{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:26:53Z","timestamp":1760056013499,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723377"},{"type":"electronic","value":"9783031723384"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72338-4_2","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T10:03:01Z","timestamp":1726480981000},"page":"17-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DGFormer: A Dynamic Kernel with\u00a0Gaussian Fusion Transformer for\u00a0Semantic Image Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0802-6133","authenticated-orcid":false,"given":"Haoran","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5244-0657","authenticated-orcid":false,"given":"Longyi","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7407-2443","authenticated-orcid":false,"given":"Tingting","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1541-4226","authenticated-orcid":false,"given":"Binyu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"2_CR1","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":"2_CR2","unstructured":"Cajas, S.A., et\u00a0al.: A multi-modal satellite imagery dataset for public health analysis in colombia"},{"key":"2_CR3","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected crfs. In: ICLR (2015)"},{"issue":"4","key":"2_CR4","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 Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR5","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"2_CR6","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":"2_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-58520-4_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Chen","year":"2020","unstructured":"Chen, W., et al.: Tensor low-rank reconstruction for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 52\u201369. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_4"},{"key":"2_CR8","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, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Shuai, B., Liu, A.Q., Wang, G.: Semantic correlation promoted shape-variant context for segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8885\u20138894 (2019)","DOI":"10.1109\/CVPR.2019.00909"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Ding, X., Guo, Y., Ding, G., Han, J.: Acnet: strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1911\u20131920 (2019)","DOI":"10.1109\/ICCV.2019.00200"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows (2021)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"2_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Fu, J., 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":"2_CR14","doi-asserted-by":"crossref","unstructured":"He, J., Deng, Z., Qiao, Y.: Dynamic multi-scale filters for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (October 2019)","DOI":"10.1109\/ICCV.2019.00366"},{"key":"2_CR15","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":"2_CR16","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261\u20132269 (2016). https:\/\/api.semanticscholar.org\/CorpusID:9433631","DOI":"10.1109\/CVPR.2017.243"},{"key":"2_CR17","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Jin, Z., et al.: Mining contextual information beyond image for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7231\u20137241 (2021)","DOI":"10.1109\/ICCV48922.2021.00714"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Jin, Z., Liu, B., Chu, Q., Yu, N.: Isnet: integrate image-level and semantic-level context for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7189\u20137198 (2021)","DOI":"10.1109\/ICCV48922.2021.00710"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R.B., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6392\u20136401 (2019), https:\/\/api.semanticscholar.org\/CorpusID:57721164","DOI":"10.1109\/CVPR.2019.00656"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, J., Willette, J., Hwang, S.J.: Mpvit: multi-path vision transformer for dense prediction. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7277\u20137286 (2021), https:\/\/api.semanticscholar.org\/CorpusID:245353322","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"2_CR22","unstructured":"Li, K., et al.: Uniformer: unified transformer for efficient spatiotemporal representation learning. arXiv preprint arXiv:2201.04676 (2022)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, Y., Zhao, Q., Shen, T., Lin, Z., Liu, H.: Spatial pyramid based graph reasoning for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8950\u20138959 (2020)","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"2_CR24","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":"2_CR25","unstructured":"Lin, F., Liang, Z., He, J., Zheng, M., Tian, S., Chen, K.: Structtoken: Rethinking semantic segmentation with structural prior. arXiv preprint arXiv:2203.12612 (2022)"},{"key":"2_CR26","doi-asserted-by":"publisher","first-page":"119933","DOI":"10.1109\/ACCESS.2023.3326843","volume":"11","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Yang, H., Wu, C.: Unveiling patterns: a study on semi-supervised classification of strip surface defects. IEEE Access 11, 119933\u2013119946 (2023)","journal-title":"IEEE Access"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11966\u201311976 (2022). https:\/\/api.semanticscholar.org\/CorpusID:245837420","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2_CR30","unstructured":"MMSegmentation Contributors: OpenMMLab Semantic Segmentation Toolbox and Benchmark (July 2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"issue":"8","key":"2_CR31","first-page":"2399","volume":"64","author":"LF Nakayama","year":"2023","unstructured":"Nakayama, L.F., et al.: Pixel snow and differential privacy in retinal fundus photos de-identification. Investigative Ophthalmol. Vis. Sci. 64(8), 2399\u20132399 (2023)","journal-title":"Investigative Ophthalmol. Vis. Sci."},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Restrepo, D., Wu, C., V\u00e1squez-Venegas, C., Nakayama, L.F., Celi, L.A., L\u00f3pez, D.M.: Df-dm: A foundational process model for multimodal data fusion in the artificial intelligence era. arXiv preprint arXiv:2404.12278 (2024)","DOI":"10.21203\/rs.3.rs-4277992\/v1"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: Transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7262\u20137272 (October 2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2_CR36","unstructured":"Wantlin, K., et\u00a0al.: Benchmd: A benchmark for modality-agnostic learning on medical images and sensors. arXiv preprint arXiv:2304.08486 (2023)"},{"key":"2_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-030-58520-4_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Wu","year":"2020","unstructured":"Wu, T., et al.: GINet: graph interaction network for scene parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 34\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_3"},{"key":"2_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-030-01228-1_2","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Lee","year":"2018","unstructured":"Lee, D., Yun, S., Choi, S., Yoo, H., Yang, M.-H., Oh, S.: Unsupervised holistic image generation from key local patches. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 21\u201337. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_2"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: Metaformer is actually what you need for vision. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10809\u201310819 (2021). https:\/\/api.semanticscholar.org\/CorpusID:244478080","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"2_CR40","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":"2_CR41","first-page":"4971","volume":"35","author":"B Zhang","year":"2022","unstructured":"Zhang, B., Tian, Z., Tang, Q., Chu, X., Wei, X., Shen, C., et al.: Segvit: semantic segmentation with plain vision transformers. Adv. Neural. Inf. Process. Syst. 35, 4971\u20134982 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Context encoding for semantic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"2_CR43","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":"2_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"issue":"3","key":"2_CR45","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, M., Bai, S., Huang, T., Bai, X.: Asymmetric non-local neural networks for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 593\u2013602 (2019)","DOI":"10.1109\/ICCV.2019.00068"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72338-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T07:49:59Z","timestamp":1759996199000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72338-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723377","9783031723384"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72338-4_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}