{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:40:54Z","timestamp":1769186454184,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819555666","type":"print"},{"value":"9789819555673","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5567-3_32","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:21Z","timestamp":1769116401000},"page":"464-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bidirectional Spatial Semantics Correlation for\u00a0Referring Image Segmentation"],"prefix":"10.1007","author":[{"given":"Jiaxing","family":"Yang","sequence":"first","affiliation":[]},{"given":"Lihe","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jiayu","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Chng, Y.X., Zheng, H., Han, Y., Qiu, X., Huang, G.: Mask grounding for referring image segmentation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog. (2024)","DOI":"10.1109\/CVPR52733.2024.02509"},{"key":"32_CR2","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":"32_CR3","doi-asserted-by":"crossref","unstructured":"Ding, H., et al.: Bilateral knowledge interaction network for referring image segmentation. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3305869"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 16321\u201316330 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"32_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: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 15506\u201315515 (2021)","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: Proc. Eur. Conf. Comput. Vis., pp. 108\u2013124. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"32_CR7","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: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 4424\u20134433 (2020)","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Jing, Y., Kong, T., Wang, W., Wang, L., Li, L., Tan, T.: Locate then segment: a strong pipeline for referring image segmentation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 9858\u20139867 (2021)","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Empirical Methods in Natural Language Process, pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Kim, N.H., Kim, D., Lan, C., Zeng, W., Kwak, S.: ReSTR: convolution-free referring image segmentation using transformers. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 18124\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: LISA: reasoning segmentation via large language model. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 9579\u20139589 (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"32_CR12","unstructured":"Li, M., Sigal, L.: Referring transformer: a one-step approach to multi-task visual grounding. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Proc. Adv. Neural Inf. Process. Syst. (2021). https:\/\/openreview.net\/forum?id=J64lDCrYGi"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Zhang, Y., Jiang, X.: Multi-modal mutual attention and iterative interaction for referring image segmentation. IEEE Trans. Image Process (2023)","DOI":"10.1109\/TIP.2023.3277791"},{"issue":"1","key":"32_CR15","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s44267-024-00049-8","volume":"2","author":"C Liu","year":"2024","unstructured":"Liu, C., Jiang, X., Ding, H.: PrimitiveNet: decomposing the global constraints for referring segmentation. Vis. Intell. 2(1), 16 (2024)","journal-title":"Vis. Intell."},{"key":"32_CR16","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: Proc. IEEE Int. Conf. Comput. Vis., pp. 1271\u20131280 (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: PolyFormer: referring image segmentation as sequential polygon generation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 18653\u201318663 (2023)","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 10034\u201310043 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Tang, J., Zheng, G., Shi, C., Yang, S.: Contrastive grouping with transformer for referring image segmentation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 23570\u201323580 (2023)","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: CLIP-driven referring image segmentation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Wu, J., Li, X., Li, X., Ding, H., Tong, Y., Tao, D.: Towards robust referring image segmentation. IEEE Trans. Image Process (2024)","DOI":"10.1109\/TIP.2024.3371348"},{"issue":"4","key":"32_CR26","doi-asserted-by":"publisher","first-page":"3234","DOI":"10.1109\/TCSVT.2024.3508752","volume":"35","author":"M Xu","year":"2025","unstructured":"Xu, M., Xiao, T., Liu, Y., Tang, H., Hu, Y., Nie, L.: CMIRNet: cross-modal interactive reasoning network for referring image segmentation. IEEE Trans. Circuits Syst. Video Technol. 35(4), 3234\u20133249 (2025). https:\/\/doi.org\/10.1109\/TCSVT.2024.3508752","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Yang, J., Zhang, L., Lu, H.: Referring image segmentation with fine-grained semantic funneling infusion. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3281372"},{"key":"32_CR28","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: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 10502\u201310511 (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"32_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: Semantics-aware dynamic localization and refinement for referring image segmentation. In: Proc. AAAI Conf. Artif. Intell., vol.\u00a037, pp. 3222\u20133230 (2023)","DOI":"10.1609\/aaai.v37i3.25428"},{"key":"32_CR32","first-page":"19769","volume":"36","author":"X Zou","year":"2023","unstructured":"Zou, X.: Segment everything everywhere all at once. Proc. Adv. Neural Inf. Process. Syst. 36, 19769\u201319782 (2023)","journal-title":"Proc. Adv. Neural Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5567-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:27Z","timestamp":1769116407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5567-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819555666","9789819555673"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5567-3_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}