{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:04:20Z","timestamp":1784534660380,"version":"3.55.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.jvcir.2026.104872","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T23:36:55Z","timestamp":1781566615000},"page":"104872","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A low-computational video synopsis framework and a benchmark dataset"],"prefix":"10.1016","volume":"119","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0599-4118","authenticated-orcid":false,"given":"R.","family":"Malekpour","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2237-1374","authenticated-orcid":false,"given":"M.M.","family":"Morsali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9852-5088","authenticated-orcid":false,"given":"H.","family":"Mohammadzade","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104872_b1","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.jvcir.2026.104872_b2","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1109\/TIP.2022.3143699","article-title":"Video summarization through reinforcement learning with a 3d spatio-temporal u-net","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104872_b3","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1109\/TIP.2022.3146012","article-title":"Graph convolutional dictionary selection with l2, p norm for video summarization","volume":"31","author":"Ma","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104872_b4","doi-asserted-by":"crossref","first-page":"3017","DOI":"10.1109\/TIP.2022.3163855","article-title":"Relational reasoning over spatial\u2013temporal graphs for video summarization","volume":"31","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104872_b5","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":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104872_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2020.102991","article-title":"Multiview video summarization using video partitioning and clustering","volume":"74","author":"Singh Parihar","year":"2021","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104872_b7","doi-asserted-by":"crossref","first-page":"5889","DOI":"10.1109\/TIP.2020.2985868","article-title":"Query-biased self-attentive network for query-focused video summarization","volume":"29","author":"Xiao","year":"2020","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"10.1016\/j.jvcir.2026.104872_b8","doi-asserted-by":"crossref","first-page":"2654","DOI":"10.1109\/TIP.2018.2889265","article-title":"User-ranking video summarization with multi-stage spatio\u2013temporal representation","volume":"28","author":"Huang","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104872_b9","doi-asserted-by":"crossref","unstructured":"B. Yang, R. Nevatia, Multi-target tracking by online learning of non-linear motion patterns and robust appearance models, in: 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 1918\u20131925.","DOI":"10.1109\/CVPR.2012.6247892"},{"key":"10.1016\/j.jvcir.2026.104872_b10","doi-asserted-by":"crossref","unstructured":"R.R. Sillito, B. Fisher, Semi-supervised learning for anomalous trajectory detection, in: Proceedings British Machine Vision Conference BMVC2008, 2008, pp. 1035\u20131044.","DOI":"10.5244\/C.22.103"},{"issue":"3","key":"10.1016\/j.jvcir.2026.104872_b11","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1007\/s11277-019-06802-3","article-title":"Aco\u2013mkfcm: an optimized object detection and tracking using dnn and gravitational search algorithm","volume":"110","author":"Mahalingam","year":"2020","journal-title":"Wirel. Pers. Commun."},{"key":"10.1016\/j.jvcir.2026.104872_b12","doi-asserted-by":"crossref","unstructured":"B. Kille, F. Hopfgartner, T. Brodt, T. Heintz, The plista dataset, in: Proceedings of the 2013 International News Recommender Systems Workshop and Challenge, 2013, pp. 16\u201323.","DOI":"10.1145\/2516641.2516643"},{"key":"10.1016\/j.jvcir.2026.104872_b13","series-title":"2012 Visual Communications and Image Processing","first-page":"1","article-title":"Background modeling using local binary patterns of motion vector","author":"Wang","year":"2012"},{"key":"10.1016\/j.jvcir.2026.104872_b14","doi-asserted-by":"crossref","unstructured":"C. Schuldt, I. Laptev, B. Caputo, Recognizing human actions: a local svm approach, in: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., Vol. 3, 2004, pp. 32\u201336, Vol. 3.","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"10.1016\/j.jvcir.2026.104872_b15","doi-asserted-by":"crossref","unstructured":"M. Blank, L. Gorelick, E. Shechtman, M. Irani, R. Basri, Actions as space\u2013time shapes, in: Tenth IEEE International Conference on Computer Vision (ICCV\u201905) Volume 1, Vol. 2, 2005, pp. 1395\u20131402, Vol. 2.","DOI":"10.1109\/ICCV.2005.28"},{"key":"10.1016\/j.jvcir.2026.104872_b16","series-title":"CVPR 2011","first-page":"3153","article-title":"A large-scale benchmark dataset for event recognition in surveillance video","author":"Oh","year":"2011"},{"key":"10.1016\/j.jvcir.2026.104872_b17","doi-asserted-by":"crossref","unstructured":"J.