{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T20:08:51Z","timestamp":1793477331812,"version":"4.5.0"},"reference-count":83,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"The University of Tokyo","id":[{"id":"https:\/\/ror.org\/057zh3y96","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s10044-026-01686-z","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T12:26:02Z","timestamp":1782735962000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Language-guided frameworks for personalized video summarization"],"prefix":"10.1007","volume":"29","author":[{"given":"Tomoya","family":"Sugihara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuntaro","family":"Masuda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshihiko","family":"Yamasaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"1686_CR1","doi-asserted-by":"crossref","unstructured":"Zhou K, Qiao Y, Xiang T (2018) Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp 7582\u20137589","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"1686_CR2","doi-asserted-by":"crossref","unstructured":"Mahasseni B, Lam M, Todorovic S (2017) Unsupervised video summarization with adversarial lstm networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 202\u2013211","DOI":"10.1109\/CVPR.2017.318"},{"key":"1686_CR3","doi-asserted-by":"crossref","unstructured":"Jung Y, Cho D, Woo S, Kweon IS (2020) Global-and-local relative position embedding for unsupervised video summarization. In: Proceedings of the European Conference on Computer Vision. pp 167\u2013183","DOI":"10.1007\/978-3-030-58595-2_11"},{"key":"1686_CR4","doi-asserted-by":"crossref","unstructured":"Ghauri JA, Hakimov S, Ewerth R (2021) Supervised video summarization via multiple feature sets with parallel attention. In: Proceedings of the IEEE International Conference on Multimedia and Expo. pp 1\u20136","DOI":"10.1109\/ICME51207.2021.9428318"},{"key":"1686_CR5","doi-asserted-by":"crossref","unstructured":"Chen Y, Tao L, Wang X, Yamasaki T (2019) Weakly supervised video summarization by hierarchical reinforcement learning. In: Proceedings of the ACM International Conference on Multimedia in Asia. pp 1\u20136","DOI":"10.1145\/3338533.3366583"},{"key":"1686_CR6","doi-asserted-by":"crossref","unstructured":"Son J, Park J, Kim K (2024) Csta: Cnn-based spatiotemporal attention for video summarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 18847\u201318856","DOI":"10.1109\/CVPR52733.2024.01783"},{"key":"1686_CR7","doi-asserted-by":"crossref","unstructured":"Jung Y, Cho D, Kim D, Woo S, Kweon IS (2019) Discriminative feature learning for unsupervised video summarization. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp 8537\u20138544","DOI":"10.1609\/aaai.v33i01.33018537"},{"issue":"2","key":"1686_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3477538","volume":"18","author":"S-H Zhong","year":"2022","unstructured":"Zhong S-H, Lin J, Lu J, Fares A, Ren T (2022) Deep semantic and attentive network for unsupervised video summarization. ACM Trans Multimed Comput Commun Appl 18(2):1\u201321","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"1686_CR9","doi-asserted-by":"crossref","unstructured":"Apostolidis E, Balaouras G, Mezaris V, Patras I (2022) Summarizing videos using concentrated attention and considering the uniqueness and diversity of the video frames. In: Proceedings of the International Conference on Multimedia Retrieval. pp 407\u2013415","DOI":"10.1145\/3512527.3531404"},{"key":"1686_CR10","doi-asserted-by":"crossref","unstructured":"Abbasi M, Saeedi P (2023) Adopting self-supervised learning into unsupervised video summarization through restorative score. In: Proceedings of the IEEE International Conference on Image Processing. pp 425\u2013429","DOI":"10.1109\/ICIP49359.2023.10222350"},{"key":"1686_CR11","doi-asserted-by":"crossref","unstructured":"Li