{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:03:43Z","timestamp":1765357423184},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T00:00:00Z","timestamp":1685404800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T00:00:00Z","timestamp":1685404800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. Comput. Sci. Technol."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11390-023-3064-6","type":"journal-article","created":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T10:02:20Z","timestamp":1691488940000},"page":"540-553","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Emotion-Aware Music Driven Movie Montage"],"prefix":"10.1007","volume":"38","author":[{"given":"Wu-Qin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min-Xuan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai-Bin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong-Yang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ming","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang-Sheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,30]]},"reference":[{"key":"3064_CR1","unstructured":"Narasimhan M, Rohrbach A, Darrell T. Clip-it! Language-guided video summarization. In Proc. the 35th International Conference on Neural Information Processing Systems, Dec. 2021, pp.13988\u201314000."},{"key":"3064_CR2","doi-asserted-by":"publisher","unstructured":"Lin J C, Wei W L, Wang H M. EMV-matchmaker: Emotional temporal course modeling and matching for automatic music video generation. In Proc. the 23rd ACM International Conference on Multimedia, Oct. 2015, pp.899\u2013902. https:\/\/doi.org\/10.1145\/2733373.2806359.","DOI":"10.1145\/2733373.2806359"},{"key":"3064_CR3","doi-asserted-by":"publisher","unstructured":"Lin J C, Wei W L, Wang H M. DEMV-matchmaker: Emotional temporal course representation and deep similarity matching for automatic music video generation. In Proc. the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, Mar. 2016, pp.2772\u2013 2776. https:\/\/doi.org\/10.1109\/ICASSP.2016.7472182.","DOI":"10.1109\/ICASSP.2016.7472182"},{"key":"3064_CR4","unstructured":"Murch W. In the Blink of an Eye. Silman-James Press, 2001."},{"key":"3064_CR5","unstructured":"Radford A, Kim J W, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I. Learning transferable visual models from natural language supervision. In Proc. the 38th International Conference on Machine Learning, Jul. 2021, pp.8748\u20138763."},{"issue":"2","key":"3064_CR6","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s11042-008-0225-0","volume":"41","author":"JC Yoon","year":"2009","unstructured":"Yoon J C, Lee I K, Byun S. Automated music video generation using multi-level feature-based segmentation. Multimedia Tools and Applications, 2009, 41(2): 197\u2013214. https:\/\/doi.org\/10.1007\/s11042-008-0225-0.","journal-title":"Multimedia Tools and Applications"},{"key":"3064_CR7","doi-asserted-by":"publisher","unstructured":"Kuo F F, Shan M K, Lee S Y. Background music recommendation for video based on multimodal latent semantic analysis. In Proc. the 2013 IEEE International Conference on Multimedia and Expo, Jul. 2013. https:\/\/doi.org\/10.1109\/ICME.2013.6607444.","DOI":"10.1109\/ICME.2013.6607444"},{"key":"3064_CR8","doi-asserted-by":"publisher","unstructured":"Liao Z C, Yu Y Z, Gong B C, Cheng L C. Audeosynth: Music-driven video montage. ACM Trans. Graphics, 2015, 34(4): Article No. 68. https:\/\/doi.org\/10.1145\/2766966.","DOI":"10.1145\/2766966"},{"key":"3064_CR9","doi-asserted-by":"publisher","unstructured":"Wang J C, Yang Y H, Jhuo I H, Lin Y Y, Wang H M. The acousticvisual emotion Guassians model for automatic generation of music video. In Proc. the 20th ACM International Conference on Multimedia, Oct. 