{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:30:55Z","timestamp":1779337855997,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695248","type":"print"},{"value":"9783030695255","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69525-5_41","type":"book-chapter","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T16:21:16Z","timestamp":1614356476000},"page":"689-705","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5841-3455","authenticated-orcid":false,"given":"Chia-Yuan","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4916-499X","authenticated-orcid":false,"given":"Shuo-En","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1750-7118","authenticated-orcid":false,"given":"Pei-Yung","family":"Hsiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6947-7646","authenticated-orcid":false,"given":"Li-Chen","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"41_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"41_CR4","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517\u20136525 (2016)","DOI":"10.1109\/CVPR.2017.690"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: The IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R.B., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9396\u20139405 (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: UpsNet: a unified panoptic segmentation network. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00902"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Sofiiuk, K., Barinova, O., Konushin, A.: Adaptis: adaptive instance selection network. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00745"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Yang, Y., Li, H., Li, X., Zhao, Q., Wu, J., Lin, Z.: SOGNet: scene overlap graph network for panoptic segmentation. arXiv preprint arXiv:1911.07527 (2019)","DOI":"10.1609\/aaai.v34i07.6955"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: An end-to-end network for panoptic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6165\u20136174 (2019)","DOI":"10.1109\/CVPR.2019.00633"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Attention-guided unified network for panoptic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7019\u20137028 (2018)","DOI":"10.1109\/CVPR.2019.00719"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Dollar, P.: Panoptic feature pyramid networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2016)","DOI":"10.1109\/CVPR.2017.106"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"41_CR18","unstructured":"de Geus, D., Meletis, P., Dubbelman, G.: Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network. arXiv preprint arXiv:1809.02110 (2018)"},{"key":"41_CR19","unstructured":"Li, J., Raventos, A., Bhargava, A., Tagawa, T., Gaidon, A.: Learning to fuse things and stuff. arXiv preprint arXiv:1812.01192 (2018)"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4396\u20134405 (2018)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Fidler, S., Urtasun, R.: Instance-level segmentation for autonomous driving with deep densely connected MRFs. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 669\u2013677 (2015)","DOI":"10.1109\/CVPR.2016.79"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Schwing, A.G., Fidler, S., Urtasun, R.: Monocular object instance segmentation and depth ordering with CNNs. In: The IEEE International Conference on Computer Vision (ICCV), pp. 2614\u20132622 (2015)","DOI":"10.1109\/ICCV.2015.300"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Cordts, M., Franke, U., Brox, T.: Pixel-level encoding and depth layering for instance-level semantic labeling. In: GCPR (2016)","DOI":"10.1007\/978-3-319-45886-1_2"},{"key":"41_CR24","doi-asserted-by":"publisher","first-page":"2978","DOI":"10.1109\/TPAMI.2017.2775623","volume":"40","author":"X Liang","year":"2015","unstructured":"Liang, X., Lin, L., Wei, Y., Shen, X., Yang, J., Yan, S.: Proposal-free network for instance-level object segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 40, 2978\u20132991 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR25","unstructured":"Yang, T.J., et al.: DeeperLab: single-shot image parser. arXiv preprint arXiv:1902.05093 (2019)"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Gao, N., et al.: Ssap: single-shot instance segmentation with affinity pyramid. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00073"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: Yolact: real-time instance segmentation. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.D.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5168\u20135177 (2016)","DOI":"10.1109\/CVPR.2017.549"},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, X., Peng, C., Cheng, D., Sun, J.: Exfuse: enhancing feature fusion for semantic segmentation. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"41_CR30","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: towards balanced learning for object detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"41_CR31","doi-asserted-by":"crossref","unstructured":"Porzi, L., Bulo, S.R., Colovic, A., Kontschieder, P.: Seamless scene segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00847"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"41_CR33","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 (2018)"},{"key":"41_CR34","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"41_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"41_CR36","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"41_CR38","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2014","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2014)","journal-title":"Int. J. Comput. Vis."},{"key":"41_CR39","doi-asserted-by":"crossref","unstructured":"Hou, R., et al.: Real-time panoptic segmentation from dense detections. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8520\u20138529 (2020)","DOI":"10.1109\/CVPR42600.2020.00855"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69525-5_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T17:10:26Z","timestamp":1614359426000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69525-5_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695248","9783030695255"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69525-5_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"27 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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":"3","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.","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)"}}]}}