{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:32:50Z","timestamp":1743031970511,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756117"},{"type":"electronic","value":"9789819756124"}],"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\/978-981-97-5612-4_27","type":"book-chapter","created":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T13:03:51Z","timestamp":1722344631000},"page":"313-324","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fuse and Calibrate: A Bi-directional Vision-Language Guided Framework for Referring Image Segmentation"],"prefix":"10.1007","author":[{"given":"Yichen","family":"Yan","sequence":"first","affiliation":[]},{"given":"Xingjian","family":"He","sequence":"additional","affiliation":[]},{"given":"Sihan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shichen","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"key":"27_CR1","unstructured":"Cheng, Z., et al.: Parallel vertex diffusion for unified visual grounding. arXiv preprint arXiv:2303.07216 (2023)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Cho, Y., Yu, H., Kang, S.J.: Cross-aware early fusion with stage-divided vision and language transformer encoders for referring image segmentation. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3340062"},{"key":"27_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: VLT: vision-language transformer and query generation for referring segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"27_CR5","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, pp. 15506\u201315515 (2021)","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR7","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-319-46448-0_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Hu","year":"2016","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016. LNCS, vol. 9905, pp. 108\u2013124. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_7"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"27_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, pp. 18145\u201318154 (2022)","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"27_CR10","unstructured":"Li, M., Sigal, L.: Referring transformer: a one-step approach to multi-task visual grounding. In: Advances in Neural Information Processing Systems, vol. 34, pp. 19652\u201319664 (2021)"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Referring image segmentation via recurrent refinement networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2018)","DOI":"10.1109\/CVPR.2018.00602"},{"key":"27_CR12","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, pp. 1271\u20131280 (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR14","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, pp. 1274\u20131282 (2020)","DOI":"10.1145\/3394171.3414006"},{"key":"27_CR15","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1007\/978-3-319-46493-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"VK Nagaraja","year":"2016","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016. LNCS, vol. 9908, pp. 792\u2013807. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_48"},{"key":"27_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6629\u20136638 (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"27_CR18","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, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"27_CR19","unstructured":"Wang, Z., Liu, W., He, Q., Wu, X., Yi, Z.: CLIP-GEN: language-free training of a text-to-image generator with clip. arXiv preprint arXiv:2203.00386 (2022)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Wu, J., Li, X., Li, X., Ding, H., Tong, Y., Tao, D.: Towards robust referring image segmentation. arXiv preprint arXiv:2209.09554 (2023)","DOI":"10.1109\/TIP.2024.3371348"},{"key":"27_CR21","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, pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: modular attention network for referring expression comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1307\u20131315 (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\/978-981-97-5612-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T13:09:05Z","timestamp":1722344945000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5612-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756117","9789819756124"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5612-4_27","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":"31 July 2024","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":"Tianjin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}