-P. Jodoin, G.-A. Bilodeau, N. Saunier, Urban tracker: Multiple object tracking in urban mixed traffic, in: IEEE Winter Conference on Applications of Computer Vision, 2014, pp. 885\u2013892.","DOI":"10.1109\/WACV.2014.6836010"},{"key":"10.1016\/j.jvcir.2026.104872_b18","doi-asserted-by":"crossref","unstructured":"S. Jagtap, N.B. Chopade, A comprehensive investigation about video synopsis methodology and research challenges, in: Inventive Computation and Information Technologies: Proceedings of ICICIT 2020, 2021, pp. 911\u2013923.","DOI":"10.1007\/978-981-33-4305-4_66"},{"key":"10.1016\/j.jvcir.2026.104872_b19","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.cviu.2019.02.004","article-title":"Video synopsis: A survey","volume":"181","author":"Baskurt","year":"2019","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.jvcir.2026.104872_b20","doi-asserted-by":"crossref","unstructured":"N. K, A. Narayanan, Video synopsis: State-of-the-art and research challenges, in: 2018 International Conference on Circuits and Systems in Digital Enterprise Technology, ICCSDET, 2018, pp. 1\u201310.","DOI":"10.1109\/ICCSDET.2018.8821157"},{"issue":"2","key":"10.1016\/j.jvcir.2026.104872_b21","doi-asserted-by":"crossref","first-page":"108","DOI":"10.3390\/systems11020108","article-title":"Video synopsis algorithms and framework: A survey and comparative evaluation","volume":"11","author":"Ingle","year":"2023","journal-title":"Systems"},{"issue":"8","key":"10.1016\/j.jvcir.2026.104872_b22","doi-asserted-by":"crossref","first-page":"3798","DOI":"10.1109\/TIP.2018.2823420","article-title":"Video synopsis in complex situations","volume":"27","author":"Li","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"10.1016\/j.jvcir.2026.104872_b23","doi-asserted-by":"crossref","first-page":"1971","DOI":"10.1109\/TPAMI.2008.29","article-title":"Nonchronological video synopsis and indexing","volume":"30","author":"Pritch","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.jvcir.2026.104872_b24","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1109\/TCE.2020.2981829","article-title":"Hsajaya: An improved optimization scheme for consumer surveillance video synopsis generation","volume":"66","author":"Ghatak","year":"2020","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"4","key":"10.1016\/j.jvcir.2026.104872_b25","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1007\/s11760-020-01794-1","article-title":"Object-based video synopsis approach using particle swarm optimization","volume":"15","author":"Moussa","year":"2021","journal-title":"Signal, Image Video Process."},{"issue":"2","key":"10.1016\/j.jvcir.2026.104872_b26","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/TIP.2015.2507942","article-title":"Surveillance video synopsis via scaling down objects","volume":"25","author":"Li","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104872_b27","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1109\/TIP.2019.2942543","article-title":"Collision-free video synopsis incorporating object speed and size changes","volume":"29","author":"Nie","year":"2020","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"10.1016\/j.jvcir.2026.104872_b28","doi-asserted-by":"crossref","first-page":"1664","DOI":"10.1109\/TVCG.2012.176","article-title":"Compact video synopsis via global spatiotemporal optimization","volume":"19","author":"Nie","year":"2013","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.jvcir.2026.104872_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2022.103817","article-title":"An improved tube rearrangement strategy for choice-based surveillance video synopsis generation","volume":"132","author":"Ghatak","year":"2023","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.jvcir.2026.104872_b30","first-page":"92603","article-title":"Video synopsis based on attention mechanism and local transparent processing","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvcir.2026.104872_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104057","article-title":"Surveillance video synopsis framework base on tube set","volume":"98","author":"Zhang","year":"2024","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"8","key":"10.1016\/j.jvcir.2026.104872_b32","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.1016\/j.jvcir.2013.10.001","article-title":"Surveillance video synopsis in the compressed domain for fast video browsing","volume":"24","author":"zheng Wang","year":"2013","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"7","key":"10.1016\/j.jvcir.2026.104872_b33","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1109\/TCSVT.2014.2363738","article-title":"High-performance video condensation