{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T05:29:14Z","timestamp":1770701354343,"version":"3.49.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T00:00:00Z","timestamp":1609545600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T00:00:00Z","timestamp":1609545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s11227-020-03514-5","type":"journal-article","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T21:13:09Z","timestamp":1609621989000},"page":"6435-6455","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Video reasoning for conflict events through feature extraction"],"prefix":"10.1007","volume":"77","author":[{"given":"Sheng-Tzong","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chih-Wei","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0193-2104","authenticated-orcid":false,"given":"Gwo-Jiun","family":"Horng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ci-Ruei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,2]]},"reference":[{"key":"3514_CR1","unstructured":"Statista (2020) YouTube: hours of video uploaded every minute 2019 | Statistic. [online] Available at: https:\/\/www.statista.com\/statistics\/259477\/hours-of-video-uploaded-to-youtube-every-minute\/ [Accessed 28 May. 2020]"},{"key":"3514_CR2","unstructured":"Omnicoreagency.com Instagram by the Numbers (2020): Stats, Demographics and Fun Facts. [online] Available at: https:\/\/www.omnicoreagency.com\/instagram-statistics\/ [Accessed 28 May. 2020]"},{"key":"3514_CR3","doi-asserted-by":"crossref","unstructured":"Karpathy A et al (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Columbus","DOI":"10.1109\/CVPR.2014.223"},{"key":"3514_CR4","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: advances in neural information processing systems. Montreal"},{"key":"3514_CR5","doi-asserted-by":"crossref","unstructured":"Richard A, Gall J, (2016) Temporal action detection using a statistical language model, Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas","DOI":"10.1109\/CVPR.2016.341"},{"key":"3514_CR6","doi-asserted-by":"crossref","unstructured":"Venugopalan S et al (2015) Sequence to sequence-video to text, Proceedings of the IEEE International conference on computer vision, Santiago","DOI":"10.1109\/ICCV.2015.515"},{"key":"3514_CR7","doi-asserted-by":"crossref","unstructured":"Tapaswi M et al (2016) Movieqa: Understanding stories in movies through question-answering, Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas","DOI":"10.1109\/CVPR.2016.501"},{"key":"3514_CR8","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Su H, Wang C, Yang M (2018) BSN: boundary sensitive network for temporal action proposal generation, proceedings of the European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"3514_CR9","doi-asserted-by":"crossref","unstructured":"Wei J, Wang H, Yi Y, Li Q, Huang D (2019) P3D-CTN: Pseudo-3D convolutional tube network for spatio-temporal action detection in videos, Proceedings of the IEEE International Conference on Image Processing (ICIP)","DOI":"10.1109\/ICIP.2019.8802979"},{"key":"3514_CR10","doi-asserted-by":"crossref","unstructured":"He K et al (2016) Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas","DOI":"10.1109\/CVPR.2016.90"},{"key":"3514_CR11","doi-asserted-by":"crossref","unstructured":"Qiu Z, Ting Y, Tao M (2017) Learning spatio-temporal representation with pseudo-3d residual networks, Proceedings of the IEEE International Conference on Computer Vision, Venice","DOI":"10.1109\/ICCV.2017.590"},{"key":"3514_CR12","doi-asserted-by":"crossref","unstructured":"Rodriguez MD, Ahmed J, Shah M, (2008) Action MACH: A spatio-temporal maximum average correlation height filter for action recognition, in Proc. CVPR\u201908","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"3514_CR13","doi-asserted-by":"crossref","unstructured":"Jhuang H, Gall v, Zuffi S, Schmid C, Black M J (2013) Towards understanding action recognition, in Proc. ICCV\u201913","DOI":"10.1109\/ICCV.2013.396"},{"key":"3514_CR14","unstructured":"Barchiesi D, et al (2014) Acoustic scene classification,:1411.3715\u00a0"},{"issue":"1","key":"3514_CR15","first-page":"142","volume":"23","author":"A Rakotomamonjy","year":"2015","unstructured":"Rakotomamonjy A, Gasso G (2015) Histogram of gradients of time-frequency representations for audio scene classification, IEEE\/ACM transactions on audio. speech and language processing (TASLP) 23(1):142\u2013153","journal-title":"Speech and Language Processing (TASLP)"},{"key":"3514_CR16","doi-asserted-by":"crossref","unstructured":"Salamon J, Bello JP (2015) Unsupervised feature learning for urban sound classification, acoustics, speech and signal processing (ICASSP), 2015 IEEE international conference