H, Klabjan D, Utke J (2024) Unsupervised video summarization via iterative training and simplified gan. In: Proceedings of the Asian Conference on Computer Vision. pp 1585\u20131601","DOI":"10.1007\/978-981-96-0966-6_16"},{"key":"1686_CR12","doi-asserted-by":"crossref","unstructured":"Huang J-H (2024) Multi-modal video summarization. In: Proceedings of the International Conference on Multimedia Retrieval. pp 1214\u20131218","DOI":"10.1145\/3652583.3657582"},{"key":"1686_CR13","unstructured":"Narasimhan M, Rohrbach A, Darrell T (2021) Clip-it! language-guided video summarization. In: Proceedings of Neural Information Processing Systems. pp 13988\u201314000"},{"key":"1686_CR14","doi-asserted-by":"crossref","unstructured":"Li H, Ke Q, Gong M, Drummond T (2023) Progressive video summarization via multimodal self-supervised learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp 5584\u20135593","DOI":"10.1109\/WACV56688.2023.00554"},{"key":"1686_CR15","doi-asserted-by":"crossref","unstructured":"He B, Wang J, Qiu J, Bui T, Shrivastava A, Wang Z (2023) Align and attend: multimodal summarization with dual contrastive losses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 14867\u201314878","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"1686_CR16","doi-asserted-by":"crossref","unstructured":"Argaw DM, Yoon S, Heilbron FC, Deilamsalehy H, Bui T, Wang Z, Dernoncourt F, Chung JS (2024) Scaling up video summarization pretraining with large language models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 8332\u20138341","DOI":"10.1109\/CVPR52733.2024.00796"},{"key":"1686_CR17","doi-asserted-by":"crossref","unstructured":"Lee MJ, Gong D, Cho M (2025) Video summarization with large language models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 18981\u201318991","DOI":"10.1109\/CVPR52734.2025.01768"},{"key":"1686_CR18","doi-asserted-by":"crossref","unstructured":"Tian X, Jin Y, Zhang Z, Liu P, Tang X (2024) Mtidnet: a multimodal temporal interest detection network for video summarization. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing. pp 2740\u20132744","DOI":"10.1109\/ICASSP48485.2024.10448236"},{"key":"1686_CR19","doi-asserted-by":"crossref","unstructured":"Otani M, Nakashima Y, Sato T, Yokoya N (2017) Video summarization using textual descriptions for authoring video blogs. Multimed Tools Appl 12097\u201312115","DOI":"10.1007\/s11042-016-4061-3"},{"key":"1686_CR20","doi-asserted-by":"crossref","unstructured":"Jiang H, Mu Y (2022) Joint video summarization and moment localization by cross-task sample transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 16367\u201316377","DOI":"10.1109\/CVPR52688.2022.01590"},{"key":"1686_CR21","doi-asserted-by":"crossref","unstructured":"Chaves J, Tripathi S (2024) Videosage: video summarization with graph representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp 2527\u20132534","DOI":"10.1109\/CVPRW63382.2024.00259"},{"key":"1686_CR22","doi-asserted-by":"crossref","unstructured":"Kim K, Hahm J, Kim S, Sul J, Kim B, Lee J (2025) Summdiff: generative modeling of video summarization with diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 15096\u201315106","DOI":"10.1109\/ICCV51701.2025.01401"},{"key":"1686_CR23","doi-asserted-by":"crossref","unstructured":"Gygli M, Grabner H, Riemenschneider H, Gool L-V (2014) Creating summaries from user videos. In: Proceedings of the European Conference on Computer Vision. pp 505\u2013520","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"1686_CR24","doi-asserted-by":"crossref","unstructured":"Song Y, Vallmitjana J, Stent A, Jaimes A (2015) TVSum: summarizing web videos using titles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 5179\u20135187","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"1686_CR25","doi-asserted-by":"crossref","unstructured":"Terbouche H, Morel M, Rodriguez M, Othmani A (2023) Multi-annotation attention model for video summarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp 3143\u20133152","DOI":"10.1109\/CVPRW59228.2023.00316"},{"key":"1686_CR26","unstructured":"Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, Almeida D, Altenschmidt J, Altman S, Anadkat S et al (2023) Gpt-4 technical report. arXiv preprint. arXiv:2303.08774"},{"key":"1686_CR27","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E Azhar F et al (2023) Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"1686_CR28","unstructured":"Team G, Anil R, Borgeaud S, Wu Y, Alayrac J-B, Yu J, Soricut R, Schalkwyk J, Dai AM, Hauth A et al (2023) Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805"},{"key":"1686_CR29","doi-asserted-by":"crossref","unstructured":"Yoo KM, Park D, Kang J, Lee S-W, Park W (2021) GPT3Mix: leveraging large-scale language models for text augmentation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp 2225\u20132239","DOI":"10.18653\/v1\/2021.findings-emnlp.192"},{"key":"1686_CR30","doi-asserted-by":"crossref","unstructured":"Meng Y, Huang J, Zhang Y, Han J (2022) Generating training data with language models: towards zero-shot language understanding. In: Proceedings of Neural Information Processing Systems. pp 462\u2013477","DOI":"10.52202\/068431-0034"},{"key":"1686_CR31","doi-asserted-by":"publisher","first-page":"2555","DOI":"10.1609\/aaai.v37i2.25353","volume":"37","author":"J Wang","year":"2023","unstructured":"Wang J, Chan KC, Loy CC (2023) Exploring clip for assessing the look and feel of images. Proceedings of the AAAI Conference on Artificial Intelligence 37:2555\u20132563","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1686_CR32","doi-asserted-by":"crossref","unstructured":"Zhao Y, Misra I, Kr\u00e4henb\u00fchl P, Girdhar R (2023) Learning video representations from large language models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 6586\u20136597","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"1686_CR33","doi-asserted-by":"crossref","unstructured":"Yamanishi H, Xiao L, Yamasaki T (2024) Llava-tour: A large multimodal model for Japanese tourist spot prediction and review generation. In: Proceedings of the IEEE International Conference on Visual Communications and Image Processing. pp 1\u20135","DOI":"10.1109\/VCIP63160.2024.10849859"},{"key":"1686_CR34","doi-asserted-by":"crossref","unstructured":"Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y (2022) Large language models are zero-shot reasoners. In: Proceedings of Neural Information Processing Systems. pp 22199\u201322213","DOI":"10.52202\/068431-1613"},{"key":"1686_CR35","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A (2020) Language models are few-shot learners. In: Proceedings of Neural Information Processing Systems. pp 1877\u20131901"},{"key":"1686_CR36","doi-asserted-by":"crossref","unstructured":"Sugihara T, Masuda S, Xiao L, Yamasaki T (2024) Language-guided self-supervised video summarization using text semantic matching considering the diversity of the video. In: Proceedings of the ACM International Conference on Multimedia in Asia. pp 801\u2013806","DOI":"10.1145\/3696409.3700273"},{"key":"1686_CR37","unstructured":"Gong Y, Liu X (2000) Video summarization using singular value decomposition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 174\u2013180"},{"issue":"2","key":"1686_CR38","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1109\/TCSVT.2004.841694","volume":"15","author":"C-W Ngo","year":"2005","unstructured":"Ngo C-W, Ma Y-F, Zhang H-J (2005) Video summarization and scene detection by graph modeling. IEEE Trans Circuits Syst Video Technol 15(2):296\u2013305","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"1686_CR39","doi-asserted-by":"crossref","unstructured":"Lagani\u00e8re R, Bacco R, Hocevar A, Lambert P, Pa\u00efs G, Ionescu BE (2008) Video