{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:57:05Z","timestamp":1780675025738,"version":"3.54.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734137","type":"print"},{"value":"9783031734144","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73414-4_23","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:02:54Z","timestamp":1729789374000},"page":"399-416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Collaborative Vision-Text Representation Optimizing for\u00a0Open-Vocabulary Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0795-8401","authenticated-orcid":false,"given":"Siyu","family":"Jiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1356-5153","authenticated-orcid":false,"given":"Hongguang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2447-9928","authenticated-orcid":false,"given":"Jiannan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-8781","authenticated-orcid":false,"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2922-5663","authenticated-orcid":false,"given":"Humphrey","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"23_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR2","unstructured":"Bucher, M., Vu, T.H., Cord, M., P\u00e9rez, P.: Zero-shot semantic segmentation. Advances in Neural Information Processing Systems 32 (2019)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"issue":"4","key":"23_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":"23_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Li, S., Lim, S.N., Torralba, A., Zhao, H.: Open-vocabulary panoptic segmentation with embedding modulation. arXiv preprint arXiv:2303.11324 (2023)","DOI":"10.1109\/ICCV51070.2023.00111"},{"key":"23_CR6","unstructured":"Cheng, B., Choudhuri, A., Misra, I., Kirillov, A., Girdhar, R., Schwing, A.G.: Mask2former for video instance segmentation. arXiv preprint arXiv:2112.10764 (2021)"},{"key":"23_CR7","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Advances in Neural Information Processing Systems 34 (2021)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"23_CR9","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.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Fang, Y., Zhu, F., Cheng, B., Liu, L., Zhao, Y., Wei, Y.: Locating noise is halfway denoising for semi-supervised segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16612\u201316622 (2023)","DOI":"10.1109\/ICCV51070.2023.01523"},{"key":"23_CR11","doi-asserted-by":"publisher","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVI, pp. 540\u2013557. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_31","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Gu, Z., Zhou, S., Niu, L., Zhao, Z., Zhang, L.: Context-aware feature generation for zero-shot semantic segmentation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1921\u20131929 (2020)","DOI":"10.1145\/3394171.3413593"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Han, K., Liu, Y., Liew, J.H., Ding, H., Wei, Y., Liu, J., Wang, Y., Tang, Y., Yang, Y., Feng, J., et\u00a0al.: Global knowledge calibration for fast open-vocabulary segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00080"},{"key":"23_CR14","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"},{"issue":"1","key":"23_CR15","first-page":"550","volume":"44","author":"Z Huang","year":"2021","unstructured":"Huang, Z., Wei, Y., Wang, X., Liu, W., Huang, T.S., Shi, H.: Alignseg: feature-aligned segmentation networks. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 550\u2013557 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"23_CR16","first-page":"5","volume":"2","author":"G Ilharco","year":"2021","unstructured":"Ilharco, G., et al.: Openclip, July 2021. If you use this software, please cite it as below 2(4), 5 (2021)","journal-title":"If you use this software, please cite it as below"},{"key":"23_CR17","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"23_CR18","unstructured":"Jiao, S., Wei, Y., Wang, Y., Zhao, Y., Shi, H.: Learning mask-aware clip representations for zero-shot segmentation. Advances in Neural Information Processing Systems 36 (2023)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9404\u20139413 (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"issue":"1\u20132","key":"23_CR20","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logistics Quarterly 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logistics Quarterly"},{"key":"23_CR21","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=RriDjddCLN"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol.\u00a024, pp. 109\u2013165. Elsevier (1989)","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"23_CR25","unstructured":"Qin, J., et\u00a0al.: Freeseg: Unified, universal and open-vocabulary image segmentation. arXiv preprint arXiv:2303.17225 (2023)"},{"key":"23_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Shaban, A., Bansal, S., Liu, Z., Essa, I., Boots, B.: One-shot learning for semantic segmentation. arXiv preprint arXiv:1709.03410 (2017)","DOI":"10.5244\/C.31.167"},{"key":"23_CR29","unstructured":"Sun, Y., et al.: Singular value fine-tuning: Few-shot segmentation requires few-parameters fine-tuning. arXiv preprint arXiv:2206.06122 (2022)"},{"key":"23_CR30","unstructured":"Touvron, H., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Xian, Y., Choudhury, S., He, Y., Schiele, B., Akata, Z.: Semantic projection network for zero-and few-label semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8256\u20138265 (2019)","DOI":"10.1109\/CVPR.2019.00845"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Xiao, J.W., Zhang, C.B., Feng, J., Liu, X., van\u00a0de Weijer, J., Cheng, M.M.: Endpoints weight fusion for class incremental semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7204\u20137213 (2023)","DOI":"10.1109\/CVPR52729.2023.00696"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Xu, J., De\u00a0Mello, S., Liu, S., Byeon, W., Breuel, T., Kautz, J., Wang, X.: Groupvit: Semantic segmentation emerges from text supervision. CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"23_CR36","doi-asserted-by":"publisher","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXIX, pp. 736\u2013753. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"23_CR37","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., Chen, L.C.: Convolutions die hard: open-vocabulary segmentation with single frozen convolutional clip. Advances in Neural Information Processing Systems 36 (2023)"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, C.B., Xiao, J.W., Liu, X., Chen, Y.C., Cheng, M.M.: Representation compensation networks for continual semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7053\u20137064 (2022)","DOI":"10.1109\/CVPR52688.2022.00692"},{"key":"23_CR39","first-page":"823","volume":"35","author":"G Zhang","year":"2022","unstructured":"Zhang, G., Navasardyan, S., Chen, L., Zhao, Y., Wei, Y., Shi, H., et al.: Mask matching transformer for few-shot segmentation. Adv. Neural. Inf. Process. Syst. 35, 823\u2013836 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, G., Wang, L., Kang, G., Chen, L., Wei, Y.: Slca: slow learner with classifier alignment for continual learning on a pre-trained model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19148\u201319158 (2023)","DOI":"10.1109\/ICCV51070.2023.01754"},{"key":"23_CR41","first-page":"24340","volume":"35","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., Gao, G., Fang, Z., Jiao, J., Wei, Y.: Mining unseen classes via regional objectness: a simple baseline for incremental segmentation. Adv. Neural. Inf. Process. Syst. 35, 24340\u201324353 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Gao, G., Jiao, J., Liu, C.H., Wei, Y.: Coinseg: Contrast inter-and intra-class representations for incremental segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00084"},{"key":"23_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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"23_CR44","unstructured":"Zheng\u00a0Ding, Jieke\u00a0Wang, Z.T.: Open-vocabulary universal image segmentation with maskclip. In: International Conference on Machine Learning (2023)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73414-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:12:07Z","timestamp":1729789927000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73414-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031734137","9783031734144"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73414-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}