{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:43:08Z","timestamp":1784738588078,"version":"3.55.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585761","type":"print"},{"value":"9783030585778","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58577-8_20","type":"book-chapter","created":{"date-parts":[[2020,9,23]],"date-time":"2020-09-23T14:04:27Z","timestamp":1600869867000},"page":"322-339","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":406,"title":["Not only Look, But Also Listen: Learning Multimodal Violence Detection Under Weak Supervision"],"prefix":"10.1007","author":[{"given":"Peng","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujia","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujia","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangtao","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,9,24]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: Advances in Neural Information Processing Systems (NIPS), pp. 892\u2013900 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"20_CR2","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: See, hear, and read: deep aligned representations. arXiv preprint arXiv:1706.00932 (2017)"},{"key":"20_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 (CVPR), pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"issue":"17","key":"20_CR4","doi-asserted-by":"publisher","first-page":"7379","DOI":"10.1007\/s11042-014-1984-4","volume":"74","author":"CH Demarty","year":"2015","unstructured":"Demarty, C.H., Penet, C., Soleymani, M., Gravier, G.: 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)","journal-title":"Multimedia Tools Appl."},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"20_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-642-12842-4_13","volume-title":"Artificial Intelligence: Theories, Models and Applications","author":"T Giannakopoulos","year":"2010","unstructured":"Giannakopoulos, T., Makris, A., Kosmopoulos, D., Perantonis, S., Theodoridis, S.: Audio-visual fusion for detecting violent scenes in videos. In: Konstantopoulos, S., Perantonis, S., Karkaletsis, V., Spyropoulos, C.D., Vouros, G. (eds.) SETN 2010. LNCS (LNAI), vol. 6040, pp. 91\u2013100. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-12842-4_13"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T., Pikrakis, A., Theodoridis, S.: A multi-class audio classification method with respect to violent content in movies using Bayesian networks. In: IEEE 9th Workshop on Multimedia Signal Processing, pp. 90\u201393. IEEE (2007)","DOI":"10.1109\/MMSP.2007.4412825"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T., Pikrakis, A., Theodoridis, S.: A multimodal approach to violence detection in video sharing sites. In: 20th International Conference on Pattern Recognition (ICPR), pp. 3244\u20133247. IEEE (2010)","DOI":"10.1109\/ICPR.2010.793"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3497\u20133506 (2019)","DOI":"10.1109\/CVPR.2019.00361"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: Ava: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"20_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-030-11012-3_24","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"A Hanson","year":"2019","unstructured":"Hanson, A., PNVR, K., Krishnagopal, S., Davis, L.: Bidirectional convolutional LSTM for the detection of violence in videos. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 280\u2013295. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_24"},{"key":"20_CR14","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 (CVPR), pp. 733\u2013742 (2016)","DOI":"10.1109\/CVPR.2016.86"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Hassner, T., Itcher, Y., Kliper-Gross, O.: Violent flows: real-time detection of violent crowd behavior. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 1\u20136. IEEE (2012)","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Kazakos, E., Nagrani, A., Zisserman, A., Damen, D.: Epic-fusion: audio-visual temporal binding for egocentric action recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 5492\u20135501 (2019)","DOI":"10.1109\/ICCV.2019.00559"},{"key":"20_CR20","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Li, G., Muller, M., Thabet, A., Ghanem, B.: DeepGCNs: can GCNs go as deep as CNNs? In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 9267\u20139276 (2019)","DOI":"10.1109\/ICCV.2019.00936"},{"key":"20_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1007\/978-3-642-10467-1_84","volume-title":"Advances in Multimedia Information Processing - PCM 2009","author":"J Lin","year":"2009","unstructured":"Lin, J., Wang, W.: Weakly-supervised violence detection in movies with audio and video based co-training. In: Muneesawang, P., Wu, F., Kumazawa, I., Roeksabutr, A., Liao, M., Tang, X. (eds.) PCM 2009. LNCS, vol. 5879, pp. 930\u2013935. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-10467-1_84"},{"key":"20_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-46478-7_1","volume-title":"Computer Vision \u2013 ECCV 2016","author":"S Mohammadi","year":"2016","unstructured":"Mohammadi, S., Perina, A., Kiani, H., Murino, V.: Angry crowds: detecting violent events in videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 3\u201318. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_1"},{"key":"20_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1007\/978-3-642-23678-5_39","volume-title":"Computer Analysis of Images and Patterns","author":"E Bermejo Nievas","year":"2011","unstructured":"Bermejo Nievas, E., Deniz Suarez, O., Bueno Garc\u00eda, G., Sukthankar, R.: Violence detection in video using computer vision techniques. In: Real, P., Diaz-Pernil, D., Molina-Abril, H., Berciano, A., Kropatsch, W. (eds.) CAIP 2011. LNCS, vol. 6855, pp. 332\u2013339. