{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:10:52Z","timestamp":1770347452056,"version":"3.49.0"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s11263-024-02165-w","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T17:01:36Z","timestamp":1720803696000},"page":"6004-6020","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multi-modal Prototypes for Open-World Semantic Segmentation"],"prefix":"10.1007","volume":"132","author":[{"given":"Yuhuan","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaofan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Ju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6115-5194","authenticated-orcid":false,"given":"Jiangchao","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,12]]},"reference":[{"issue":"3","key":"2165_CR1","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1145\/116873.116880","volume":"23","author":"F Aurenhammer","year":"1991","unstructured":"Aurenhammer, F. (1991). Voronoi diagrams-a survey of a fundamental geometric data structure. ACM Computing Surveys (CSUR), 23(3), 345\u2013405.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2165_CR2","doi-asserted-by":"crossref","unstructured":"Baek, D., Oh, Y., & Ham, B. (2021). Exploiting a joint embedding space for generalized zero-shot semantic segmentation. Proceedings of the international conference on computer vision, (pp. 9516\u20139525). IEEE.","DOI":"10.1109\/ICCV48922.2021.00940"},{"key":"2165_CR3","doi-asserted-by":"crossref","unstructured":"Boudiaf, M., Kervadec, H., Masud, Z. I., Piantanida, P., Ayed, I. B., & Dolz, J. (2021). Few-shot segmentation without meta-learning: A good transductive inference is all you need? Proceedings of the IEEE conference on computer vision and pattern recognition, (pp. 13979\u201313988). IEEE.","DOI":"10.1109\/CVPR46437.2021.01376"},{"key":"2165_CR4","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, (Vol.\u00a033, pp. 1877\u20131901) Curran Associates, Inc."},{"key":"2165_CR5","unstructured":"Bucher, M., Vu, T.-H., Cord, M., & P\u00e9rez, P. (2019). Zero-shot semantic segmentation. Advances in neural information processing systems (Vol. 12353, pp. 539\u2013555). Springer."},{"key":"2165_CR6","doi-asserted-by":"crossref","unstructured":"Cai, K., Ren, P., Zhu, Y., Xu, H., Liu, J., Li, C., & Liang, X. (2023). Mixreorg: Cross-modal mixed patch reorganization is a good mask learner for open-world semantic segmentation. Proceedings of the international conference on computer vision (pp. 1196\u20131205). IEEE.","DOI":"10.1109\/ICCV51070.2023.00116"},{"key":"2165_CR7","doi-asserted-by":"crossref","unstructured":"Cha, J., Mun, J., & Roh, B. (2023). Learning to generate text-grounded mask for open-world semantic segmentation from only image-text pairs. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 11165\u201311174). IEEE.","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"2165_CR8","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., & Soricut, R. (2021). Conceptual 12M: Pushing web-scale image-text pre-training to recognize long-tail visual concepts. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3558\u20133568). IEEE.","DOI":"10.1109\/CVPR46437.2021.00356"},{"issue":"4","key":"2165_CR9","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2165_CR10","unstructured":"Cheng, B., Schwing, A.G., & Kirillov, A. (2021). Per-pixel classification is not all you need for semantic segmentation. Advances in neural information processing systems (Vol.\u00a034, pp. 17864\u201317875). Curran Associates, Inc."},{"key":"2165_CR11","unstructured":"Dong, N., & Xing, E.P. (2018). Few-shot semantic segmentation with prototype learning. Proceedings of the British machine vision conference (p.79). BMVA Press."},{"issue":"7","key":"2165_CR12","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00011","volume":"3","author":"V Dumoulin","year":"2018","unstructured":"Dumoulin, V., Perez, E., Schucher, N., Strub, F., Vries, H. D., Courville, A., & Bengio, Y. (2018). Feature-wise transformations. Distill, 3(7), e11.","journal-title":"Distill"},{"issue":"1","key":"2165_CR13","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1), 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"key":"2165_CR14","doi-asserted-by":"crossref","unstructured":"Fan, Q., Pei, W., Tai, Y.-W., & Tang, C.-K. (2022). Self-support few-shot semantic segmentation. Proceedings of the European conference on computer vision (Vol. 13679, pp. 701\u2013719). Springer.","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"2165_CR15","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Gu, X., Cui, Y., & Lin, T.