{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T15:40:54Z","timestamp":1770392454940,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557578","type":"print"},{"value":"9789819557585","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\/978-981-95-5758-5_19","type":"book-chapter","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:00:25Z","timestamp":1770354025000},"page":"251-265","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SageNet: A\u00a0Training-Free Few-Shot Image Segmentation Network via\u00a0Semantic-Geometric Alignment and\u00a0Diverse Prompting"],"prefix":"10.1007","author":[{"given":"Ming","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Gaofeng","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Dingzhou","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Fan","family":"Qin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,7]]},"reference":[{"key":"19_CR1","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019)"},{"key":"19_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Hong, S., Cho, S., Nam, J., Lin, S., Kim, S.: Cost aggregation with 4D convolutional Swin transformer for few-shot segmentation. In: Computer Vision, ECCV 2022, pp. 108\u2013126 (2022)","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"19_CR6","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Meila, M. (ed.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, 18\u201324 July 2021, vol.\u00a0139, pp. 4904\u20134916. PMLR (2021)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"19_CR8","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping Language-Image Pre-training for unified vision-language understanding and generation. In: Chaudhuri (ed.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 12888\u201312900. PMLR (2022)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Li, X., Wei, T., Chen, Y.P., Tai, Y.W., Tang, C.K.: FSS-1000: a 1000-class dataset for few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., Cho, M.: Hypercorrelation squeeze for few-shot segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6941\u20136952 (2021)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"19_CR11","unstructured":"Morabia, K., Arora, J., Vijaykumar, T.: Attention-based joint detection of object and semantic part (2020). https:\/\/arxiv.org\/abs\/2007.02419"},{"key":"19_CR12","unstructured":"Nagendra, S., Rashid, K., Shen, C., Kifer, D.: Samic: segment anything with in-context spatial prompt engineering (2024). https:\/\/arxiv.org\/abs\/2412.11998"},{"key":"19_CR13","unstructured":"Oquab, M., Darcet, T., Moutakanni, T.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024). Featured Certification"},{"key":"19_CR14","unstructured":"Pont-Tuset, J., et al.: The 2017 Davis challenge on video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA (2017)"},{"key":"19_CR15","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M. (ed.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, 18\u201324 July 2021, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Kalia, A.: Paco: parts and attributes of common objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7141\u20137151 (2023)","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Sun, Y., Chen, J., Zhang, S.: VRP-SAM: SAM with visual reference prompt. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23565\u201323574 (2024)","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"19_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-024-02185-6","volume":"133","author":"L Tang","year":"2025","unstructured":"Tang, L., Jiang, P.T., Xiao, H., Li, B.: Towards training-free open-world segmentation via image prompt foundation models. Int. J. Comput. Vis. 133, 1\u201315 (2025)","journal-title":"Int. J. Comput. Vis."},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., Huang, T.: Images speak in images: a generalist painter for in-context visual learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6830\u20136839 (2023)","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: SegGPT: towards segmenting everything in context. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1130\u20131140 (2023)","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"19_CR21","unstructured":"Yuan, L., Chen, D., Chen, Y.L., Codella, N.: Florence: a new foundation model for computer vision (2021). https:\/\/arxiv.org\/abs\/2111.11432"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Prompt, generate, then cache: Cascade of foundation models makes strong few-shot learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15211\u201315222 (2023)","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"19_CR23","unstructured":"Zhang, R., et al.: Personalize segment anything model with one shot. In: The Twelfth International Conference on Learning Representations (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5758-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:00:34Z","timestamp":1770354034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5758-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557578","9789819557585"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5758-5_19","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":"7 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}