{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:49:12Z","timestamp":1792514952771,"version":"4.5.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586065","type":"print"},{"value":"9783030586072","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\/978-3-030-58607-2_21","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T08:04:11Z","timestamp":1604649851000},"page":"352-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":103,"title":["Efficient Semantic Video Segmentation with Per-Frame Inference"],"prefix":"10.1007","author":[{"given":"Yifan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changqian","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"21_CR1","unstructured":"Bian, J.W., Zhan, H., Wang, N., Chin, T.J., Shen, C., Reid, I.: Unsupervised depth learning in challenging indoor video: weak rectification to rescue. arXiv:2006.02708 (2020). Comp. Res. Repository"},{"key":"21_CR2","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 35\u201345 (2019)"},{"key":"21_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/978-3-540-88682-2_5","volume-title":"Computer Vision \u2013 ECCV 2008","author":"GJ Brostow","year":"2008","unstructured":"Brostow, G.J., Shotton, J., Fauqueur, J., Cipolla, R.: Segmentation and recognition using structure from motion point clouds. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 44\u201357. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_5"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Chandra, S., Couprie, C., Kokkinos, I.: Deep spatio-temporal random fields for efficient video segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8915\u20138924 (2018)","DOI":"10.1109\/CVPR.2018.00929"},{"issue":"4","key":"21_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","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 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"21_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1007\/978-3-319-54407-6_33","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"M Fayyaz","year":"2017","unstructured":"Fayyaz, M., Saffar, M.H., Sabokrou, M., Fathy, M., Huang, F., Klette, R.: STFCN: spatio-temporal fully convolutional neural network for semantic segmentation of street scenes. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10116, pp. 493\u2013509. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54407-6_33"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Gadde, R., Jampani, V., Gehler, P.V.: Semantic video CNNs through representation warping. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4453\u20134462 (2017)","DOI":"10.1109\/ICCV.2017.477"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Alahi, A., Fei-Fei, L.: Characterizing and improving stability in neural style transfer. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4067\u20134076 (2017)","DOI":"10.1109\/ICCV.2017.438"},{"key":"21_CR10","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"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"He, T., Shen, C., Tian, Z., Gong, D., Sun, C., Yan, Y.: Knowledge adaptation for efficient semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 578\u2013587 (2019)","DOI":"10.1109\/CVPR.2019.00067"},{"key":"21_CR12","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv:1503.02531 (2015). Comp. Res. Repository"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Jain, S., Wang, X., Gonzalez, J.E.: Accel: a corrective fusion network for efficient semantic segmentation on video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8866\u20138875 (2019)","DOI":"10.1109\/CVPR.2019.00907"},{"key":"21_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01267-0_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"W-S Lai","year":"2018","unstructured":"Lai, W.-S., Huang, J.-B., Wang, O., Shechtman, E., Yumer, E., Yang, M.-H.: Learning blind video temporal consistency. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 179\u2013195. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_11"},{"issue":"3","key":"21_CR15","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1145\/1015706.1015780","volume":"23","author":"A Levin","year":"2004","unstructured":"Levin, A., Lischinski, D., Weiss, Y.: Colorization using optimization. ACM Trans. Graph. 23(3), 689\u2013694 (2004)","journal-title":"ACM Trans. Graph."},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Li, Q., Jin, S., Yan, J.: Mimicking very efficient network for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7341\u20137349 (2017)","DOI":"10.1109\/CVPR.2017.776"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Shi, J., Lin, D.: Low-latency video semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5997\u20136005 (2018)","DOI":"10.1109\/CVPR.2018.00628"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Liu, S., Wang, C., Qian, R., Yu, H., Bao, R., Sun, Y.: Surveillance video parsing with single frame supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 413\u2013421 (2017)","DOI":"10.1109\/CVPR.2017.114"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2604\u20132613 (2019)","DOI":"10.1109\/CVPR.2019.00271"},{"key":"21_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-030-01249-6_34","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Mehta","year":"2018","unstructured":"Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., Hajishirzi, H.: ESPNet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 561\u2013580. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_34"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Miksik, O., Munoz, D., Bagnell, J.A., Hebert, M.: Efficient temporal consistency for streaming video scene analysis. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 133\u2013139. IEEE (2013)","DOI":"10.1109\/ICRA.2013.6630567"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Nilsson, D., Sminchisescu, C.: Semantic video segmentation by gated recurrent flow propagation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6819\u20136828 (2018)","DOI":"10.1109\/CVPR.2018.00713"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Orsic, M., Kreso, I., Bevandic, P., Segvic, S.: In defense of pre-trained ImageNet architectures for real-time semantic segmentation of road-driving images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01289"},{"key":"21_CR24","unstructured":"Reda, F., Pottorff, R., Barker, J., Catanzaro, B.: FlowNet2-PyTorch: PyTorch implementation of FlowNet 2.0: evolution of optical flow estimation with deep networks (2017). https:\/\/github.com\/NVIDIA\/flownet2-pytorch"},{"key":"21_CR25","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. arXiv:1412.6550 (2014). Comp. Res. Repository"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"21_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-49409-8_69","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"E Shelhamer","year":"2016","unstructured":"Shelhamer, E., Rakelly, K., Hoffman, J., Darrell, T.: Clockwork convnets for video semantic segmentation. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 852\u2013868. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_69"},{"key":"21_CR28","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 802\u2013810 (2015)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"21_CR30","unstructured":"Sun, K., et al.: High-resolution representations for labeling pixels and regions. arXiv:1904.04514 (2019). Comp. Res. Repository"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Tian, Z., He, T., Shen, C., Yan, Y.: Decoders matter for semantic segmentation: data-dependent decoding enables flexible feature aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3126\u20133135 (2019)","DOI":"10.1109\/CVPR.2019.00324"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Xu, Y.S., Fu, T.J., Yang, H.K., Lee, C.Y.: Dynamic video segmentation network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6556\u20136565 (2018)","DOI":"10.1109\/CVPR.2018.00686"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Yao, C.H., Chang, C.Y., Chien, S.Y.: Occlusion-aware video temporal consistency. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 777\u2013785. ACM (2017)","DOI":"10.1145\/3123266.3123363"},{"key":"21_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/978-3-030-01261-8_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Yu","year":"2018","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 334\u2013349. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_20"},{"key":"21_CR35","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. In: Proceedings of the International Conference on Learning Representations (2017)"},{"key":"21_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1007\/978-3-030-01219-9_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Zhao","year":"2018","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 418\u2013434. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_25"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, X., Dai, J., Yuan, L., Wei, Y.: Towards high performance video object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7210\u20137218 (2018)","DOI":"10.1109\/CVPR.2018.00753"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2349\u20132358 (2017)","DOI":"10.1109\/CVPR.2017.441"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8856\u20138865 (2019)","DOI":"10.1109\/CVPR.2019.00906"}],"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\/978-3-030-58607-2_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:46:55Z","timestamp":1730854015000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58607-2_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586065","9783030586072"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58607-2_21","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":"7 November 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)"}}]}}