summarization from spatio-temporal features. In: Proceedings of the ACM International Conference on Multimedia Workshops. pp 144\u2013148","DOI":"10.1145\/1463563.1463590"},{"key":"1686_CR40","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1109\/TIP.2022.3146012","volume":"31","author":"M Ma","year":"2022","unstructured":"Ma M, Mei S, Wan S, Wang Z, Hua X-S, Feng DD (2022) Graph convolutional dictionary selection with l 2p norm for video summarization. IEEE Trans Image Process 31:1789\u20131804","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"1686_CR41","doi-asserted-by":"publisher","first-page":"3967","DOI":"10.1109\/TCSVT.2020.3044600","volume":"31","author":"M Ma","year":"2021","unstructured":"Ma M, Mei S, Wan S, Wang Z, Feng DD, Bennamoun M (2021) Similarity based block sparse subset selection for video summarization. IEEE Trans Circuits Syst Video Technol 31(10):3967\u20133980","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"1686_CR42","doi-asserted-by":"crossref","unstructured":"Zhang K, Chao W-L, Sha F, Grauman K (2016) Summary transfer: exemplar-based subset selection for video summarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 1059\u20131067","DOI":"10.1109\/CVPR.2016.120"},{"key":"1686_CR43","first-page":"2069","volume":"27","author":"B Gong","year":"2014","unstructured":"Gong B, Chao W-L, Grauman K, Sha F (2014) Diverse sequential subset selection for supervised video summarization. Proc Neural Inf Proc Syst 27:2069\u20132077","journal-title":"Proc Neural Inf Proc Syst"},{"issue":"8","key":"1686_CR44","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"issue":"5","key":"1686_CR45","first-page":"2793","volume":"44","author":"B Zhao","year":"2021","unstructured":"Zhao B, Li H, Lu X, Li X (2021) Reconstructive sequence-graph network for video summarization. IEEE Trans Pattern Anal Mach Intell 44(5):2793\u20132801","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1686_CR46","doi-asserted-by":"crossref","unstructured":"Wang H, Zhou B, Zhang Z, Du Y, Ho D, Wong K-F (2024) M3sum: A novel unsupervised language-guided video summarization. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing. pp 4140\u20134144","DOI":"10.1109\/ICASSP48485.2024.10447504"},{"key":"1686_CR47","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu H, Luo D (2023) Self-supervised video summarization guided by semantic inverse optimal transport. In: Proceedings of the ACM International Conference on Multimedia. pp 6611\u20136622","DOI":"10.1145\/3581783.3612087"},{"key":"1686_CR48","doi-asserted-by":"crossref","unstructured":"Huynh-Lam H-D, Ho-Thi N-P, Tran M-T, Le T-N (2023) Cluster-based video summarization with temporal context awareness. In: Pacific-Rim Symposium on Image and Video Technology. pp 15\u201328","DOI":"10.1007\/978-981-97-0376-0_2"},{"key":"1686_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2024.104200","volume":"102","author":"J Gunuganti","year":"2024","unstructured":"Gunuganti J, Yeh Z-T, Wang J-H, Norouzi M (2024) Unsupervised video summarization with adversarial graph-based attention network. J Vis Commun Image Represent 102:104200","journal-title":"J Vis Commun Image Represent"},{"key":"1686_CR50","doi-asserted-by":"crossref","unstructured":"Otani M, Nakashima Y, Rahtu E, Heikkila J (2019) Rethinking the evaluation of video summaries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 7596\u20137604","DOI":"10.1109\/CVPR.2019.00778"},{"key":"1686_CR51","doi-asserted-by":"crossref","unstructured":"Lee H, Lee G (2019) Summarizing long-length videos with gan-enhanced audio\/visual features. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp 3727\u20133731","DOI":"10.1109\/ICCVW.2019.00462"},{"key":"1686_CR52","doi-asserted-by":"crossref","unstructured":"Zhong M, Liu P, Chen Y, Wang D, Qiu X, Huang X (2020) Extractive summarization as text matching. