{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:44:23Z","timestamp":1781585063399,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819981809","type":"print"},{"value":"9789819981816","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8181-6_16","type":"book-chapter","created":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T23:02:30Z","timestamp":1701039750000},"page":"205-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Violence-MFAS: Audio-Visual Violence Detection Using Multimodal Fusion Architecture Search"],"prefix":"10.1007","author":[{"given":"Dan","family":"Si","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jindi","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiancheng","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,27]]},"reference":[{"key":"16_CR1","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":"16_CR2","doi-asserted-by":"crossref","unstructured":"Du, X., et al.: SpineNet: learning scale-permuted backbone for recognition and localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11592\u201311601 (2020)","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Hanson, A., Pnvr, K., Krishnagopal, S., Davis, L.: Bidirectional convolutional LSTM for the detection of violence in videos. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pp. 0\u20130 (2018)","DOI":"10.1007\/978-3-030-11012-3_24"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A.K., Davis, L.S.: Learning temporal regularity in video sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 733\u2013742 (2016)","DOI":"10.1109\/CVPR.2016.86"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: ICASSP 2017\u20132017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"16_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/978-3-642-25566-3_40","volume-title":"Learning and Intelligent Optimization","author":"F Hutter","year":"2011","unstructured":"Hutter, F., Hoos, H.H., Leyton-Brown, K.: Sequential model-based optimization for general algorithm configuration. In: Coello, C.A.C. (ed.) LION 2011. LNCS, vol. 6683, pp. 507\u2013523. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-25566-3_40"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Li, S., Liu, F., Jiao, L.: Self-training multi-sequence learning with transformer for weakly supervised video anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 1395\u20131403 (2022)","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Progressive neural architecture search. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 19\u201334 (2018)","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Lv, J., Ye, Q., Sun, Y., Zhao, J., Lv, J.: Heart-Darts: classification of heartbeats using differentiable architecture search. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9534184"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Pang, W.F., He, Q.H., Hu, Y.j., Li, Y.X.: Violence detection in videos based on fusing visual and audio information. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2260\u20132264. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413686"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Peixoto, B., Lavi, B., Martin, J.P.P., Avila, S., Dias, Z., Rocha, A.: Toward subjective violence detection in videos. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8276\u20138280. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682833"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-R\u00faa, J.M., Vielzeuf, V., Pateux, S., Baccouche, M., Jurie, F.: MFAS: multimodal fusion architecture search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6966\u20136975 (2019)","DOI":"10.1109\/CVPR.2019.00713"},{"key":"16_CR13","unstructured":"Real, E., et al.: Large-scale evolution of image classifiers. In: International Conference on Machine Learning, pp. 2902\u20132911. PMLR (2017)"},{"key":"16_CR14","unstructured":"Sch\u00f6lkopf, B., Williamson, R.C., Smola, A., Shawe-Taylor, J., Platt, J.: Support vector method for novelty detection. In: Advances in Neural Information Processing Systems, vol. 12 (1999)"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6479\u20136488 (2018)","DOI":"10.1109\/CVPR.2018.00678"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J.W., Carneiro, G.: Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4975\u20134986 (2021)","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"16_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"16_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"16_CR19","doi-asserted-by":"publisher","first-page":"3513","DOI":"10.1109\/TIP.2021.3062192","volume":"30","author":"P Wu","year":"2021","unstructured":"Wu, P., Liu, J.: Learning causal temporal relation and feature discrimination for anomaly detection. IEEE Trans. Image Process. 30, 3513\u20133527 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Wu, P., et al.: Not only look, but also listen: Learning multimodal violence detection under weak supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol. 12375, pp. 322\u2013339. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_20","DOI":"10.1007\/978-3-030-58577-8_20"},{"issue":"7","key":"16_CR21","first-page":"1753","volume":"32","author":"Q Ye","year":"2020","unstructured":"Ye, Q., Sun, Y., Zhang, J., Lv, J.: A distributed framework for EA-based NAS. IEEE Trans. Parallel Distrib. Syst. 32(7), 1753\u20131764 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Yu, J., Liu, J., Cheng, Y., Feng, R., Zhang, Y.: Modality-aware contrastive instance learning with self-distillation for weakly-supervised audio-visual violence detection. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 6278\u20136287 (2022)","DOI":"10.1145\/3503161.3547868"},{"key":"16_CR23","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697\u20138710 (2018)","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8181-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:28:12Z","timestamp":1710329292000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8181-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,27]]},"ISBN":["9789819981809","9789819981816"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8181-6_16","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,27]]},"assertion":[{"value":"27 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","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":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"0","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":"51% - 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":"4.14","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":"2.46","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}