{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:46:14Z","timestamp":1743061574555,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819958467"},{"type":"electronic","value":"9789819958474"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-5847-4_27","type":"book-chapter","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T20:30:00Z","timestamp":1693341000000},"page":"375-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stepwise Fusion Transformer for Affective Video Content Analysis"],"prefix":"10.1007","author":[{"given":"Zeyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,30]]},"reference":[{"issue":"1","key":"27_CR1","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.: LIRIS-accede: a video database for affective content analysis. IEEE Trans. Affect. Comput. 6(1), 43\u201355 (2015)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"27_CR2","unstructured":"Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Chan, C.H., Jones, G.J.: Affect-based indexing and retrieval of films. In: Proceedings of the 13th Annual ACM International Conference on Multimedia, pp. 427\u2013430 (2005)","DOI":"10.1145\/1101149.1101243"},{"key":"27_CR5","unstructured":"Chen, S., Jin, Q.: RUC at mediaeval 2016 emotional impact of movies task: fusion of multimodal features. In: MediaEval, vol. 1739 (2016)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chen, T., Wang, Y., Wang, S., Chen, S.: Exploring domain knowledge for affective video content analyses. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 769\u2013776 (2017)","DOI":"10.1145\/3123266.3123352"},{"key":"27_CR7","unstructured":"Dellandr\u00e9a, E., Chen, L., Baveye, Y., Sj\u00f6berg, M.V., Chamaret, C.: The mediaeval 2016 emotional impact of movies task. In: CEUR Workshop Proceedings (2016)"},{"key":"27_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"45\u201360","key":"27_CR9","first-page":"16","volume":"98","author":"P Ekman","year":"1999","unstructured":"Ekman, P.: Basic emotions. Handbook of Cognition And Emotion 98(45\u201360), 16 (1999)","journal-title":"Handbook of Cognition And Emotion"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"issue":"5","key":"27_CR12","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TCSVT.2020.3014889","volume":"31","author":"Y Ou","year":"2020","unstructured":"Ou, Y., Chen, Z., Wu, F.: Multimodal local-global attention network for affective video content analysis. IEEE Trans. Circuits Syst. Video Technol. 31(5), 1901\u20131914 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"27_CR13","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"6","key":"27_CR14","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. J. Pers. Soc. Psychol. 39(6), 1161 (1980)","journal-title":"J. Pers. Soc. Psychol."},{"key":"27_CR15","unstructured":"Sj\u00f6berg, M., et al.: The mediaeval 2015 affective impact of movies task. In: MediaEval, vol. 1436 (2015)"},{"issue":"24","key":"27_CR16","doi-asserted-by":"publisher","first-page":"8356","DOI":"10.3390\/s21248356","volume":"21","author":"HTP Thao","year":"2021","unstructured":"Thao, H.T.P., Balamurali, B., Roig, G., Herremans, D.: Attendaffectnet-emotion prediction of movie viewers using multimodal fusion with self-attention. Sensors 21(24), 8356 (2021)","journal-title":"Sensors"},{"key":"27_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, B., Hu, W., Wu, O.: Horror video scene recognition via multiple-instance learning. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1325\u20131328. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5946656"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xiang, X., Zhao, J., Deng, X.: P2SL: private-shared subspaces learning for affective video content analysis. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859902"},{"issue":"4","key":"27_CR20","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1109\/TAFFC.2015.2432791","volume":"6","author":"S Wang","year":"2015","unstructured":"Wang, S., Ji, Q.: Video affective content analysis: a survey of state-of-the-art methods. IEEE Trans. Affect. Comput. 6(4), 410\u2013430 (2015)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"10","key":"27_CR21","doi-asserted-by":"publisher","first-page":"13331","DOI":"10.1007\/s11042-018-5662-9","volume":"78","author":"Y Yi","year":"2019","unstructured":"Yi, Y., Wang, H.: Multi-modal learning for affective content analysis in movies. Multimed. Tools App. 78(10), 13331\u201313350 (2019)","journal-title":"Multimed. Tools App."},{"issue":"9","key":"27_CR22","doi-asserted-by":"publisher","first-page":"2454","DOI":"10.1109\/TMM.2019.2955300","volume":"22","author":"Y Yi","year":"2019","unstructured":"Yi, Y., Wang, H., Li, Q.: Affective video content analysis with adaptive fusion recurrent network. IEEE Trans. Multimed. 22(9), 2454\u20132466 (2019)","journal-title":"IEEE Trans. Multimed."},{"key":"27_CR23","unstructured":"Yi, Y., Wang, H., Tang, P.: Unified multi-stage fusion network for affective video content analysis. SSRN 4080629"},{"issue":"2","key":"27_CR24","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/TMM.2006.886310","volume":"9","author":"Z Zeng","year":"2007","unstructured":"Zeng, Z., Tu, J., Liu, M., Huang, T.S., Pianfetti, B., Roth, D., Levinson, S.: Audio-visual affect recognition. IEEE Trans. Multimedia 9(2), 424\u2013428 (2007)","journal-title":"IEEE Trans. Multimedia"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, S., Yao, H., Sun, X., Xu, P., Liu, X., Ji, R.: Video indexing and recommendation based on affective analysis of viewers. In: Proceedings of the 19th ACM International Conference on Multimedia, pp. 1473\u20131476 (2011)","DOI":"10.1145\/2072298.2072043"}],"container-title":["Communications in Computer and Information Science","International Conference on Neural Computing for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-5847-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T20:33:49Z","timestamp":1693341229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-5847-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819958467","9789819958474"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-5847-4_27","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NCAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Computing for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ncaa2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dl2link.com\/ncaa2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"83","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.67","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}