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. pp 6197\u20136208","DOI":"10.18653\/v1\/2020.acl-main.552"},{"key":"1686_CR53","doi-asserted-by":"crossref","unstructured":"Xu S, Zhang X, Wu Y, Wei F (2022) Sequence level contrastive learning for text summarization. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp 11556\u201311565","DOI":"10.1609\/aaai.v36i10.21409"},{"key":"1686_CR54","doi-asserted-by":"crossref","unstructured":"Sosea T, Zhan H, Li JJ, Caragea C (2023) Unsupervised extractive summarization of emotion triggers. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. pp 9550\u20139569","DOI":"10.18653\/v1\/2023.acl-long.531"},{"key":"1686_CR55","doi-asserted-by":"crossref","unstructured":"Liu Y, Lapata M (2019) Text summarization with pretrained encoders. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing. pp 3730\u20133740","DOI":"10.18653\/v1\/D19-1387"},{"key":"1686_CR56","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. pp 7871\u20137880","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"1686_CR57","doi-asserted-by":"crossref","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics. pp 7871\u20137880","DOI":"10.18653\/v1\/N19-1423"},{"key":"1686_CR58","doi-asserted-by":"crossref","unstructured":"Bromley J, Guyon I, LeCun Y, Sackinger E, Shah R (1994) Signature verification using a \"siamese\" time delay neural network. In: Proceedings of Neural Information Processing Systems, pp 737\u2013744","DOI":"10.1142\/9789812797926_0003"},{"key":"1686_CR59","unstructured":"OpenAI (2025) Update to GPT-5 System Card: GPT-5.2. Accessed: 2026\u201301-20. https:\/\/cdn.openai.com\/pdf\/3a4153c8-c748-4b71-8e31-aecbde944f8d\/oai_5_2_system-card.pdf"},{"key":"1686_CR60","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Proceedings of Neural Information Processing Systems, pp 5998\u20136008"},{"key":"1686_CR61","unstructured":"Zhao WX, Zhou K, Li J, Tang T, Wang X, Hou Y, Min Y, Zhang B, Zhang J, Dong Z, et al. (2023) A survey of large language models. arXiv preprint arXiv:2303.18223"},{"key":"1686_CR62","doi-asserted-by":"crossref","unstructured":"Tam D, Mascarenhas A, Zhang S, Kwan S, Bansal M, Raffel C (2023) Evaluating the factual consistency of large language models through news summarization. In: Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics. pp 5220\u20135255","DOI":"10.18653\/v1\/2023.findings-acl.322"},{"key":"1686_CR63","doi-asserted-by":"crossref","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Xia F, Le CE, Zhou QV, D (2022) Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of Neural Information Processing Systems. pp 24824\u201324837","DOI":"10.52202\/068431-1800"},{"key":"1686_CR64","unstructured":"Wang J, Yang Z, Hu X, Li L, Lin K, Gan Z, Liu Z, Liu C, Wang L (2022) GIT: a generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100"},{"key":"1686_CR65","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1686_CR66","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M (2009) Imagenet large scale visual recognition challenge. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 248\u2013255"},{"key":"1686_CR67","doi-asserted-by":"crossref","unstructured":"Potapov D, Douze M, Harchaoui Z, Schmid C (2014) Category-specific video summarization. In: Proceedings of the European Conference on Computer Vision. pp 540\u2013555","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"1686_CR68","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. pp 3982\u20133992","DOI":"10.18653\/v1\/D19-1410"},{"key":"1686_CR69","doi-asserted-by":"crossref","unstructured":"Wei H, Ni B, Yan Y, Yu H, Yang X, Yao C (2018) Video summarization via semantic attended networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 216\u2013223","DOI":"10.1609\/aaai.v32i1.11297"},{"key":"1686_CR70","doi-asserted-by":"crossref","unstructured":"Adams G, Fabbri A, Ladhak F, Lehman E, Elhadad N (2023) From sparse to dense: GPT-4 summarization with chain of density prompting. