{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:52:47Z","timestamp":1743007967169,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533044"},{"type":"electronic","value":"9783031533051"}],"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\/978-3-031-53305-1_14","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"172-186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["\u201cCar or\u00a0Bus?\" CLearSeg: CLIP-Enhanced Discrimination Among Resembling Classes for\u00a0Few-Shot Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2112-8199","authenticated-orcid":false,"given":"Anqi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0083-3016","authenticated-orcid":false,"given":"Guangyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0117-1473","authenticated-orcid":false,"given":"Zhuocheng","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4394-7629","authenticated-orcid":false,"given":"Yukun","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Boudiaf, M., Kervadec, H., Masud, Z.I., Piantanida, P., Ben Ayed, I., Dolz, J.: Few-shot segmentation without meta-learning: a good transductive inference is all you need? In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 13979\u201313988 (2021)","DOI":"10.1109\/CVPR46437.2021.01376"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"14_CR3","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Inter. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Inter. J. Comput. Vis."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Fan, Q., Pei, W., Tai, Y.W., Tang, C.K.: Self-support few-shot semantic segmentation. In: Proceedings of European Conference on Computer Vision, pp. 701\u2013719 (2022)","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"14_CR5","unstructured":"Gao, P., Geng, S., Zhang, R., et al.: Clip-adapter: better vision-language models with feature adapters. arXiv preprint arXiv:2110.04544 (2021)"},{"key":"14_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-319-10584-0_20","volume-title":"Computer Vision \u2013 ECCV 2014","author":"B Hariharan","year":"2014","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 297\u2013312. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_20"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR8","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: Proceedings of European Conference on Computer Vision. pp. 108\u2013126 (2022)","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Lang, C., Cheng, G., Tu, B., Han, J.: Learning what not to segment: a new perspective on few-shot segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 8057\u20138067 (2022)","DOI":"10.1109\/CVPR52688.2022.00789"},{"key":"14_CR10","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., et a.: Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546 (2022)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Li, G., Jampani, V., Sevilla-Lara, L., Sun, D., Kim, J., Kim, J.: Adaptive prototype learning and allocation for few-shot segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 8334\u20138343 (2021)","DOI":"10.1109\/CVPR46437.2021.00823"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Liang, F., Wu, B., Dai, X., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. arXiv preprint arXiv:2210.04150 (2022)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"14_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"14_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-030-58545-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Zhang, X., Zhang, S., He, X.: Part-aware prototype network for few-shot semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 142\u2013158. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_9"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, N., Cao, Q., et al.: Learning non-target knowledge for few-shot semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 11573\u201311582 (2022)","DOI":"10.1109\/CVPR52688.2022.01128"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, N., Yao, X., Han, J.: Intermediate prototype mining transformer for few-shot semantic segmentation. In: Proceedings of Neural Information Processing Systems (2022)","DOI":"10.1109\/CVPR52688.2022.01128"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Lu, Z., He, S., Zhu, X., Zhang, L., Song, Y.Z., Xiang, T.: Simpler is better: few-shot semantic segmentation with classifier weight transformer. In: Proceedings of IEEE International Conference on Computer Vision, pp. 8741\u20138750 (2021)","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., Cho, M.: Hypercorrelation squeeze for few-shot segmentation. In: Proceedings of IEEE International Conference on Computer Vision, pp. 6941\u20136952 (2021)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Moon, S., Sohn, S.S., Zhou, H., et al.: Hm: hybrid masking for few-shot segmentation. In: Proceedings of European Conference on Computer Vision, pp. 506\u2013523 (2022)","DOI":"10.1007\/978-3-031-20044-1_29"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Moon, S., Sohn, S.S., Zhou, H., et al.: Msi: maximize support-set information for few-shot segmentation. arXiv preprint arXiv:2212.04673 (2022)","DOI":"10.1109\/ICCV51070.2023.01765"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Todorovic, S.: Feature weighting and boosting for few-shot segmentation. In: Proceedings of IEEE International Conference on Computer Vision, pp. 622\u2013631 (2019)","DOI":"10.1109\/ICCV.2019.00071"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Okazawa, A.: Interclass prototype relation for few-shot segmentation. In: Proceedings of European Conference on Computer Vision, pp. 362\u2013378 (2022)","DOI":"10.1007\/978-3-031-19818-2_21"},{"key":"14_CR23","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Shaban, A., Bansal, S., Liu, Z., Essa, I., Boots, B.: One-shot learning for semantic segmentation. In: Proceedings of British Machine Vision Conference, pp. 167.1-167.13 (2017)","DOI":"10.5244\/C.31.167"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Shi, X., et al.: Dense cross-query-and-support attention weighted mask aggregation for few-shot segmentation. In: Proceedings of European Conference on Computer Vision, pp. 151\u2013168 (2022)","DOI":"10.1007\/978-3-031-20044-1_9"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)","DOI":"10.1109\/ICCV.2015.314"},{"issue":"2","key":"14_CR27","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","volume":"44","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Zhao, H., Shu, M., Yang, Z., Li, R., Jia, J.: Prior guided feature enrichment network for few-shot segmentation. IEEE Trans. Pattern Recog. Mach. Intell. 44(2), 1050\u20131065 (2020)","journal-title":"IEEE Trans. Pattern Recog. Mach. Intell."},{"key":"14_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Proceedings of Neural Information Processing Systems 30 (2017)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: Panet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of IEEE International Conference on Computer Vision, pp. 9197\u20139206 (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Li, H., Zhu, X.X.: Doubly deformable aggregation of covariance matrices for few-shot segmentation. In: Proceedings of European Conference on Computer Vision, pp. 133\u2013150 (2022)","DOI":"10.1007\/978-3-031-20044-1_8"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lin, G., Liu, F., Guo, J., Wu, Q., Yao, R.: Pyramid graph networks with connection attentions for region-based one-shot semantic segmentation. In: Proceedings of IEEE International Conference on Computer Vision, pp. 9587\u20139595 (2019)","DOI":"10.1109\/ICCV.2019.00968"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lin, G., Liu, F., Yao, R., Shen, C.: Canet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5217\u20135226 (2019)","DOI":"10.1109\/CVPR.2019.00536"},{"key":"14_CR33","first-page":"21984","volume":"34","author":"G Zhang","year":"2021","unstructured":"Zhang, G., Kang, G., Yang, Y., Wei, Y.: Few-shot segmentation via cycle-consistent transformer. Proc. Neural Inform. Process. Syst. 34, 21984\u201321996 (2021)","journal-title":"Proc. Neural Inform. Process. Syst."},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhang, W., Fang, R., eg al.: Tip-adapter: training-free adaption of clip for few-shot classification. In: Proceedings of European Conference on Computer Vision, pp. 493\u2013510 (2022)","DOI":"10.1007\/978-3-031-19833-5_29"},{"issue":"9","key":"14_CR35","doi-asserted-by":"publisher","first-page":"3855","DOI":"10.1109\/TCYB.2020.2992433","volume":"50","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Wei, Y., Yang, Y., Huang, T.S.: Sg-one: similarity guidance network for one-shot semantic segmentation. IEEE Trans. Cybern. 50(9), 3855\u20133865 (2020)","journal-title":"IEEE Trans. Cybern."},{"issue":"9","key":"14_CR36","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Inter. J. Comput. Vis. 130(9), 2337\u20132348 (2022)","journal-title":"Inter. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53305-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T09:56:18Z","timestamp":1731146178000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53305-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533044","9783031533051"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53305-1_14","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":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"112","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}