system","volume":"25","author":"Zhu","year":"2015","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104872_b34","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.neucom.2013.12.041","article-title":"Online video synopsis of structured motion","volume":"135","author":"Fu","year":"2014","journal-title":"Neurocomputing"},{"issue":"8","key":"10.1016\/j.jvcir.2026.104872_b35","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1109\/TCSVT.2014.2308603","article-title":"Maximum a posteriori probability estimation for online surveillance video synopsis","volume":"24","author":"Huang","year":"2014","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104872_b36","doi-asserted-by":"crossref","unstructured":"J. Jin, F. Liu, Z. Gan, Z. Cui, Online video synopsis method through simple tube projection strategy, in: 2016 8th International Conference on Wireless Communications & Signal Processing, WCSP, 2016, pp. 1\u20135.","DOI":"10.1109\/WCSP.2016.7752708"},{"key":"10.1016\/j.jvcir.2026.104872_b37","doi-asserted-by":"crossref","unstructured":"S. Feng, Z. Lei, D. Yi, S.Z. Li, Online content-aware video condensation, in: 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 2082\u20132087.","DOI":"10.1109\/CVPR.2012.6247913"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104872_b38","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/LSP.2016.2633374","article-title":"Fast online video synopsis based on potential collision graph","volume":"24","author":"He","year":"2017","journal-title":"IEEE Signal Process. Lett."},{"issue":"8","key":"10.1016\/j.jvcir.2026.104872_b39","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.1109\/LSP.2018.2848842","article-title":"Parallelized tube rearrangement algorithm for online video synopsis","volume":"25","author":"Ra","year":"2018","journal-title":"IEEE Signal Process. Lett."},{"issue":"8","key":"10.1016\/j.jvcir.2026.104872_b40","doi-asserted-by":"crossref","first-page":"3873","DOI":"10.1109\/TIP.2019.2903322","article-title":"Rearranging online tubes for streaming video synopsis: A dynamic graph coloring approach","volume":"28","author":"Ruan","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104872_b41","doi-asserted-by":"crossref","first-page":"8318","DOI":"10.1109\/TIP.2021.3114986","article-title":"Scene adaptive online surveillance video synopsis via dynamic tube rearrangement using octree","volume":"30","author":"Yang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104872_b42","doi-asserted-by":"crossref","unstructured":"C.-Y. Wang, A. Bochkovskiy, H.-Y.M. Liao, Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, in: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 7464\u20137475.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"10.1016\/j.jvcir.2026.104872_b43","unstructured":"[Online]. Available: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"10.1016\/j.jvcir.2026.104872_b44","series-title":"Sfsort: Scene features-based simple online real-time tracker","author":"Morsali","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104872_b45","series-title":"Pedestrian walking, human activity recognition video, DataSet by UET peshawar","author":"Imtiaz","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104872_b46","series-title":"[Live camera] tanukikoji shopping street in sapporo and Hokkaido and Japan","author":"Tanukiya LIVE","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104872_b47","series-title":"Kranjska gora town center - live WebCam","author":"Kranjska Gora","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104872_b48","author":"APM Digital. AC Boardwalk Live","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104872_b49","series-title":"Radical video jockey-rvjjp. [live] osaka dotonbori live camera","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104872_b50","doi-asserted-by":"crossref","unstructured":"D. Davila, D. Du, B. Lewis, C. Funk, J. Van Pelt, R. Collins, K. Corona, M. Brown, S. McCloskey, A. Hoogs, B. Clipp, Mevid: Multi-view extended videos with identities for video person re-identification, in: 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV, 2023, pp. 1634\u20131643.","DOI":"10.1109\/WACV56688.2023.00168"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001677?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001677?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:24:10Z","timestamp":1784532250000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326001677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":50,"alternative-id":["S1047320326001677"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104872","relation":{"is-supplemented-by":[{"id-type":"uri","id":"https:\/\/drive.google.com\/drive\/folders\/14rqDbwsedevmk6n_ZCFfRzw-ofq-wGi0?usp=drive_link","asserted-by":"subject"}]},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A low-computational video synopsis framework and a benchmark dataset","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104872","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104872"}}