on, IEEE, Brisbane","DOI":"10.1109\/ICASSP.2015.7177954"},{"issue":"8","key":"3514_CR17","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"},{"key":"3514_CR18","doi-asserted-by":"crossref","unstructured":"Piczak KJ (2015) Environmental sound classification with convolutional neural networks,\u00a02015 IEEE 25th International workshop on machine learning for signal processing (MLSP), Boston","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"3514_CR19","doi-asserted-by":"crossref","unstructured":"Hertel L, Phan H, Mertins A (2016) Comparing time and frequency domain for audio event recognition using deep learning, 2016 IEEE international joint conference on neural networks (IJCNN), Budapest","DOI":"10.1109\/IJCNN.2016.7727635"},{"issue":"3","key":"3514_CR20","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1109\/TASLP.2015.2389618","volume":"23","author":"I McLoughlin","year":"2015","unstructured":"McLoughlin I et al (2015) Robust sound event classification using deep neural networks. IEEE\/ACM Trans audio speech language process 23(3):540\u2013552","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"key":"3514_CR21","volume-title":"Aaron, Sander Dieleman, and Benjamin Schrauwen, \"Deep content-based music recommendation,\"","author":"V den Oord","year":"2013","unstructured":"den Oord V A, Sander D, Schrauwen B (2013) Deep content-based music recommendation advnces in neural information processing systems, stateline"},{"key":"3514_CR22","unstructured":"Hannun AY, Case C, Casper J, Catanzaro B, Diamos G, Elsen E, Prenger R, Satheesh S, Sengupta S, Coates A, Ng AY (2014) Deep speech: scaling up end-to-end speech recognition. arXiv:1412.5567"},{"key":"3514_CR23","volume-title":"Soundnet: Learning sound representations from unlabeled video","author":"Y Aytar","year":"2016","unstructured":"Aytar Y, Vondrick C, Torralba A (2016) Soundnet: learning sound representations from unlabeled video. advances in neural information processing systems, Barcelona"},{"key":"3514_CR24","doi-asserted-by":"crossref","unstructured":"CARUNA R Multitask learning: A knowledge-based source of inductive bias, Proceedings of the 10th International conference in machine learning, Amherst, 1993.","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"issue":"1","key":"3514_CR25","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1007327622663","volume":"28","author":"J Baxter","year":"1997","unstructured":"Baxter J (1997) A Bayesian\/information theoretic model of learning to learn via multiple task sampling. Mach learn 28(1):7\u201339","journal-title":"Mach learn"},{"key":"3514_CR26","doi-asserted-by":"crossref","unstructured":"Duong L et al (2015) Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser, Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th International joint conference on natural language processing (Volume 2: Short Papers), Vol. 2","DOI":"10.3115\/v1\/P15-2139"},{"key":"3514_CR27","unstructured":"Yang Y, Hospedales TM (2017) Trace Norm Regularised Deep Multi-Task Learning. ICLR (Workshop)"},{"key":"3514_CR28","unstructured":"Soomro K, Zamir AR, Shah M (2012) UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402"},{"key":"3514_CR29","volume-title":"\"Hmdb51: A large video database for human motion recognition, High Performance Computing in Science and Engineering \u201812","author":"H Kuehne","year":"2013","unstructured":"Kuehne H et al (2013) Hmdb51: a large video database for human motion recognition, High performance computing in science and engineering 12. Springer, Berlin, Heidelberg"},{"key":"3514_CR30","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, Viola F, Green T, Back T, Natsev Pa, Suleyman M, Zisserman A (2017) The kinetics human action video dataset"},{"key":"3514_CR31","doi-asserted-by":"crossref","unstructured":"Caba Heilbron F et al (2015) Activitynet: a large-scale video benchmark for human activity understanding, Proceedings of the IEEE conference on computer vision and pattern recognition, Boston","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"3514_CR32","doi-asserted-by":"crossref","unstructured":"Krishna R  et al (2017) Dense-Captioning events in videos, Proceedings of the IEEE International conference on computer vision, Venice","DOI":"10.1109\/ICCV.2017.83"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03514-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03514-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03514-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T12:32:26Z","timestamp":1620736346000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03514-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,2]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["3514"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03514-5","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,2]]},"assertion":[{"value":"16 November 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}