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing Workshops. pp 68\u201374","DOI":"10.18653\/v1\/2023.newsum-1.7"},{"issue":"3","key":"1686_CR71","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1093\/biomet\/33.3.239","volume":"33","author":"MG Kendall","year":"1945","unstructured":"Kendall MG (1945) The treatment of ties in ranking problems. Biometrika 33(3):239\u2013251","journal-title":"Biometrika"},{"key":"1686_CR72","doi-asserted-by":"crossref","unstructured":"Zwillinger D, Kokoska S (1999) CRC standard probability and statistics tables and formulae. CRC Press","DOI":"10.1201\/9780367802417"},{"key":"1686_CR73","unstructured":"Yang A, Yu B, Li C, Liu D, Huang F, Huang H, Jiang J, Tu J, Zhang J, Zhou J, Lin J, Dang K, Yang K, Yu L, Li M, Sun M, Zhu Q, Men R, He T, Xu W, Yin W, Yu W, Qiu X, Ren X, Yang X, Li Y, Xu Z, Zhang Z (2025) Qwen 2.5-1m technical report. arXiv preprint arXiv:2501.15383"},{"key":"1686_CR74","unstructured":"Hurst A, Lerer A, Goucher AP, Perelman A, Ramesh A, Clark A, Ostrow A, Welihinda A, Hayes A, Radford A et al (2024) Gpt-4o system card. arXiv preprint arXiv:2410.21276"},{"key":"1686_CR75","unstructured":"Vyas A, Katharopoulos A, Fleuret F (2020) Fast transformers with clustered attention. In: Proceedings of Neural Information Processing Systems. pp 21665\u201321674"},{"key":"1686_CR76","doi-asserted-by":"crossref","unstructured":"Kendall A, Gal Y, Cipolla R (2018) Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 7482\u20137491","DOI":"10.1109\/CVPR.2018.00781"},{"key":"1686_CR77","unstructured":"Yang A, Li A, Yang B, Zhang B, Hui B, Zheng B, Yu B, Gao C, Huang C, Lv C et al. (2025) Qwen3 technical report. arXiv preprint arXiv:2505.09388"},{"key":"1686_CR78","first-page":"40542","volume":"36","author":"J Sul","year":"2023","unstructured":"Sul J, Han J, Lee J (2023) Mr. hisum: a large-scale dataset for video highlight detection and summarization. Proc Neural Inf Process Syst 36:40542\u201340555","journal-title":"Proc Neural Inf Process Syst"},{"key":"1686_CR79","first-page":"56615","volume":"36","author":"Z Khan","year":"2023","unstructured":"Khan Z, Bg VK, Schulter S, Chandraker M, Fu Y (2023) Exploring question decomposition for zero-shot vqa. Proc Neural Inf Process Syst 36:56615\u201356627","journal-title":"Proc Neural Inf Process Syst"},{"key":"1686_CR80","doi-asserted-by":"crossref","unstructured":"Ma F, Zhou Y, Zhang Y, Wu S, Zhang Z, He Z, Rao F, Sun X (2024) Task navigator: decomposing complex tasks for multimodal large language models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp 2248\u20132257","DOI":"10.1109\/CVPRW63382.2024.00230"},{"key":"1686_CR81","unstructured":"Li J, Li D, Savarese S, Hoi S (2023) Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the International Conference on Machine Learning, pp 19730\u201319742"},{"key":"1686_CR82","unstructured":"Liu Y (2019) Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"1686_CR83","unstructured":"Abu-El-Haija S, Kothari N, Lee J, Natsev P, Toderici G, Varadarajan B, Vijayanarasimhan S (2016) Youtube-8m: a large-scale video classification benchmark. arXiv preprint arXiv:1609.08675"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01686-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-026-01686-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01686-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T11:19:52Z","timestamp":1790075992000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-026-01686-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":83,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["1686"],"URL":"https:\/\/doi.org\/10.1007\/s10044-026-01686-z","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"assertion":[{"value":"6 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"123"}}