{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T14:01:49Z","timestamp":1784469709305,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233779","type":"print"},{"value":"9789819233786","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3378-6_40","type":"book-chapter","created":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T13:01:45Z","timestamp":1784466105000},"page":"484-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Independent Vision and Language Adapters for Referring Image Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2877-8960","authenticated-orcid":false,"given":"Qiang","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9455-5327","authenticated-orcid":false,"given":"Yu","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9122-6123","authenticated-orcid":false,"given":"Lu","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6595-6893","authenticated-orcid":false,"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"40_CR1","unstructured":"Chen, B., Hu, Z., Ji, Z., Bai, J., Zuo, W.: Position-aware contrastive alignment for referring image segmentation. arXiv preprint arXiv:2212.13419 (2022)"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Chen, D.J., Jia, S., Lo, Y.C., Chen, H.T., Liu, T.L.: See-through-text grouping for referring image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7454\u20137463 (2019)","DOI":"10.1109\/ICCV.2019.00755"},{"key":"40_CR3","unstructured":"Chen, Y.W., Tsai, Y.H., Wang, T., Lin, Y.Y., Yang, M.H.: Referring expression object segmentation with caption-aware consistency. arXiv preprint arXiv:1910.04748 (2019)"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Feng, G., Hu, Z., Zhang, L., Lu, H.: Encoder fusion network with co-attention embedding for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: roceedings of the European Conference on Computer Vision (ECCV), pp. 108\u2013124. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Hu, Z., Feng, G., Sun, J., Zhang, L., Lu, H.: Bi-directional relationship inferring network for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Referring image segmentation via cross-modal progressive comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Hui, T., et al.: Linguistic structure guided context modeling for referring image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Kim, N., Kim, D., Lan, C., Zeng, W., Kwak, S.: ReSTR: Convolution-free referring image segmentation using transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18145\u201318154 (2022)","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Referring image segmentation via recurrent refinement networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00602"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: PolyFormer: Referring image segmentation as sequential polygon generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18653\u201318663 (2023)","DOI":"10.1109\/CVPR52729.2023.01789"},{"issue":"9","key":"40_CR13","first-page":"4761","volume":"44","author":"S Liu","year":"2021","unstructured":"Liu, S., Hui, T., Huang, S., Wei, Y., Li, B., Li, G.: Cross-modal progressive comprehension for referring segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 4761\u20134775 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR14","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), pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"40_CR15","unstructured":"Lu, H., et al.: Uni-Adapter: Unified parameter-efficient transfer learning for cross-modal modeling. arXiv preprint arXiv:2302.06605 (2023)"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Cascade grouped attention network for referring expression segmentation. In: Proceedings of the 28th ACM International Conference on Multimedia (ACM MM) (2020)","DOI":"10.1145\/3394171.3414006"},{"key":"40_CR17","unstructured":"Sun, J., Qin, J., Lin, Z., Chen, C.: Prompt tuning based adapter for vision-language model adaption. arXiv preprint arXiv:2303.15234 (2023)"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Sung, Y.L., Cho, J., Bansal, M.: VL-Adapter: Parameter-efficient transfer learning for vision-and-language tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5227\u20135237 (2022)","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"40_CR19","unstructured":"Tziafas, G., Kasaei, H.: Towards open-world grasping with large vision-language models. arXiv preprint arXiv:2406.18722 (2024)"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: CLIP-driven referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chen, Z., Zhang, Y., Song, Y., Wan, X., Li, G.: Bridging vision and language encoders: parameter-efficient tuning for referring image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17503\u201317512 (2023)","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4644\u20134653 (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Yang, S., Xia, M., Li, G., Zhou, H.Y., Yu, Y.: Bottom-up shift and reasoning for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11266\u201311275 (2021)","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: LAVT: Language-aware vision transformer for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: Modular attention network for referring expression comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00142"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3378-6_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T13:01:49Z","timestamp":1784466109000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3378-6_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"ISBN":["9789819233779","9789819233786"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3378-6_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"assertion":[{"value":"20 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}