{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:56:56Z","timestamp":1740106616029,"version":"3.37.3"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100011665","name":"Deanship of Scientific Research, King Saud University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009392","name":"Prince Sattam bin Abdulaziz University","doi-asserted-by":"publisher","award":["PSAU\/2024\/R\/1445"],"id":[{"id":"10.13039\/100009392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1016\/j.jvcir.2024.104130","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T14:57:02Z","timestamp":1711637822000},"page":"104130","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A deep audio-visual model for efficient dynamic video summarization"],"prefix":"10.1016","volume":"100","author":[{"given":"Gamal","family":"El-Nagar","sequence":"first","affiliation":[]},{"given":"Ahmed","family":"El-Sawy","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4946-3682","authenticated-orcid":false,"given":"Metwally","family":"Rashad","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2024.104130_b1","first-page":"1","article-title":"A static video summarization approach via block-based self-motivated visual attention scoring mechanism","author":"Li","year":"2023","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.jvcir.2024.104130_b2","doi-asserted-by":"crossref","unstructured":"H. Terbouche, M. Morel, M. Rodriguez, A. Othmani, Multi-Annotation Attention Model for Video Summarization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 3143\u20133152.","DOI":"10.1109\/CVPRW59228.2023.00316"},{"issue":"8","key":"10.1016\/j.jvcir.2024.104130_b3","doi-asserted-by":"crossref","first-page":"9823","DOI":"10.1007\/s12652-021-03641-8","article-title":"A multi-stage deep adversarial network for video summarization with knowledge distillation","volume":"14","author":"Sreeja","year":"2023","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"issue":"10","key":"10.1016\/j.jvcir.2024.104130_b4","doi-asserted-by":"crossref","first-page":"6065","DOI":"10.3390\/app13106065","article-title":"Static video summarization using video coding features with frame-level temporal subsampling and deep learning","volume":"13","author":"Issa","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.jvcir.2024.104130_b5","series-title":"2022 International Conference on Signal and Information Processing","first-page":"1","article-title":"S-VSUM: Static video content summarization using CNN","author":"Tonge","year":"2022"},{"key":"10.1016\/j.jvcir.2024.104130_b6","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1007\/s11760-020-01791-4","article-title":"Static video summarization using multi-CNN with sparse autoencoder and random forest classifier","volume":"15","author":"Nair","year":"2020","journal-title":"Signal, Image Video Process."},{"key":"10.1016\/j.jvcir.2024.104130_b7","series-title":"Proceedings of IEEE International Conference on Image Processing","article-title":"Adopting self-supervised learning into unsupervised video summarization through restorative score","author":"Abbasi","year":"2023"},{"issue":"10","key":"10.1016\/j.jvcir.2024.104130_b8","doi-asserted-by":"crossref","first-page":"14071","DOI":"10.1007\/s12652-022-04112-4","article-title":"VSMCNN-dynamic summarization of videos using salient features from multi-CNN model","volume":"14","author":"Nair","year":"2023","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"10.1016\/j.jvcir.2024.104130_b9","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":"8","key":"10.1016\/j.jvcir.2024.104130_b10","doi-asserted-by":"crossref","first-page":"3278","DOI":"10.1109\/TCSVT.2020.3037883","article-title":"AC-SUM-GAN: Connecting actor-critic and generative adversarial networks for unsupervised video summarization","volume":"31","author":"Apostolidis","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2024.104130_b11","first-page":"1","article-title":"Bayesian fuzzy clustering and deep CNN-based automatic video summarization","author":"Singh","year":"2023","journal-title":"Multimedia Tools Appl."