{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:21:18Z","timestamp":1783610478578,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031189128","type":"print"},{"value":"9783031189135","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-18913-5_48","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"623-637","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal Violent Video Recognition Based on Mutual Distillation"],"prefix":"10.1007","author":[{"given":"Yimeng","family":"Shang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"48_CR1","doi-asserted-by":"crossref","unstructured":"Mohammadi, H., Nazerfard, E.: SSHA: Video Violence Recognition and Localization using a Semi-Supervised Hard Attention Model (2022)","DOI":"10.1016\/j.eswa.2022.118791"},{"key":"48_CR2","doi-asserted-by":"publisher","unstructured":"Ding, C., Fan, S., Ming, Z., et al.: Violence detection in video by using 3D convolutional neural networks. In: International Symposium on Visual Computing. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-14364-4_53","DOI":"10.1007\/978-3-319-14364-4_53"},{"key":"48_CR3","doi-asserted-by":"crossref","unstructured":"Samuel, D., Fnil, E., Manogaran, G., et al.: Real time violence detection framework for football stadium comprising of big data analysis and deep learning through bidirectional LSTM. Computer Networks 151(MAR.14), 191\u2013200 (2019)","DOI":"10.1016\/j.comnet.2019.01.028"},{"key":"48_CR4","doi-asserted-by":"publisher","unstructured":"Hanson, A., Pnvr, K., Krishnagopal, S., et al.: Bidirectional Convolutional LSTM for the Detection of Violence in Videos. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_24","DOI":"10.1007\/978-3-030-11012-3_24"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Abdali, A.R.: Data Efficient Video Transformer for Violence Detection. In: 2021 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT). IEEE (2021)","DOI":"10.1109\/COMNETSAT53002.2021.9530829"},{"key":"48_CR6","doi-asserted-by":"publisher","unstructured":"Nievas, E.B., Suarez, O.D., Gloria Bueno Garc\u00eda, et al.: Violence detection in video using computer vision techniques. In: International Conference on Computer Analysis of Images and Patterns. Springer, Berlin, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-23678-5_39","DOI":"10.1007\/978-3-642-23678-5_39"},{"key":"48_CR7","unstructured":"Elesawy, M., Hussein, M., Mina, A.E.M.: https:\/\/www.kaggle.com\/mohamedmustafa\/real-life-violence-situations-dataset"},{"key":"48_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, M., Cai, K., Li, M.: RWF-2000: an open large scale video database for violence detection. In: 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, pp. 4183\u20134190 (2021)","DOI":"10.1109\/ICPR48806.2021.9412502"},{"key":"48_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., et al.: Deep Mutual Learning (2017)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"48_CR10","doi-asserted-by":"crossref","unstructured":"Islam, Z., Rukonuzzaman, M., Ahmed, R., et al.: Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM (2021)","DOI":"10.1109\/IJCNN52387.2021.9534280"},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Xu, Q., See, J., Lin, W.: Localization guided fight action detection in surveillance videos. In: 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE, pp. 568\u2013573 (2019)","DOI":"10.1109\/ICME.2019.00104"},{"key":"48_CR12","unstructured":"Dai, Q., Zhao, R.W., Wu, Z., et al.: Fudan-Huawei at MediaEval 2015: Detecting Violent Scenes and Affective Impact in Movies with Deep Learning (2015)"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Peixoto, B., Lavi, B., Martin, J.P.P., et al.: Toward subjective violence detection in videos. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 8276\u20138280 (2019)","DOI":"10.1109\/ICASSP.2019.8682833"},{"key":"48_CR14","doi-asserted-by":"crossref","unstructured":"Pang, W.F., He, Q.H., Hu, Y., et al.: 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). IEEE, pp. 2260\u20132264 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413686"},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Perez, M., Kot, A.C., Rocha, A.: Detection of real-world fights in surveillance videos. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683676"},{"key":"48_CR16","doi-asserted-by":"crossref","unstructured":"Hassner, T., Itcher, Y., Kliper-Gross, O.: Violent flows: real-time detection of violent crowd behavior. In: Computer Vision & Pattern Recognition Workshops. IEEE (2012)","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"48_CR17","doi-asserted-by":"crossref","unstructured":"Demarty, C.H., et al.: VSD: A public dataset for the detection of violent scenes in movies: design, annotation, analysis and evaluation. Multimedia Tools Appl. 74(17), 7379\u20137404 (2015)","DOI":"10.1007\/s11042-014-1984-4"},{"key":"48_CR18","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":"48_CR19","doi-asserted-by":"publisher","unstructured":"Wu, P., Liu, J., Shi, Y., et al.: Not only look, but also listen: Learning multimodal violence detection under weak supervision. In: European Conference on Computer Vision. Springer, Cham, pp. 322\u2013339 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_20","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"48_CR20","doi-asserted-by":"crossref","unstructured":"Halder, R., Chatterjee, R.: CNN-BiLSTM model for violence detection in smart surveillance. SN Computer Sci. 1(4), 1\u20139 (2020)","DOI":"10.1007\/s42979-020-00207-x"},{"key":"48_CR21","unstructured":"Sargana, A.B.: Fast learning through deep multi-net CNN model for violence recognition in video surveillance. The Computer Journal (2020)"},{"key":"48_CR22","doi-asserted-by":"crossref","unstructured":"Song, W., Zhang, D., Zhao, X., et al.: A novel violent video detection scheme based on modified 3d convolutional neural networks. IEEE Access, pp. 39172\u201339179 (2019)","DOI":"10.1109\/ACCESS.2019.2906275"},{"key":"48_CR23","doi-asserted-by":"crossref","unstructured":"Xu, X., Wu, X., Wang, G., et al.: Violent video classification based on spatial-temporal cues using deep learning. In: 2018 11th International Symposium on Computational Intelligence and Design (ISCID) (2018)","DOI":"10.1109\/ISCID.2018.00079"},{"key":"48_CR24","doi-asserted-by":"crossref","unstructured":"Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans. Pattern Analysis Machine Intell. 