{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:54:05Z","timestamp":1780764845221,"version":"3.54.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198144","type":"print"},{"value":"9783031198151","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\/978-3-031-19815-1_36","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T23:11:54Z","timestamp":1666221114000},"page":"624-639","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["A Transformer-Based Decoder for Semantic Segmentation with Multi-level Context Mining"],"prefix":"10.1007","author":[{"given":"Bowen","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junni","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"36_CR2","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., et al: Semantic image segmentation with deep convolutional nets and fully connected crfs. In: ICLR (2015)"},{"key":"36_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2017","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., et al.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. TPAMI 40, 834\u2013848 (2017)","journal-title":"TPAMI"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L., Papandreou, G., Schroff, F., et al: Rethinking atrous convolution for semantic image segmentation. arXiv (2017)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhu, Y., Papandreou, G., et al: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"36_CR6","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS (2021)"},{"key":"36_CR7","unstructured":"Chu, X., Tian, Z., Wang, Y., et. al: Twins: revisiting the design of spatial attention in vision transformers. In: NeurIPS (2021)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., et al: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"36_CR9","unstructured":"Cordts, M., Omran, M., Ramos, S., et al: Semantic understanding of scenes through the ade20k dataset. In: CVPR (2017)"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Chen, D., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"36_CR11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Fang, J., Xie, L., Wang, X., et al: Msg-transformer: exchanging local spatial information by manipulating messenger tokens. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.01175"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., et al: Dual attention network for scene segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Huang, S., Lu, Z., Cheng, R., et al: FaPN: feature-aligned pyramid network for dense image prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Wei, Y., et al: Ccnet: criss-cross attention for semantic segmentation. In: TPAMI (2020)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"36_CR16","unstructured":"Jain, J., Singh, A., Orlov, N., et al.: Semask: semantically masking transformer backbones for effective semantic segmentation. arXiv (2021)"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Jin, Z., Gong, T., Yu, D., et al.: Mining contextual information beyond image for semantic segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00714"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., et al: Panoptic feature pyramid networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, Z., Wu, J., et al: Expectation-maximization attention networks for semantic segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00926"},{"key":"36_CR20","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":"36_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. arXiv (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., et al: Segmenter: transformer for semantic segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"36_CR25","unstructured":"Touvron, H., Cord, M., Douze, M., et al: Training data-efficient image transformers & distillation through attention. arXiv (2020)"},{"key":"36_CR26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., et al: Exploring cross-image pixel contrast for semantic segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., et al: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., et al: Unified perceptual parsing for scene understanding. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"36_CR30","unstructured":"Xie, E., Wang, W., Yu, Z., et al.: Segformer: simple and efficient design for semantic segmentation with transformers. In: NeurIPS (2021)"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. arXiv (2019)","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"36_CR32","unstructured":"Yuan, Y., Wang, J.: Ocnet: object context network for scene parsing. arXiv (2018)"},{"key":"36_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, F., C, Y., Li, Z., et al: Acfnet: attentional class feature network for semantic segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00690"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., et al: Context encoding for semantic segmentation. arXiv (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"36_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., et al: Pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"36_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, Y., Liu, S., et. al: PSANet: point-wise spatial attention network for scene parsing. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"36_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., et al: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00681"}],"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\/978-3-031-19815-1_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T23:28:43Z","timestamp":1666394923000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19815-1_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198144","9783031198151"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19815-1_36","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":"20 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)"}}]}}