{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:40:50Z","timestamp":1778010050490,"version":"3.51.4"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729423","type":"print"},{"value":"9783031729430","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72943-0_14","type":"book-chapter","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T13:39:20Z","timestamp":1732801160000},"page":"239-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":74,"title":["Context-Guided Spatial Feature Reconstruction for\u00a0Efficient Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3358-1994","authenticated-orcid":false,"given":"Zhenliang","family":"Ni","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2102-8235","authenticated-orcid":false,"given":"Xinghao","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7593-6055","authenticated-orcid":false,"given":"Yingjie","family":"Zhai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0322-4283","authenticated-orcid":false,"given":"Yehui","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0142-509X","authenticated-orcid":false,"given":"Yunhe","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"14_CR1","unstructured":"Bousselham, W., et al.: Efficient self-ensemble for semantic segmentation. In: British Machine Vision Conference (2022)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: CVPR. pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: non-local networks meet squeeze-excitation networks and beyond. In: ICCV Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Cavagnero, N., et al.: PEM: prototype-based efficient maskformer for image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01496"},{"issue":"4","key":"14_CR6","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 T-PAMI 40(4), 834\u2013848 (2017)","journal-title":"IEEE T-PAMI"},{"key":"14_CR7","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV, pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"14_CR11","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. NeurIPS 34, 17864\u201317875 (2021)","journal-title":"NeurIPS"},{"key":"14_CR12","unstructured":"Contributors, M.: MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Fan, M., et al.: Rethinking BISeNet for real-time semantic segmentation. In: CVPR, pp. 9716\u20139725 (2021)","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"14_CR14","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: CVPR, pp. 3146\u20133154 (2019)"},{"key":"14_CR15","unstructured":"Geng, Z., Guo, M.H., Chen, H., Li, X., Wei, K., Lin, Z.: Is attention better than matrix decomposition? arXiv preprint arXiv:2109.04553 (2021)"},{"key":"14_CR16","unstructured":"Guo, M.H., Lu, C.Z., Hou, Q., Liu, Z.N., Cheng, M.M., Hu, S.M.: Segnext: rethinking convolutional attention design for semantic segmentation. In: NeurIPS (2022)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"14_CR18","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Vedaldi, A.: Gather-excite: exploiting feature context in convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: criss-cross attention for semantic segmentation. In: ICCV, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Li, H., Xiong, P., Fan, H., Sun, J.: DFANet: deep feature aggregation for real-time semantic segmentation. In: CVPR, pp. 9522\u20139531 (2019)","DOI":"10.1109\/CVPR.2019.00975"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, W., Zhou, T., Quan, R., Yang, Y.: Semantic hierarchy-aware segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3332435"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, Z., Wu, J., Yang, Y., Lin, Z., Liu, H.: Expectation-maximization attention networks for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9167\u20139176 (2019)","DOI":"10.1109\/ICCV.2019.00926"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Rethinking vision transformers for mobilenet size and speed. arXiv preprint arXiv:2212.08059 (2022)","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"14_CR24","unstructured":"Liang, J., Zhou, T., Liu, D., Wang, W.: CLUSTSEG: clustering for universal segmentation. arXiv preprint arXiv:2305.02187 (2023)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Auto-deeplab: hierarchical neural architecture search for semantic image segmentation. In: CVPR, pp. 82\u201392 (2019)","DOI":"10.1109\/CVPR.2019.00017"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Shim, J.H., Yu, H., Kong, K., Kang, S.J.: Feedformer: revisiting transformer decoder for efficient semantic segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2263\u20132271 (2023)","DOI":"10.1609\/aaai.v37i2.25321"},{"key":"14_CR30","unstructured":"Wan, Q., Huang, Z., Lu, J., Yu, G., Zhang, L.: Seaformer: squeeze-enhanced axial transformer for mobile semantic segmentation (2023)"},{"key":"14_CR31","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. TPAMI (2019)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., Van\u00a0Gool, L.: Exploring cross-image pixel contrast for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7303\u20137313 (2021)","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"14_CR34","unstructured":"Wu, Y.H., et al.: Low-resolution self-attention for semantic segmentation. arXiv preprint arXiv:2310.05026 (2023)"},{"key":"14_CR35","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. NeurIPS 34, 12077\u201312090 (2021)","journal-title":"NeurIPS"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Bisenet: bilateral segmentation network for real-time semantic segmentation. In: ECCV, pp. 325\u2013341 (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Yu, W., Zhou, P., Yan, S., Wang, X.: Inceptionnext: when inception meets convnext. arXiv preprint arXiv:2303.16900 (2023)","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"14_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-030-58539-6_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 173\u2013190. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_11"},{"key":"14_CR39","first-page":"7281","volume":"34","author":"Y Yuan","year":"2021","unstructured":"Yuan, Y., et al.: HRFormer: high-resolution vision transformer for dense predict. NeurIPS 34, 7281\u20137293 (2021)","journal-title":"NeurIPS"},{"key":"14_CR40","unstructured":"Zhang, B., et\u00a0al.: Segvit: semantic segmentation with plain vision transformers, pp. 4971\u20134982 (2022)"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Context encoding for semantic segmentation. In: CVPR, pp. 7151\u20137160 (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: TopFormer: token pyramid transformer for mobile semantic segmentation. In: CVPR, pp. 12083\u201312093 (2022)","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, W., Konukoglu, E., Van\u00a0Gool, L.: Rethinking semantic segmentation: a prototype view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2582\u20132593 (2022)","DOI":"10.1109\/CVPR52688.2022.00261"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72943-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T14:19:10Z","timestamp":1732803550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72943-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"ISBN":["9783031729423","9783031729430"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72943-0_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"assertion":[{"value":"29 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}