{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:51:50Z","timestamp":1784904710175,"version":"3.55.0"},"publisher-location":"Cham","reference-count":70,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585792","type":"print"},{"value":"9783030585808","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\/978-3-030-58580-8_26","type":"book-chapter","created":{"date-parts":[[2020,12,2]],"date-time":"2020-12-02T07:03:09Z","timestamp":1606892589000},"page":"436-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":121,"title":["Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video\u00a0Parsing"],"prefix":"10.1007","author":[{"given":"Yapeng","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingzeyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,12,3]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"26_CR2","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, pp. 892\u2013900 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"issue":"4","key":"26_CR3","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.conb.2006.06.008","volume":"16","author":"DA Bulkin","year":"2006","unstructured":"Bulkin, D.A., Groh, J.M.: Seeing sounds: visual and auditory interactions in the brain. Current Opinion Neurobiol. 16(4), 415\u2013419 (2006)","journal-title":"Current Opinion Neurobiol."},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chorowski, J., Jaitly, N.: Towards better decoding and language model integration in sequence to sequence models. arXiv preprint arXiv:1612.02695 (2016)","DOI":"10.21437\/Interspeech.2017-343"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Chou, S.Y., Jang, J.S.R., Yang, Y.H.: Learning to recognize transient sound events using attentional supervision. In: IJCAI, pp. 3336\u20133342 (2018)","DOI":"10.24963\/ijcai.2018\/463"},{"key":"26_CR7","unstructured":"Elizalde, B., et al.: Experiments on the dcase challenge 2016: acoustic scene classification and sound event detection in real life recording. arXiv preprint arXiv:1607.06706 (2016)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. arXiv preprint arXiv:1804.03619 (2018)","DOI":"10.1145\/3197517.3201357"},{"issue":"11","key":"26_CR9","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.1109\/TPAMI.2013.65","volume":"35","author":"A Gaidon","year":"2013","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Temporal localization of actions with actoms. IEEE Trans. Pattern Anal. Mach. Intell. 35(11), 2782\u20132795 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Gan, C., Huang, D., Zhao, H., Tenenbaum, J.B., Torralba, A.: Music gesture for visual sound separation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10478\u201310487 (2020)","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 35\u201353 (2018)","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: 2.5 D visual sound. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 324\u2013333 (2019)","DOI":"10.1109\/CVPR.2019.00041"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: Co-separating sounds of visual objects. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3879\u20133888 (2019)","DOI":"10.1109\/ICCV.2019.00398"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: action recognition by previewing audio. arXiv preprint arXiv:1912.04487 (2019)","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"26_CR15","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":"26_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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"26_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-4722-2013-1","volume":"2013","author":"T Heittola","year":"2013","unstructured":"Heittola, T., Mesaros, A., Eronen, A., Virtanen, T.: Context-dependent sound event detection. EURASIP J. Audio Speech Music Process. 2013(1), 1 (2013)","journal-title":"EURASIP J. Audio Speech Music Process."},{"issue":"8","key":"26_CR18","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Hu, D., Nie, F., Li, X.: Deep multimodal clustering for unsupervised audiovisual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9248\u20139257 (2019)","DOI":"10.1109\/CVPR.2019.00947"},{"issue":"11","key":"26_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/19.11.1","volume":"19","author":"RA Jacobs","year":"2019","unstructured":"Jacobs, R.A., Xu, C.: Can multisensory training aid visual learning? A computational investigation. J. Vis. 19(11), 1\u20131 (2019)","journal-title":"J. Vis."},{"key":"26_CR21","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, pp. 5492\u20135501 (2019)","DOI":"10.1109\/ICCV.2019.00559"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Kong, Q., Xu, Y., Wang, W., Plumbley, M.D.: Audio set classification with attention model: a probabilistic perspective. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 316\u2013320. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461392"},{"key":"26_CR23","unstructured":"Korbar, B., Tran, D., Torresani, L.: Cooperative learning of audio and video models from self-supervised synchronization. In: Advances in Neural Information Processing Systems, pp. 7763\u20137774 (2018)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Korbar, B., Tran, D., Torresani, L.: Scsampler: sampling salient clips from video for efficient action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6232\u20136242 (2019)","DOI":"10.1109\/ICCV.2019.00633"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"26_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Li, Y.J., Wang, Y.C.F.: Dual-modality seq2seq network for audio-visual event localization. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 2002\u20132006. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Liu, D., Jiang, T., Wang, Y.: Completeness modeling and context separation for weakly supervised temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1298\u20131307 (2019)","DOI":"10.1109\/CVPR.2019.00139"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 344\u2013353 (2019)","DOI":"10.1109\/CVPR.2019.00043"},{"key":"26_CR30","unstructured":"Maron, O., Lozano-P\u00e9rez, T.: A framework for multiple-instance learning. In: Advances in Neural Information Processing Systems, pp. 570\u2013576 (1998)"},{"issue":"11","key":"26_CR31","doi-asserted-by":"publisher","first-page":"2180","DOI":"10.1109\/TASLP.2018.2858559","volume":"26","author":"B McFee","year":"2018","unstructured":"McFee, B., Salamon, J., Bello, J.P.: Adaptive pooling operators for weakly labeled sound event detection. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(11), 2180\u20132193 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"26_CR32","unstructured":"Mesaros, A., et al.: DCASE 2017 challenge setup: tasks, datasets and baseline system (2017)"},{"issue":"6","key":"26_CR33","doi-asserted-by":"publisher","first-page":"162","DOI":"10.3390\/app6060162","volume":"6","author":"A Mesaros","year":"2016","unstructured":"Mesaros, A., Heittola, T., Virtanen, T.: Metrics for polyphonic sound event detection. Appl. Sci. 6(6), 162 (2016)","journal-title":"Appl. Sci."},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Naphade, M.R., Huang, T.S.: Discovering recurrent events in video using unsupervised methods. In: Proceedings of the International Conference on Image Processing, vol. 2, pp. II-II. IEEE (2002)","DOI":"10.1109\/ICIP.2002.1039875"},{"key":"26_CR35","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: ICML (2011)"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6752\u20136761 (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"26_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/978-3-030-01231-1_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Owens","year":"2018","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 639\u2013658. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_39"},{"key":"26_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/978-3-319-46448-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Owens","year":"2016","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Ambient sound provides supervision for visual learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 801\u2013816. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_48"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Parascandolo, G., Huttunen, H., Virtanen, T.: Recurrent neural networks for polyphonic sound event detection in real life recordings. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6440\u20136444. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 563\u2013579 (2018)","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Rahman, T., Xu, B., Sigal, L.: Watch, listen and tell: multi-modal weakly supervised dense event captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8908\u20138917 (2019)","DOI":"10.1109\/ICCV.2019.00900"},{"key":"26_CR42","unstructured":"Reed, S., Lee, H., Anguelov, D., Szegedy, C., Erhan, D., Rabinovich, A.: Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596 (2014)"},{"key":"26_CR43","unstructured":"Roma, G., Nogueira, W., Herrera, P., de Boronat, R.: Recurrence quantification analysis features for auditory scene classification. IEEE AASP challenge on detection and classification of acoustic scenes and events 2 (2013)"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Salamon, J., Jacoby, C., Bello, J.P.: A dataset and taxonomy for urban sound research. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 1041\u20131044 (2014)","DOI":"10.1145\/2647868.2655045"},{"key":"26_CR45","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, pp. 4358\u20134366 (2018)","DOI":"10.1109\/CVPR.2018.00458"},{"issue":"11","key":"26_CR46","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.tics.2008.07.006","volume":"12","author":"L Shams","year":"2008","unstructured":"Shams, L., Seitz, A.R.: Benefits of multisensory learning. Trends Cogn. Sci. 12(11), 411\u2013417 (2008)","journal-title":"Trends Cogn. Sci."},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.F.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5734\u20135743 (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131058 (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Lee, Y.J.: Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: IEEE International Conference on Computer Vision (ICCV), pp. 3544\u20133553. IEEE (2017)","DOI":"10.1109\/ICCV.2017.381"},{"key":"26_CR50","unstructured":"Song, H.O., Lee, Y.J., Jegelka, S., Darrell, T.: Weakly-supervised discovery of visual pattern configurations. In: Advances in Neural Information Processing Systems, pp. 1637\u20131645 (2014)"},{"issue":"13","key":"26_CR51","doi-asserted-by":"publisher","first-page":"R519","DOI":"10.1016\/S0960-9822(03)00445-7","volume":"13","author":"C Spence","year":"2003","unstructured":"Spence, C., Squire, S.: Multisensory integration: maintaining the perception of synchrony. Curr. Biol. 13(13), R519\u2013R521 (2003)","journal-title":"Curr. Biol."},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"26_CR53","unstructured":"Tian, Y., Guan, C., Goodman, J., Moore, M., Xu, C.: An attempt towards interpretable audio-visual video captioning. arXiv preprint arXiv:1812.02872 (2018)"},{"key":"26_CR54","unstructured":"Tian, Y., Guan, C., Justin, G., Moore, M., Xu, C.: Audio-visual interpretable and controllable video captioning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2019"},{"key":"26_CR55","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"},{"key":"26_CR56","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in the wild. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2019)"},{"key":"26_CR57","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"26_CR58","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"issue":"1","key":"26_CR59","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.cogbrainres.2004.07.003","volume":"22","author":"J Vroomen","year":"2004","unstructured":"Vroomen, J., Keetels, M., De Gelder, B., Bertelson, P.: Recalibration of temporal order perception by exposure to audio-visual asynchrony. Cogn. Brain Res. 22(1), 32\u201335 (2004)","journal-title":"Cogn. Brain Res."},{"key":"26_CR60","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Van Gool, L.: Untrimmednets for weakly supervised action recognition and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4325\u20134334 (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"26_CR61","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Y.F., Wang, W.Y.: Watch, listen, and describe: globally and locally aligned cross-modal attentions for video captioning. arXiv preprint arXiv:1804.05448 (2018)","DOI":"10.18653\/v1\/N18-2125"},{"key":"26_CR62","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, J., Metze, F.: A comparison of five multiple instance learning pooling functions for sound event detection with weak labeling. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 31\u201335. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"26_CR63","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00639"},{"key":"26_CR64","doi-asserted-by":"crossref","unstructured":"Yang, Y., Liu, J., Shah, M.: Video scene understanding using multi-scale analysis. In: IEEE 12th International Conference on Computer Vision, pp. 1669\u20131676. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459376"},{"key":"26_CR65","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Ma, W.C., Torralba, A.: The sound of motions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1735\u20131744 (2019)","DOI":"10.1109\/ICCV.2019.00182"},{"key":"26_CR66","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 570\u2013586 (2018)","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"26_CR67","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"26_CR68","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"26_CR69","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Z., Xu, X., Luo, P., Wang, X.: Vision-infused deep audio inpainting. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 283\u2013292 (2019)","DOI":"10.1109\/ICCV.2019.00037"},{"key":"26_CR70","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-58610-2_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhou","year":"2020","unstructured":"Zhou, H., Xu, X., Lin, D., Wang, X., Liu, Z.: Sep-stereo: visually guided stereophonic audio generation by associating source separation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 52\u201369. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_4"}],"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\/978-3-030-58580-8_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:12:32Z","timestamp":1733098352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58580-8_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585792","9783030585808"],"references-count":70,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58580-8_26","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":"3 December 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. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}