2012, pp.1379\u20131380. https:\/\/doi.org\/10.1145\/2393347.2396494.","DOI":"10.1145\/2393347.2396494"},{"key":"3064_CR10","doi-asserted-by":"publisher","unstructured":"Lin J C, Wei W L, Wang H M. Automatic music video generation based on emotion-oriented pseudo song prediction and matching. In Proc. the 24th ACM International Conference on Multimedia, Oct. 2016, pp.372\u2013376. https:\/\/doi.org\/10.1145\/2964284.2967245.","DOI":"10.1145\/2964284.2967245"},{"key":"3064_CR11","doi-asserted-by":"publisher","unstructured":"Lin J C, Wei W L, Yang J, Wang H M, Liao H Y M. Automatic music video generation based on simultaneous soundtrack recommendation and video editing. In Proc. the 25th ACM International Conference on Multimedia, Oct. 2017, pp.519\u2013527. https:\/\/doi.org\/10.1145\/3123266.3123399.","DOI":"10.1145\/3123266.3123399"},{"key":"3064_CR12","unstructured":"Gross S, Wei X X, Zhu J. Automatic realistic music video generation from segments of YouTube videos. arXiv: 1905. 12245, 2019. https:\/\/arxiv.org\/abs\/1905.12245, Jun. 2023."},{"key":"3064_CR13","doi-asserted-by":"publisher","unstructured":"Liu T C, Kender J R. Optimization algorithms for the selection of key frame sequences of variable length. In Proc. the 7th European Conference on Computer Vision, Apr. 2002, pp.403\u2013417. https:\/\/doi.org\/10.1007\/3-540-47979-1_27.","DOI":"10.1007\/3-540-47979-1_27"},{"key":"3064_CR14","doi-asserted-by":"publisher","unstructured":"Mahmoud K M, Ghanem N M, Ismail M A. Unsupervised video summarization via dynamic modeling-based hierarchical clustering. In Proc. the 12th International Conference on Machine Learning and Applications, Dec. 2013, pp.303\u2013308. https:\/\/doi.org\/10.1109\/ICMLA.2013.140.","DOI":"10.1109\/ICMLA.2013.140"},{"key":"3064_CR15","doi-asserted-by":"publisher","unstructured":"Song Y L, Vallmitjana J, Stent A, Jaimes A. TVSum: Summarizing web videos using titles. In Proc. the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2015, pp.5179\u20135187. https:\/\/doi.org\/10.1109\/CVPR.2015.7299154.","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"3064_CR16","doi-asserted-by":"publisher","unstructured":"Gygli M, Grabner H, Riemenschneider H, Van Gool L. Creating summaries from user videos. In Proc. the 13th European Conference on Computer Vision, Sept. 2014, pp.505\u2013520. https:\/\/doi.org\/10.1007\/978-3-319-10584-0_33.","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"3064_CR17","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1109\/TIP.2020.3039886","volume":"30","author":"WC Zhu","year":"2021","unstructured":"Zhu W C, Lu J W, Li J H, Zhou J. DSNet: A flexible detect-to-summarize network for video summarization. IEEE Trans. Image Processing, 2021, 30: 948\u2013962. https:\/\/doi.org\/10.1109\/TIP.2020.3039886.","journal-title":"IEEE Trans. Image Processing"},{"key":"3064_CR18","doi-asserted-by":"publisher","unstructured":"Sharghi A, Gong B Q, Shah M. Query-focused extractive video summarization. In Proc. the 14th European Conference on Computer Vision, Oct. 2016, pp.3\u201319. https:\/\/doi.org\/10.1007\/978-3-319-46484-8_1.","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"3064_CR19","doi-asserted-by":"publisher","unstructured":"Irie G, Satou T, Kojima A, Yamasaki T, Aizawa K. Automatic trailer generation. In Proc. the 18th ACM International Conference on Multimedia, Oct. 2010, pp.839\u2013842. https:\/\/doi.org\/10.1145\/1873951.1874092.","DOI":"10.1145\/1873951.1874092"},{"key":"3064_CR20","doi-asserted-by":"publisher","unstructured":"Xu H T, Zhen Y, Zha H Y. Trailer generation via a point process-based visual attractiveness model. In Proc. the 24th International Conference on Artificial Intelligence, Jul. 2015, pp.2198\u20132204. https:\/\/doi.org\/10.5555\/2832415.2832554.","DOI":"10.5555\/2832415.2832554"},{"key":"3064_CR21","unstructured":"Papalampidi P, Keller F, Lapata M. Film trailer generation via task decomposition. arXiv: 2111.08774, 2021. https:\/\/arxiv.org\/abs\/2111.08774, Jun. 2023."