43(11), 4037\u20134058 (2020)","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"48_CR25","unstructured":"Alwassel, H., Mahajan, D., Torresani, L., et al.: Self-Supervised Learning by Cross-Modal Audio-Video Clustering (2019)"},{"key":"48_CR26","doi-asserted-by":"crossref","unstructured":"Morgado, P., Vasconcelos, N., Misra, I.: Audio-Visual Instance Discrimination with Cross-Modal Agreement (2020)","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"48_CR27","unstructured":"Sarkar, P., Etemad, A.: Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Temporal Synchronicity (2021)"},{"key":"48_CR28","unstructured":"Alayrac, J.B., Recasens, A., Schneider, R., et al.: Self-Supervised MultiModal Versatile Networks (2020)"},{"issue":"7","key":"48_CR29","first-page":"38","volume":"14","author":"G Hinton","year":"2015","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Computer Science 14(7), 38\u201339 (2015)","journal-title":"Computer Science"},{"key":"48_CR30","unstructured":"Kay, W., Carreira, J., Simonyan, K., et al.: The Kinetics Human Action Video Dataset (2017)"},{"key":"48_CR31","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., Ellis, D., Freedman, D., et al.: AudioSet: an ontology and human-labeled dataset for audio events. In: IEEE International Conference on Acoustics. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"48_CR32","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: Temporal Shift Module for Efficient Video Understanding (2018)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"48_CR33","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","volume":"28","author":"Q Kong","year":"2020","unstructured":"Kong, Q., Cao, Y., Iqbal, T., et al.: Panns: Large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Trans. Audio, Speech, Language Process. 28, 2880\u20132894 (2020)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Language Process."},{"key":"48_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., et al.: ECA-Net: Efficient channel attention for deep convolutional neural networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"48_CR35","unstructured":"Du, T., Wang, H., Torresani, L., et al.: A closer look at spatiotemporal convolutions for action recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2018)"},{"key":"48_CR36","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., et al.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"48_CR37","doi-asserted-by":"crossref","unstructured":"Liu, H.: Violence recognition based on auditory-visual fusion of autoencoder mapping. Electronics 10(21), 2654 (2021)","DOI":"10.3390\/electronics10212654"},{"key":"48_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zhong, W., Ye, L., et al.: Violent scene detection of film videos based on multi-task learning of temporal-spatial features. In: 2021 IEEE 4th International Conference on Multimedia Information Processing and Retrieval (MIPR). IEEE, pp. 360\u2013365 (2021)","DOI":"10.1109\/MIPR51284.2021.00067"},{"key":"48_CR39","doi-asserted-by":"publisher","first-page":"85958","DOI":"10.1109\/ACCESS.2020.2992617","volume":"8","author":"C Gu","year":"2020","unstructured":"Gu, C., Wu, X., Wang, S.: Violent video detection based on semantic correspondence. IEEE Access 8, 85958\u201385967 (2020)","journal-title":"IEEE Access"},{"issue":"5","key":"48_CR40","first-page":"10","volume":"28","author":"X Wu","year":"2020","unstructured":"Wu, X., Gu, C., Wang, S.: Multi-modal feature fusion and multi-task learning for special video classification. Opt. Precis. Eng. 28(5), 10 (2020)","journal-title":"Opt. Precis. Eng."},{"key":"48_CR41","first-page":"1","volume-title":"Research on Violent Video Recognition based on Multi-Modal Feature and Multi-Task Learning","author":"C Gu","year":"2021","unstructured":"Gu, C.: Research on Violent Video Recognition based on Multi-Modal Feature and Multi-Task Learning, pp. 1\u201353. Library of Communication University of China, Beijing (2021)"},{"key":"48_CR42","doi-asserted-by":"publisher","unstructured":"Liu, R., Wu, X.: Multimodal attention network for violence detection. In: 2022 2nd International Conference on Consumer Electronics and Computer Engineering (ICCECE), pp. 503\u2013506 (2022). https:\/\/doi.org\/10.1109\/ICCECE54139.2022.9712676","DOI":"10.1109\/ICCECE54139.2022.9712676"},{"key":"48_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/978-3-030-01216-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Tian","year":"2018","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 252\u2013268. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_16"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18913-5_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:29:19Z","timestamp":1666826959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18913-5_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189128","9783031189135"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18913-5_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","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":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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)"}}]}}