-Y. (2022). Scaling open-vocabulary image segmentation with image-level labels. Proceedings of the European conference on computer vision (Vol. 13696, pp. 540\u2013557). Springer.","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"2165_CR16","doi-asserted-by":"crossref","unstructured":"Gu, Z., Zhou, S., Niu, L., Zhao, Z., & Zhang, L. (2020). Context-aware feature generation for zero-shot semantic segmentation. Proceedings of ACM international conference on multimedia (pp. 1921\u20131929). ACM.","DOI":"10.1145\/3394171.3413593"},{"key":"2165_CR17","doi-asserted-by":"crossref","unstructured":"Hajimiri, S., Boudiaf, M., Ben\u00a0Ayed, I., & Dolz, J. (2023). A strong baseline for generalized few-shot semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 11269\u201311278). IEEE.","DOI":"10.1109\/CVPR52729.2023.01084"},{"key":"2165_CR18","doi-asserted-by":"crossref","unstructured":"Hong, S., Cho, S., Nam, J., & Kim, S. (2022). Cost aggregation is all you need for few-shot segmentation. Proceedings of the European conference on computer vision (Vol. 13689, pp. 108\u2013126). Springer.","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"2165_CR19","doi-asserted-by":"crossref","unstructured":"Lai, X., Tian, Z., Chen, Y., Li, Y., Yuan, Y., Liu, S., & Jia, J. (2023). Lisa: Reasoning segmentation via large language model. arXiv preprint arXiv:2308.00692","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"2165_CR20","doi-asserted-by":"crossref","unstructured":"Lang, C., Cheng, G., Tu, B., & Han, J. (2022). Learning what not to segment: A new perspective on fewshot segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8047\u20138057). IEEE.","DOI":"10.1109\/CVPR52688.2022.00789"},{"key":"2165_CR21","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., & Ranftl, R. (2022). Language-driven semantic segmentation. Proceedings of the international conference on learning representations."},{"key":"2165_CR22","unstructured":"Li, P., Wei, Y., & Yang, Y. (2020). Consistent structural relation learning for zero-shot segmentation. Advances in neural information processing systems (Vol.\u00a033, pp. 10317\u201310327). Curran Associates, Inc."},{"key":"2165_CR23","doi-asserted-by":"crossref","unstructured":"Liang, F., Wu, B., Dai, X., Li, K., Zhao, Y., Zhang, H., & Marculescu, D. (2023). Open-vocabulary semantic segmentation with mask-adapted clip. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7061\u20137070). IEEE.","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"2165_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D. & Zitnick, C.L. (2014). Microsoft COCO: Common objects in context. Proceedings of the european conference on computer vision (Vol. 8693, pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2165_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, N., Cao, Q., Yao, X., Han, J., & Shao, L. (2022). Learning non-target knowledge for few-shot semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 11563\u201311572). IEEE.","DOI":"10.1109\/CVPR52688.2022.01128"},{"key":"2165_CR26","unstructured":"LIU, Y., Liu, N., Yao, X., & Han, J. (2022). Intermediate prototype mining transformer for few-shot semantic segmentation. S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.), Advances in neural information processing systems (Vol.\u00a035, pp. 38020\u201338031). Curran Associates, Inc."},{"key":"2165_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, X., Zhang, S., & He, X. (2020). Part-aware prototype network for few-shot semantic segmentation. Proceedings of the European conference on computer vision (Vol. 12354, pp. 142\u2013158). Springer.","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"2165_CR28","doi-asserted-by":"crossref","unstructured":"Lu, Z., He, S., Zhu, X., Zhang, L., Song, Y. -Z., & Xiang, T. (2021). Simpler is better: Few-shot semantic segmentation with classifier weight transformer. Proceedings of the international conference on computer vision (pp. 8721\u20138730). IEEE.","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"2165_CR29","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., & Ecker, A. (2022). Image segmentation using text and image prompts. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7076\u20137086). IEEE.","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"2165_CR30","unstructured":"Ma, C., Yang, Y., Ju, C., Zhang, F., Zhang, Y., & Wang, Y. (2023). Attrseg: Open-vocabulary semantic segmentation via attribute decomposition-aggregation. Advances in neural information processing systems (Vol.\u00a036, pp. 10258\u201310270). Curran Associates, Inc."