},{"issue":"5","key":"10.1016\/j.jvcir.2024.104130_b12","first-page":"2793","article-title":"Reconstructive sequence-graph network for video summarization","volume":"44","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2024.104130_b13","series-title":"IJCAI","first-page":"2403","article-title":"Video summarization via label distributions dual-reward","author":"Gao","year":"2021"},{"key":"10.1016\/j.jvcir.2024.104130_b14","series-title":"2021 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Supervised video summarization via multiple feature sets with parallel attention","author":"Ghauri","year":"2021"},{"key":"10.1016\/j.jvcir.2024.104130_b15","article-title":"Audiovisual video summarization","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.jvcir.2024.104130_b16","series-title":"Advanced Machine Intelligence and Signal Processing","first-page":"229","article-title":"Deep learning framework based on audio\u2013Visual features for video summarization","author":"Rhevanth","year":"2022"},{"year":"2023","series-title":"SELF-VS: Self-supervised encoding learning for video summarization","author":"Mokhtarabadi","key":"10.1016\/j.jvcir.2024.104130_b17"},{"key":"10.1016\/j.jvcir.2024.104130_b18","doi-asserted-by":"crossref","unstructured":"H. Li, Q. Ke, M. Gong, T. Drummond, Progressive video summarization via multimodal self-supervised learning, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 5584\u20135593.","DOI":"10.1109\/WACV56688.2023.00554"},{"issue":"23","key":"10.1016\/j.jvcir.2024.104130_b19","doi-asserted-by":"crossref","DOI":"10.3390\/electronics12234757","article-title":"Video summarization generation based on graph structure reconstruction","volume":"12","author":"Zhang","year":"2023","journal-title":"Electronics"},{"year":"2023","series-title":"Self-attention based generative adversarial networks for unsupervised video summarization","author":"Nektaria Minaidi","key":"10.1016\/j.jvcir.2024.104130_b20"},{"key":"10.1016\/j.jvcir.2024.104130_b21","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"},{"year":"2014","series-title":"Category-Specific Video Summarization","author":"Potapov","key":"10.1016\/j.jvcir.2024.104130_b22"},{"key":"10.1016\/j.jvcir.2024.104130_b23","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"766","article-title":"Video summarization with long short-term memory","author":"Zhang","year":"2016"},{"key":"10.1016\/j.jvcir.2024.104130_b24","series-title":"ECCV","article-title":"Creating summaries from user videos","author":"Gygli","year":"2014"},{"key":"10.1016\/j.jvcir.2024.104130_b25","doi-asserted-by":"crossref","unstructured":"Y. Song, J. Vallmitjana, A. Stent, A. Jaimes, Tvsum: Summarizing web videos using titles, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 5179\u20135187.","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"10.1016\/j.jvcir.2024.104130_b26","doi-asserted-by":"crossref","unstructured":"Y. Zhang, M. Kampffmeyer, X. Zhao, M. Tan, Dtr-gan: Dilated temporal relational adversarial network for video summarization, in: Proceedings of the ACM Turing Celebration Conference-China, 2019, pp. 1\u20136.","DOI":"10.1145\/3321408.3322622"},{"key":"10.1016\/j.jvcir.2024.104130_b27","doi-asserted-by":"crossref","unstructured":"Z. Li, L. Yang, Weakly supervised deep reinforcement learning for video summarization with semantically meaningful reward, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 3239\u20133247.","DOI":"10.1109\/WACV48630.2021.00328"},{"issue":"8","key":"10.1016\/j.jvcir.2024.104130_b28","doi-asserted-by":"crossref","first-page":"3278","DOI":"10.1109\/TCSVT.2020.3037883","article-title":"AC-SUM-GAN: Connecting actor-critic and generative adversarial networks for unsupervised video summarization","volume":"31","author":"Apostolidis","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"10.1016\/j.jvcir.2024.104130_b29","first-page":"1765","article-title":"Deep attentive video summarization with distribution consistency learning","volume":"32","year":"2021","journal-title":"IEEE Trans. Neural Netw."},{"issue":"8","key":"10.1016\/j.jvcir.2024.104130_b30","doi-asserted-by":"crossref","first-page":"9823","DOI":"10.1007\/s12652-021-03641-8","article-title":"A multi-stage deep adversarial network for video summarization with knowledge distillation","volume":"14","author":"Sreeja","year":"2022","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"year":"2023","series-title":"Multimodal frame-scoring transformer for video summarization","author":"Park","key":"10.1016\/j.jvcir.2024.104130_b31"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320324000853?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320324000853?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T05:42:58Z","timestamp":1731649378000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320324000853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":31,"alternative-id":["S1047320324000853"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2024.104130","relation":{},"ISSN":["1047-3203"],"issn-type":[{"type":"print","value":"1047-3203"}],"subject":[],"published":{"date-parts":[[2024,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A deep audio-visual model for efficient dynamic video summarization","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.2024.104130","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"104130"}}