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-23678-5_39"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Oh, T.H., et al.: Speech2face: learning the face behind a voice. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7539\u20137548 (2019)","DOI":"10.1109\/CVPR.2019.00772"},{"key":"20_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/978-3-030-01225-0_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Paul","year":"2018","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 588\u2013607. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_35"},{"key":"20_CR27","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: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8276\u20138280. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682833"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Penet, C., Demarty, C.H., Gravier, G., Gros, P.: Multimodal information fusion and temporal integration for violence detection in movies. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2393\u20132396. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6288397"},{"key":"20_CR29","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), pp. 2662\u20132666. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683676"},{"key":"20_CR30","unstructured":"Sch\u00f6lkopf, B., Williamson, R.C., Smola, A.J., Shawe-Taylor, J., Platt, J.C.: Support vector method for novelty detection. In: Advances in Neural Information Processing Systems (NIPS), pp. 582\u2013588 (2000)"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T.H., Kim, J., Yang, M.H., So Kweon, I.: Learning to localize sound source in visual scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4358\u20134366 (2018)","DOI":"10.1109\/CVPR.2018.00458"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12026\u201312035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Singh, A., Patil, D., Omkar, S.: Eye in the sky: real-time drone surveillance system (DSS) for violent individuals identification using scatternet hybrid deep learning network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1629\u20131637 (2018)","DOI":"10.1109\/CVPRW.2018.00214"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Lanz, O.: Learning to detect violent videos using convolutional long short-term memory. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"20_CR35","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 (CVPR), pp. 6479\u20136488 (2018)","DOI":"10.1109\/CVPR.2018.00678"},{"key":"20_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-01252-6_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Sun","year":"2018","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-centric relation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 335\u2013351. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_20"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"20_CR38","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"20_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-01228-1_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413\u2013431. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_25"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Wu, P., Liu, J., Li, M., Sun, Y., Shen, F.: Fast sparse coding networks for anomaly detection in videos. Pattern Recogn. 107515 (2020)","DOI":"10.1016\/j.patcog.2020.107515"},{"key":"20_CR43","first-page":"2609","volume":"31","author":"P Wu","year":"2019","unstructured":"Wu, P., Liu, J., Shen, F.: A deep one-class neural network for anomalous event detection in complex scenes. IEEE Trans. Neural Networks Learn. Syst. 31, 2609\u20132622 (2019)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI Conference on Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"20_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/978-3-030-01264-9_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Yao","year":"2018","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 711\u2013727. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_42"},{"key":"20_CR46","unstructured":"Yue, K., Sun, M., Yuan, Y., Zhou, F., Ding, E., Xu, F.: Compact generalized non-local network. In: Advances in Neural Information Processing Systems (NIPS), pp. 6510\u20136519 (2018)"},{"key":"20_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-540-74936-3_22","volume-title":"Pattern Recognition","author":"C Zach","year":"2007","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L$$^{1}$$ optical flow. In: Hamprecht, F.A., Schn\u00f6rr, C., J\u00e4hne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214\u2013223. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74936-3_22"},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Zajdel, W., Krijnders, J.D., Andringa, T., Gavrila, D.M.: Cassandra: audio-video sensor fusion for aggression detection. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 200\u2013205. IEEE (2007)","DOI":"10.1109\/AVSS.2007.4425310"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7094\u20137103 (2019)","DOI":"10.1109\/ICCV.2019.00719"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Zhong, J.X., Li, N., Kong, W., Liu, S., Li, T.H., Li, G.: Graph convolutional label noise cleaner: train a plug-and-play action classifier for anomaly detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1237\u20131246 (2019)","DOI":"10.1109\/CVPR.2019.00133"},{"key":"20_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58577-8_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:05:48Z","timestamp":1727049948000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58577-8_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585761","9783030585778"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58577-8_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"24 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}