{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:35:12Z","timestamp":1784820912164,"version":"3.55.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198359","type":"print"},{"value":"9783031198366","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\/978-3-031-19836-6_22","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T09:04:58Z","timestamp":1666343098000},"page":"386-403","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":123,"title":["Audio\u2013Visual Segmentation"],"prefix":"10.1007","author":[{"given":"Jinxing","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weixuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stan","family":"Birchfield","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingpeng","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"22_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/978-3-030-58523-5_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Afouras","year":"2020","unstructured":"Afouras, T., Owens, A., Chung, J.S., Zisserman, A.: Self-supervised learning of audio-visual objects from video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 208\u2013224. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_13"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 609\u2013617 (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"22_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-030-01246-5_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Objects that sound. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 451\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_27"},{"key":"22_CR4","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 29 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Afouras, T., Nagrani, A., Vedaldi, A., Zisserman, A.: Localizing visual sounds the hard way. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16867\u201316876 (2021)","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Vedaldi, A., Zisserman, A.: VGGSound: a large-scale audio-visual dataset. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 721\u2013725 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"issue":"4","key":"22_CR7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Wang, R., Pan, Z., Feng, R., Zhang, Y.: Look, listen, and attend: co-attention network for self-supervised audio-visual representation learning. In: Proceedings of the 28th ACM International Conference on Multimedia (ACM), pp. 3884\u20133892 (2020)","DOI":"10.1145\/3394171.3413869"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Duan, B., Tang, H., Wang, W., Zong, Z., Yang, G., Yan, Y.: Audio-visual event localization via recursive fusion by joint co-attention. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4013\u20134022 (2021)","DOI":"10.1109\/WACV48630.2021.00406"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Duke, B., Ahmed, A., Wolf, C., Aarabi, P., Taylor, G.W.: SSTVOS: sparse spatiotemporal transformers for video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5912\u20135921 (2021)","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"22_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-01219-9_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Gao","year":"2018","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 36\u201354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_3"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: Co-separating sounds of visual objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3879\u20133888 (2019)","DOI":"10.1109\/ICCV.2019.00398"},{"key":"22_CR13","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":"22_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR16","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 (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Hu, D., Nie, F., Li, X.: Deep multimodal clustering for unsupervised audiovisual learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9248\u20139257 (2019)","DOI":"10.1109\/CVPR.2019.00947"},{"key":"22_CR18","unstructured":"Hu, D., et al.: Discriminative sounding objects localization via self-supervised audiovisual matching. In: Advances in Neural Information Processing Systems (NeurIPS) 33, pp. 10077\u201310087 (2020)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6399\u20136408 (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"22_CR20","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), pp. 2002\u20132006. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"22_CR21","unstructured":"Lin, Y.B., Tseng, H.Y., Lee, H.Y., Lin, Y.Y., Yang, M.H.: Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing. In: Advances in Neural Information Processing Systems 34 (2021)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Wang, Y.C.F.: Audiovisual transformer with instance attention for audio-visual event localization. In: Proceedings of the Asian Conference on Computer Vision (ACCV) (2020)","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"22_CR24","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. CoRR abs\/1411.4038 (2014). http:\/\/arxiv.org\/abs\/1411.4038"},{"key":"22_CR25","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"22_CR26","unstructured":"Mahadevan, S., Athar, A., O\u0161ep, A., Hennen, S., Leal-Taix\u00e9, L., Leibe, B.: Making a case for 3D convolutions for object segmentation in videos. arXiv preprint arXiv:2008.11516 (2020)"},{"key":"22_CR27","unstructured":"Mao, Y., et al.: Transformer transforms salient object detection and camouflaged object detection. arXiv preprint arXiv:2104.10127 (2021)"},{"key":"22_CR28","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":"22_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1007\/978-3-030-58565-5_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Qian","year":"2020","unstructured":"Qian, R., Hu, D., Dinkel, H., Wu, M., Xu, N., Lin, W.: Multiple sound sources localization from coarse to fine. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 292\u2013308. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_18"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Ramaswamy, J.: What makes the sound?: a dual-modality interacting network for audio-visual event localization. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4372\u20134376. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Ramaswamy, J., Das, S.: See the sound, hear the pixels. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2970\u20132979 (2020)","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"22_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Rouditchenko, A., Zhao, H., Gan, C., McDermott, J., Torralba, A.: Self-supervised audio-visual co-segmentation. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2357\u20132361. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T.H., Kim, J., Yang, M.H., Kweon, I.S.: 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":"22_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-58580-8_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Li, D., Xu, C.: Unified multisensory perception: weakly-supervised audio-visual video\u00a0parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 436\u2013454. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_26"},{"key":"22_CR38","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"},{"issue":"3","key":"22_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: PVTv2: improved baselines with pyramid vision transformer. Comput. Visual Media 8(3), 1\u201310 (2022)","journal-title":"Comput. Visual Media"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yang, Y.: Exploring heterogeneous clues for weakly-supervised audio-visual video parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1326\u20131335 (2021)","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"22_CR42","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), pp. 6292\u20136300 (2019)","DOI":"10.1109\/ICCV.2019.00639"},{"key":"22_CR43","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. arXiv preprint arXiv:2105.15203 (2021)"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Xu, H., Zeng, R., Wu, Q., Tan, M., Gan, C.: Cross-modal relation-aware networks for audio-visual event localization. In: Proceedings of the 28th ACM International Conference on Multimedia (ACM), pp. 3893\u20133901 (2020)","DOI":"10.1145\/3394171.3413581"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Xuan, H., Zhang, Z., Chen, S., Yang, J., Yan, Y.: Cross-modal attention network for temporal inconsistent audio-visual event localization. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 279\u2013286 (2020)","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Yu, J., Cheng, Y., Zhao, R.W., Feng, R., Zhang, Y.: MM-pyramid: multimodal pyramid attentional network for audio-visual event localization and video parsing. arXiv preprint arXiv:2111.12374 (2021)","DOI":"10.1145\/3503161.3547869"},{"key":"22_CR47","unstructured":"Zhang, J., Xie, J., Barnes, N., Li, P.: Learning generative vision transformer with energy-based latent space for saliency prediction. Advances in Neural Information Processing Systems (NeurIPS) 34 (2021)"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Ma, W.C., Torralba, A.: The sound of motions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1735\u20131744 (2019)","DOI":"10.1109\/ICCV.2019.00182"},{"key":"22_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1007\/978-3-030-01246-5_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Zhao","year":"2018","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 587\u2013604. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_35"},{"key":"22_CR50","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"22_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, J., Zheng, L., Zhong, Y., Hao, S., Wang, M.: Positive sample propagation along the audio-visual event line. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8436\u20138444 (2021)","DOI":"10.1109\/CVPR46437.2021.00833"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19836-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T08:42:15Z","timestamp":1728204135000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19836-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198359","9783031198366"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19836-6_22","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":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.91","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)"}}]}}