{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:17:01Z","timestamp":1743016621131,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601219"},{"type":"electronic","value":"9789819601226"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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\/978-981-96-0122-6_16","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:24:44Z","timestamp":1731781484000},"page":"170-181","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AGLTN: Attention-Based Global-Local Transformer Network for Ultra-high Resolution Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1782-6473","authenticated-orcid":false,"given":"Jiafeng","family":"Li","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"issue":"11","key":"16_CR1","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"16_CR2","doi-asserted-by":"publisher","unstructured":"Ronneberger O., Fischer P., Brox T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5\u20139 , 2015, In: Proceedings, part III 18 (pp. 234\u2013241). Springer International Publishing, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"12","key":"16_CR3","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In; In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"16_CR5","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., et al.: Rethinking Atrous convolution for semantic image segmentation. arxiv preprint arxiv: 1706.05587 (2017)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Chen, W., Jiang, Z., Wang, Z., et al.: Collaborative global-local networks for memory-efficient segmentation of ultra-high resolution images. In: In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8924\u20138933 (2019)","DOI":"10.1109\/CVPR.2019.00913"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In; In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Lin T.Y., Dollar P., Girshick R., et al. Feature Pyramid Networks for Object Detection[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., et al.: 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":"16_CR10","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., et al.: CCNet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Chung, J., Tai, Y.W., et al.: CascadePSP: toward class-agnostic and very high-resolution segmentation via global and local refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8890\u20138899 (2020)","DOI":"10.1109\/CVPR42600.2020.00891"},{"issue":"07","key":"16_CR13","first-page":"12402","volume":"34","author":"T Wu","year":"2020","unstructured":"Wu, T., Lei, Z., Lin, B., et al.: Patch proposal network for fast semantic segmentation of high-resolution images. Proc. AAAI Conf. Artif. Intell. 34(07), 12402\u201312409 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"16_CR14","unstructured":"Wang, J., Long, X., Chen, G., et al.: U-HRNet: delving into improving semantic representation of high resolution network for dense prediction. arxiv preprint arxiv: 2210.07140 (2022)"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Guo, S., Liu, L., Gan, Z., et al.: ISDNet: integrating shallow and deep networks for efficient ultra-high resolution segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4361\u20134370 (2022)","DOI":"10.1109\/CVPR52688.2022.00432"},{"key":"16_CR16","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"16_CR17","unstructured":"Mehta, S., Ghazvininejad, M., Iyer, S., et al.: DeLighT: deep and light-weight transformer. arxiv preprint arxiv: 2008.00623 (2020)"},{"key":"16_CR18","unstructured":"Wu, Z., Liu, Z., Lin, J., et al.: Lite transformer with long-short range attention. arxiv preprint arxiv: 2004.11886 (2020)"},{"key":"16_CR19","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. arxiv preprint arxiv: 2001.04451 (2020)"},{"key":"16_CR20","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arxiv preprint arxiv: 2010.11929 (2020)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., et al.: 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":"16_CR22","doi-asserted-by":"crossref","unstructured":"Chen, X., Liu, Z., Tang, H., et al.: SparseViT: revisiting activation sparsity for efficient high-resolution vision transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2061\u20132070 (2023)","DOI":"10.1109\/CVPR52729.2023.00205"},{"key":"16_CR23","unstructured":"Fan, Q., You, Q., Han, X., et al.: ViTAR: vision transformer with any resolution. arxiv preprint arxiv: 2403.18361 (2024)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., et al.: ICNet for real-time semantic segmentation on high-resolution images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 405\u2013420 (2018)","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., et al. DenseASPP for semantic segmentation in street scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3684\u20133692 (2018)","DOI":"10.1109\/CVPR.2018.00388"},{"key":"16_CR26","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Shen, T., Zhang, Y., Qi, L., et al.: High quality segmentation for ultra high-resolution images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1310\u20131319 (2022)","DOI":"10.1109\/CVPR52688.2022.00137"},{"key":"16_CR28","first-page":"1","volume":"60","author":"L Ding","year":"2022","unstructured":"Ding, L., Lin, D., Lin, S., et al.: Looking outside the window: wider-context transformer for the semantic segmentation of high-resolution remote sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"2","key":"16_CR29","doi-asserted-by":"publisher","first-page":"2400","DOI":"10.1109\/TPAMI.2022.3162528","volume":"45","author":"T Verelst","year":"2022","unstructured":"Verelst, T., Tuytelaars, T.: SegBlocks: block-based dynamic resolution networks for real-time segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 2400\u20132411 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Xie, C., Xia, C., Ma, M., et al. Pyramid grafting network for one-stage high resolution saliency detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11717\u201311726 (2022)","DOI":"10.1109\/CVPR52688.2022.01142"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., et al.: 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":"16_CR32","doi-asserted-by":"crossref","unstructured":"Fan, M., Lai, S., Huang, J., et al. Rethinking BiSeNet for real-time semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9716\u20139725 (2021)","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Huynh, C., Tran, A.T., Luu, K., et al.: Progressive semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16755\u201316764 (2021)","DOI":"10.1109\/CVPR46437.2021.01648"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Li, Q., Yang, W., Liu, W., et al.: From contexts to locality: ultra-high resolution image segmentation via locality-aware contextual correlation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7252\u20137261 (2021)","DOI":"10.1109\/ICCV48922.2021.00716"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Ji, D., Zhao, F., Lu, H., et al.: Ultra-high resolution segmentation with ultra-rich context: a novel benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23621\u201323630 (2021)","DOI":"10.1109\/CVPR52729.2023.02262"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Ji, D., Zhao, F., Lu, H.: Guided patch-grouping wavelet transformer with spatial congruence for ultra-high resolution segmentation. arxiv preprint arxiv: 2307.00711 (2023)","DOI":"10.24963\/ijcai.2023\/102"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0122-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T19:18:46Z","timestamp":1731784726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0122-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601219","9789819601226"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0122-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}