dual attention and particle swarm optimization","author":"Lodhi","year":"2025"},{"key":"10.1016\/j.array.2026.100814_b48","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3538282","article-title":"Design of an integrated model for video summarization using multimodal fusion and YOLO for crime scene analysis","author":"Veesam","year":"2025","journal-title":"IEEE Access"},{"issue":"11","key":"10.1016\/j.array.2026.100814_b49","doi-asserted-by":"crossref","first-page":"2269","DOI":"10.3390\/electronics14112269","article-title":"A novel trustworthy video summarization algorithm through a mixture of LoRA experts","volume":"14","author":"Du","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.array.2026.100814_b50","series-title":"European conference on computer vision","first-page":"766","article-title":"Video summarization with long short-term memory","author":"Zhang","year":"2016"},{"issue":"11","key":"10.1016\/j.array.2026.100814_b51","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans Signal Process"},{"key":"10.1016\/j.array.2026.100814_b52","doi-asserted-by":"crossref","first-page":"73992","DOI":"10.1109\/ACCESS.2020.2988550","article-title":"Sentiment classification using a single-layered BiLSTM model","volume":"8","author":"Hameed","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.array.2026.100814_b53","doi-asserted-by":"crossref","first-page":"2767","DOI":"10.1016\/j.procs.2023.01.248","article-title":"A deep stacked bidirectional LSTM (sbilstm) model for petroleum production forecasting","volume":"218","author":"Sirisha","year":"2023","journal-title":"Procedia Comput Sci"},{"key":"10.1016\/j.array.2026.100814_b54","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"},{"key":"10.1016\/j.array.2026.100814_b55","series-title":"Proceedings first IEEE international conference on cognitive informatics","first-page":"107","article-title":"Compression and its metrics for multimedia","author":"Kinsner","year":"2002"},{"key":"10.1016\/j.array.2026.100814_b56","doi-asserted-by":"crossref","unstructured":"Apostolidis E, Adamantidou E, Metsai AI, Mezaris V, Patras I. Performance over random: A robust evaluation protocol for video summarization methods. In: Proceedings of the 28th ACM international conference on multimedia. 2020, p. 1056\u201364.","DOI":"10.1145\/3394171.3413632"},{"key":"10.1016\/j.array.2026.100814_b57","series-title":"Intelligent analysis of multimedia information","first-page":"352","article-title":"Content coverage and redundancy removal in video summarization","author":"Bhaumik","year":"2017"},{"key":"10.1016\/j.array.2026.100814_b58","series-title":"Proceedings of the 25th ACM international conference on multimedia","first-page":"863","article-title":"Hierarchical recurrent neural network for video summarization","author":"Zhao","year":"2017"},{"key":"10.1016\/j.array.2026.100814_b59","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"},{"issue":"6","key":"10.1016\/j.array.2026.100814_b60","doi-asserted-by":"crossref","first-page":"3685","DOI":"10.1007\/s00530-023-01154-2","article-title":"A two-stage attention augmented fully convolutional network-based dynamic video summarization","volume":"29","author":"Gupta","year":"2023","journal-title":"Multimedia Syst"},{"issue":"6","key":"10.1016\/j.array.2026.100814_b61","doi-asserted-by":"crossref","first-page":"680","DOI":"10.3390\/sym16060680","article-title":"Effective video summarization using channel attention-assisted encoder\u2013decoder framework","volume":"16","author":"Alharbi","year":"2024","journal-title":"Symmetry"}],"container-title":["Array"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001372?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001372?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:09:21Z","timestamp":1777367361000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2590005626001372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":61,"alternative-id":["S2590005626001372"],"URL":"https:\/\/doi.org\/10.1016\/j.array.2026.100814","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":"Deep video summarization using a Correlation Attention model","name":"articletitle","label":"Article Title"},{"value":"Array","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.array.2026.100814","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":"100814"}}