},{"key":"2165_CR31","unstructured":"Ma, C., Yang, Y., Wang, Y., Zhang, Y., & Xie, W. (2022). Open-vocabulary semantic segmentation with frozen vision-language models. Proceedings of the British machine vision conference (p.45). BMVA Press."},{"key":"2165_CR32","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., & Cho, M. (2021). Hypercorrelation squeeze for few-shot segmentation. Proceedings of the international conference on computer vision (pp. 6941\u20136952). IEEE.","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"2165_CR33","doi-asserted-by":"crossref","unstructured":"Nguyen, K., & Todorovic, S. (2019). Feature weighting and boosting for few-shot segmentation. Proceedings of the international conference on computer vision (pp. 622\u2013631). IEEE.","DOI":"10.1109\/ICCV.2019.00071"},{"key":"2165_CR34","unstructured":"OpenAI (2023). Gpt-4 technical report."},{"key":"2165_CR35","unstructured":"Qi, L., Kuen, J., Guo, W., Gu, J., Lin, Z., Du, B. & Yang, M.-H. (2023). Aims: All-inclusive multi-level segmentation. Advances in neural information processing systems (Vol.\u00a036). Curran Associates, Inc."},{"key":"2165_CR36","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S. & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. Proceedings of the international conference on machine learning (Vol.\u00a0139, pp. 8748\u20138763). PMLR."},{"key":"2165_CR37","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention (Vol. 9351, pp. 234\u2013241). Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2165_CR38","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., et al. (2022). Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, 35, 25278\u201325294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2165_CR39","doi-asserted-by":"crossref","unstructured":"Shaban, A., Bansal, S., Zhen, L., Essa, I., & Boots, B. (2017). One-shot learning for semantic segmentation. Proceedings of the British machine vision conference. BMVA Press.","DOI":"10.5244\/C.31.167"},{"issue":"4","key":"2165_CR40","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., & Darrell, T. (2017). Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), 640\u2013651.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2165_CR41","first-page":"4077","volume":"30","author":"J Snell","year":"2017","unstructured":"Snell, J., Swersky, K., & Zemel, R. (2017). Prototypical networks for few-shot learning. Advances in Neural Information Processing Systems, 30, 4077\u20134087.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2165_CR42","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., & Schmid, C. (2021). Segmenter: Transformer for semantic segmentation. Proceedings of the international conference on computer vision (pp. 7242\u20137252). IEEE.","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"2165_CR43","doi-asserted-by":"crossref","unstructured":"Tian, Z., Lai, X., Jiang, L., Liu, S., Shu, M., Zhao, H., & Jia, J. (2022). Generalized few-shot semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 11553\u201311562). IEEE.","DOI":"10.1109\/CVPR52688.2022.01127"},{"issue":"2","key":"2165_CR44","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","volume":"44","author":"Z Tian","year":"2022","unstructured":"Tian, Z., Zhao, H., Shu, M., Yang, Z., Li, R., & Jia, J. (2022). Prior guided feature enrichment network for few-shot segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(2), 1050\u20131065.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2165_CR45","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, X., Hu, Y., Yang, Y., Cao, X., & Zhen, X. (2020). Few-shot semantic segmentation with democratic attention networks. (Vol. 12358, pp. 730\u2013746). Springer.","DOI":"10.1007\/978-3-030-58601-0_43"},{"key":"2165_CR46","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., & Feng, J. (2019). Panet: Few-shot image semantic segmentation with prototype alignment. Proceedings of the international conference on computer vision (pp. 9196\u20139205). IEEE.","DOI":"10.1109\/ICCV.2019.00929"},{"key":"2165_CR47","doi-asserted-by":"crossref","unstructured":"Xian, Y., Choudhury, S., He, Y., Schiele, B., & Akata, Z. (2019). Semantic projection network for zero-and few-label semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8256\u20138265). Computer Vision Foundation \/ IEEE.","DOI":"10.1109\/CVPR.2019.00845"},{"key":"2165_CR48","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). Segformer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, 34, 12077\u201312090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2165_CR49","doi-asserted-by":"crossref","unstructured":"Xu, J., Mello, S.D., Liu, S., Byeon, W., Breuel, T., Kautz, J., & Wang, X. (2022). Groupvit: Semantic segmentation emerges from text supervision. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 18113\u201318123). IEEE.","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"2165_CR50","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Lin, Y., Cao, Y., Hu, H., & Bai, X. (2022). A simple baseline for open vocabulary semantic segmentation with pre-trained vision-language model. Proceedings of the European conference on computer vision (Vol. 13689, pp. 736\u2013753). Springer.","DOI":"10.1007\/978-3-031-19818-2_42"},{"issue":"6","key":"2165_CR51","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1007\/s11263-020-01381-4","volume":"129","author":"H-J Ye","year":"2021","unstructured":"Ye, H.-J., Hu, H., & Zhan, D.-C. (2021). Learning adaptive classifiers synthesis for generalized few-shot learning. International Journal of Computer Vision, 129(6), 1930\u20131953.","journal-title":"International Journal of Computer Vision"},{"key":"2165_CR52","first-page":"32215","volume":"36","author":"Q Yu","year":"2023","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., & Chen, L.-C. (2023). Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip. Advances in Neural Information Processing Systems, 36, 32215\u201332234.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2165_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xiao, J., & Qin, T. (2021). Self-guided and cross-guided learning for few-shot segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8312\u20138321). IEEE.","DOI":"10.1109\/CVPR46437.2021.00821"},{"key":"2165_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lin, G., Liu, F., Yao, R., & Shen, C. (2019). Canet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5217\u20135226). IEEE.","DOI":"10.1109\/CVPR.2019.00536"},{"key":"2165_CR55","first-page":"73652","volume":"36","author":"F Zhang","year":"2023","unstructured":"Zhang, F., Zhou, T., Li, B., He, H., Ma, C., Zhang, T., & Wang, Y. (2023). Uncovering prototypical knowledge for weakly open-vocabulary semantic segmentation. Advances in Neural Information Processing Systems, 36, 73652\u201373665.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2165_CR56","first-page":"21984","volume":"34","author":"G Zhang","year":"2021","unstructured":"Zhang, G., Kang, G., Yang, Y., & Wei, Y. (2021). Few-shot segmentation via cycle-consistent transformer. Advances in Neural Information Processing Systems, 34, 21984\u201321996.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2165_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, F., Zou, X., Liu, S., Li, C., Yang, J., & Zhang, L. (2023). A simple framework for open-vocabulary segmentation and detection. Proceedings of the international conference on computer vision (p.1020-1031). IEEE.","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"2165_CR58","first-page":"6575","volume":"35","author":"J-W Zhang","year":"2022","unstructured":"Zhang, J.-W., Sun, Y., Yang, Y., & Chen, W. (2022). Feature-proxy transformer for few-shot segmentation. Advances in Neural Information Processing Systems, 35, 6575\u20136588.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"11","key":"2165_CR59","doi-asserted-by":"publisher","first-page":"6609","DOI":"10.1109\/TCSVT.2023.3265075","volume":"33","author":"L Zhang","year":"2023","unstructured":"Zhang, L., Zhang, X., Wang, Q., Wu, W., Chang, X., & Liu, J. (2023). Rpmg-fss: Robust prior mask guided few-shot semantic segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 33(11), 6609\u20136621.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2165_CR60","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6230\u20136239). IEEE.","DOI":"10.1109\/CVPR.2017.660"},{"key":"2165_CR61","first-page":"6575","volume":"35","author":"X Zou","year":"2023","unstructured":"Zou, X., Yang, J., Zhang, H., Li, F., Li, L., Wang, J., & Lee, Y. J. (2023). Segment everything everywhere all at once. Advances in Neural Information Processing Systems, 35, 6575\u20136588.","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02165-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02165-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02165-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T10:26:52Z","timestamp":1731666412000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02165-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,12]]},"references-count":61,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["2165"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02165-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,12]]},"assertion":[{"value":"15 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}