},{"key":"3064_CR22","doi-asserted-by":"publisher","unstructured":"Smith J R, Joshi D, Huet B, Hsu W, Cota J. Harnessing A I. for augmenting creativity: Application to movie trailer creation. In Proc. the 25th ACM International Conference on Multimedia, Oct. 2017, pp.1799\u20131808. https:\/\/doi.org\/10.1145\/3123266.3127906.","DOI":"10.1145\/3123266.3127906"},{"issue":"3","key":"3064_CR23","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1080\/0929821042000317813","volume":"33","author":"PN Juslin","year":"2004","unstructured":"Juslin P N, Laukka P. Expression, perception, and induction of musical emotions: A review and a questionnaire study of everyday listening. Journal of New Music Research, 2004, 33(3): 217-238. https:\/\/doi.org\/10.1080\/0929821042000317813.","journal-title":"Journal of New Music Research"},{"issue":"38","key":"3064_CR24","doi-asserted-by":"publisher","first-page":"E7900","DOI":"10.1073\/pnas.1702247114","volume":"114","author":"AS Cowen","year":"2017","unstructured":"Cowen A S, Keltner D. Self-report captures 27 distinct categories of emotion bridged by continuous gradients. Proceedings of the National Academy of Sciences of the United States of America, 2017, 114(38): E7900-E7909. https:\/\/doi.org\/10.1073\/pnas.1702247114.","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"3064_CR25","unstructured":"Kim Y E, Schmidt E M, Migneco R, Morton B G, Richardson P, Scott J J, Speck J A, Turnbull D. Music emotion recognition: A state of the art review. In Proc. the 11th International Society for Music Information Retrieval Conference, Aug. 2010, pp.937\u2013952."},{"issue":"6","key":"3064_CR26","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"JA Russell","year":"1980","unstructured":"Russell J A. A circumplex model of affect. Journal of Personality and Social Psychology, 1980, 39(6): 1161\u20131178. https:\/\/doi.org\/10.1037\/h0077714.","journal-title":"Journal of Personality and Social Psychology"},{"key":"3064_CR27","doi-asserted-by":"publisher","unstructured":"Zhao S C, Gao Y, Jiang X L, Yao H X, Chua T S, Sun X S. Exploring principles-of-art features for image emotion recognition. In Proc. the 22nd ACM International Conference on Multimedia, Nov. 2014, pp.47\u201356. https:\/\/doi.org\/10.1145\/2647868.2654930.","DOI":"10.1145\/2647868.2654930"},{"key":"3064_CR28","doi-asserted-by":"publisher","unstructured":"Lu X, Suryanarayan P, Adams Jr R B, Li J, Newman M G, Wang J Z. On shape and the computability of emotions. In Proc. the 20th ACM International Conference on Multimedia, Oct. 2012, pp.229\u2013238. https:\/\/doi.org\/10.1145\/2393347.2393384.","DOI":"10.1145\/2393347.2393384"},{"issue":"1","key":"3064_CR29","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/TAFFC.2015.2396531","volume":"6","author":"Y Baveye","year":"2015","unstructured":"Baveye Y, Dellandrea E, Chamaret C, Chen L M. LIRIS-ACCEDE: A video database for affective content analysis. IEEE Trans. Affective Computing, 2015, 6(1): 43\u201355. https:\/\/doi.org\/10.1109\/TAFFC.2015.2396531.","journal-title":"IEEE Trans. Affective Computing"},{"issue":"1","key":"3064_CR30","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/TMM.2004.840618","volume":"7","author":"A Hanjalic","year":"2005","unstructured":"Hanjalic A, Xu L Q. Affective video content representation and modeling. IEEE Trans. Multimedia, 2005, 7(1): 143\u2013154. https:\/\/doi.org\/10.1109\/TMM.2004.840618.","journal-title":"IEEE Trans. Multimedia"},{"key":"3064_CR31","doi-asserted-by":"publisher","unstructured":"Guzhov A, Raue F, Hees J, Dengel A. Audioclip: Extending clip to image, text and audio. In Proc. the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, pp.976\u2013980. