{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T06:23:34Z","timestamp":1768112614891,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819544448","type":"print"},{"value":"9789819544455","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4445-5_6","type":"book-chapter","created":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T03:43:51Z","timestamp":1768103031000},"page":"82-96","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GUIDE: Generative Understanding Injection for\u00a0Dense Estimation via\u00a0Enhanced Shape Coherence"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0692-6045","authenticated-orcid":false,"given":"Shengye","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3745-7541","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7396-874X","authenticated-orcid":false,"given":"Qingyang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"6_CR1","unstructured":"Amit, T., Shaharbany, T., Nachmani, E., Wolf, L.: SegDiff: image segmentation with diffusion probabilistic models (2022). https:\/\/arxiv.org\/abs\/2112.00390"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Chen, J., Lu, J., Zhu, X., Zhang, L.: Generative semantic segmentation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7111\u20137120 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00687","DOI":"10.1109\/CVPR52729.2023.00687"},{"key":"6_CR3","doi-asserted-by":"publisher","unstructured":"Chen, L.C., Papandreou, G., et al.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Cheng, B., Misra, I., et\u00a0al.: Masked-attention mask transformer for universal image segmentation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1280\u20131289 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00135","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., et\u00a0al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Dong, Z., Gao, G., et al.: Distilling segmenters from CNNs and transformers for remote sensing images\u2019 semantic segmentation. IEEE Trans. Geosci. Remote Sens. 61, 1\u201314 (2023). https:\/\/doi.org\/10.1109\/TGRS.2023.3290411","DOI":"10.1109\/TGRS.2023.3290411"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Gu, Z., Chen, H., Xu, Z.: DiffusionInst: diffusion model for instance segmentation. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2730\u20132734 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447191","DOI":"10.1109\/ICASSP48485.2024.10447191"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., et\u00a0al.: OneFormer: one transformer to rule universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2989\u20132998, June 2023","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., et\u00a0al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Lai, X., Tian, Z., et\u00a0al.: LISA: reasoning segmentation via large language model. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9579\u20139589 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.00915","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"6_CR11","unstructured":"Liang, C., Wang, W., Miao, J., Yang, Y.: GMMSeg: Gaussian mixture based generative semantic segmentation models. In: Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS 2022. Curran Associates Inc., Red Hook, NY, USA (2022)"},{"key":"6_CR12","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 (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"6_CR13","doi-asserted-by":"publisher","unstructured":"Mou, L., Hua, Y., Zhu, X.X.: A relation-augmented fully convolutional network for semantic segmentation in aerial scenes. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12408\u201312417 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01270","DOI":"10.1109\/CVPR.2019.01270"},{"key":"6_CR14","unstructured":"Oquab, M., Darcet, T., et\u00a0al.: DINOv2: learning robust visual features without supervision (2024). https:\/\/arxiv.org\/abs\/2304.07193"},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12159\u201312168 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01196","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"6_CR16","unstructured":"Ravi, N., et al.: SAM 2: segment anything in images and videos (2024). https:\/\/arxiv.org\/abs\/2408.00714"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Roberts, M., Ramapuram, J., et\u00a0al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"6_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Shen, Y., et al.: UGNA-VPR: a novel training paradigm for visual place recognition based on uncertainty-guided NeRF augmentation (2025). https:\/\/arxiv.org\/abs\/2503.21338","DOI":"10.1109\/LRA.2025.3554105"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7242\u20137252. IEEE Computer Society, Los Alamitos, CA, USA, October 2021. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00717. https:\/\/doi.ieeecomputersociety.org\/10.1109\/ICCV48922.2021.00717","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"6_CR21","unstructured":"Wan, Q., Huang, Z., Kang, B., Feng, J., Zhang, L.: Harnessing diffusion models for visual perception with meta prompts (2023). https:\/\/arxiv.org\/abs\/2312.14733"},{"key":"6_CR22","unstructured":"Wang, H., Cao, J., et\u00a0al.: DFormer: diffusion-guided transformer for universal image segmentation (2023). https:\/\/arxiv.org\/abs\/2306.03437"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Wang, W., Dai, J., et\u00a0al.: InternImage: exploring large-scale vision foundation models with deformable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14408\u201314419, June 2023","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"6_CR24","doi-asserted-by":"publisher","unstructured":"Wang, X., He, W., et\u00a0al.: USE: universal segment embeddings for open-vocabulary image segmentation. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4187\u20134196. IEEE Computer Society, Los Alamitos, CA, USA, June 2024. https:\/\/doi.org\/10.1109\/CVPR52733.2024.00401. https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52733.2024.00401","DOI":"10.1109\/CVPR52733.2024.00401"},{"key":"6_CR25","doi-asserted-by":"publisher","unstructured":"Wei, Z., Chen, L., et\u00a0al.: Stronger, fewer, & superior: harnessing vision foundation models for domain generalized semantic segmentation. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28619\u201328630 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02704","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"6_CR26","doi-asserted-by":"publisher","unstructured":"Wu, J., Ji, W., Fu, H., Xu, M., Jin, Y., Xu, Y.: MedSegDiff-V2: diffusion-based medical image segmentation with transformer. In: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI\u201924\/IAAI\u201924\/EAAI\u201924. AAAI Press (2024). https:\/\/doi.org\/10.1609\/aaai.v38i6.28418","DOI":"10.1609\/aaai.v38i6.28418"},{"key":"6_CR27","unstructured":"Xie, E., Wang, W., et\u00a0al.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"6_CR28","unstructured":"Xu, G., Ge, Y., et\u00a0al.: What matters when repurposing diffusion models for general dense perception tasks? (2024). https:\/\/arxiv.org\/abs\/2403.06090"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Ying, X., et al.: Mapping degeneration meets label evolution: learning infrared small target detection with single point supervision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01490"},{"key":"6_CR30","doi-asserted-by":"publisher","unstructured":"You, X., He, J., Yang, J., Gu, Y.: Learning with explicit shape priors for medical image segmentation. IEEE Trans. Med. Imaging 44(2), 927\u2013940 (2025). https:\/\/doi.org\/10.1109\/TMI.2024.3469214","DOI":"10.1109\/TMI.2024.3469214"},{"key":"6_CR31","unstructured":"Yu, C., Zhao, J., Liu, Y., Zhao, S., Dai, Y., Yue, X.: From easy to hard: progressive active learning framework for infrared small target detection with single point supervision (2025). https:\/\/arxiv.org\/abs\/2412.11154"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"Zhang, H., Li, F., et\u00a0al.: MP-Former: mask-piloted transformer for image segmentation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18074\u201318083. IEEE Computer Society, Los Alamitos, CA, USA, June 2023. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01733. https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52729.2023.01733","DOI":"10.1109\/CVPR52729.2023.01733"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., et\u00a0al.: Scene parsing through ADE20K dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4445-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T03:44:06Z","timestamp":1768103046000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4445-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819544448","9789819544455"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4445-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}