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747631.","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"issue":"2","key":"3064_CR32","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1007\/s11042-020-08836-3","volume":"80","author":"YR Pandeya","year":"2021","unstructured":"Pandeya Y R, Lee J. Deep learning-based late fusion of multimodal information for emotion classification of music video. Multimedia Tools and Applications, 2021, 80(2): 2887\u20132905. https:\/\/doi.org\/10.1007\/s11042-020-08836-3.","journal-title":"Multimedia Tools and Applications"},{"issue":"3","key":"3064_CR33","first-page":"40A","volume":"9","author":"XJ Yu","year":"2017","unstructured":"Yu X J. A study on the editing frequencies trends for films emotion clips. International Journal of Organizational Innovation, 2017, 9(3): 40A\u201347A.","journal-title":"International Journal of Organizational Innovation"},{"key":"3064_CR34","unstructured":"Sou\u010dek T, Loko\u010d J. TransNet V2: An effective deep network architecture for fast shot transition detection. arXiv: 2008.04838, 2020. https:\/\/arxiv.org\/abs\/2008.04838, Jun. 2023."},{"key":"3064_CR35","doi-asserted-by":"publisher","unstructured":"Rao A Y, Xu L N, Xiong Y, Xu G D, Huang Q Q, Zhou B L, Lin D H. A local-to-global approach to multi-modal movie scene segmentation. In Proc. the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp.10146\u201310155. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01016.","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"3064_CR36","doi-asserted-by":"publisher","unstructured":"B\u00f6ck S, Korzeniowski F, Schl\u00fcter J, Krebs F, Widmer G. Madmom: A new python audio and music signal processing library. In Proc. the 24th ACM International Conference on Multimedia, Oct. 2016, pp.1174\u20131178. https:\/\/doi.org\/10.1145\/2964284.2973795..","DOI":"10.1145\/2964284.2973795"},{"key":"3064_CR37","unstructured":"Kingma D P, Ba J. Adam: A method for stochastic optimization. arXiv: 1412.6980, 2014. https:\/\/arxiv.org\/abs\/1412.6980, Jun. 2023."},{"issue":"14","key":"3064_CR38","doi-asserted-by":"publisher","first-page":"4927","DOI":"10.3390\/s21144927","volume":"21","author":"YR Pandeya","year":"2021","unstructured":"Pandeya Y R, Bhattarai B, Lee J. Deep-learning-based multimodal emotion classification for music videos. Sensors, 2021, 21(14): 4927. https:\/\/doi.org\/10.3390\/s21144927.","journal-title":"Sensors"},{"key":"3064_CR39","doi-asserted-by":"publisher","unstructured":"Wu H H, Seetharaman P, Kumar K, Bello J P. Wav2CLIP: Learning robust audio representations from clip. In Proc. the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, pp.4563\u20134567. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747669.","DOI":"10.1109\/ICASSP43922.2022.9747669"}],"container-title":["Journal of Computer Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-023-3064-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11390-023-3064-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-023-3064-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T10:35:02Z","timestamp":1691490902000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11390-023-3064-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,30]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["3064"],"URL":"https:\/\/doi.org\/10.1007\/s11390-023-3064-6","relation":{},"ISSN":["1000-9000","1860-4749"],"issn-type":[{"value":"1000-9000","type":"print"},{"value":"1860-4749","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,30]]},"assertion":[{"value":"29 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}