{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T04:47:21Z","timestamp":1785646041744,"version":"3.56.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316721","type":"print"},{"value":"9783032316738","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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\/978-3-032-31673-8_41","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T04:26:43Z","timestamp":1785644803000},"page":"616-630","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Resolving the\u00a0Inherent Contextual Insufficiency in\u00a0Referring Image Segmentation with\u00a0Global Semantic Priors"],"prefix":"10.1007","author":[{"given":"Chong","family":"Yi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seigo","family":"Ito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Murase","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daisuke","family":"Deguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"41_CR1","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers, arXiv preprint arXiv:2106.08254 (2021)"},{"key":"41_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"issue":"3","key":"41_CR3","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/s11263-025-02648-4","volume":"134","author":"J Chen","year":"2026","unstructured":"Chen, J., et al.: Semantic-centric alignment for zero-shot panoptic segmentation with limited data. Int. J. Comput. Vision 134(3), 122 (2026)","journal-title":"Int. J. Comput. Vision"},{"key":"41_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110431","volume":"152","author":"J Chen","year":"2024","unstructured":"Chen, J., Deguchi, D., Zhang, C., Zheng, X., Murase, H.: Frozen is better than learning: a new design of prototype-based classifier for semantic segmentation. Pattern Recogn. 152, 110431 (2024)","journal-title":"Pattern Recogn."},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Semantic-driven distillation for semantic segmentation with unknown classes. In: 2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), pp. 2655\u20132662. IEEE (2025)","DOI":"10.1109\/ITSC60802.2025.11423504"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Quan, Z., Zhang, C., Zheng, X., Deguchi, D., Murase, H.: Clip-to-Seg distillation for zero-shot semantic segmentation. In: IEEE Trans. Circ. Syst. Video Technol. (2025)","DOI":"10.1109\/TCSVT.2025.3616588"},{"key":"41_CR7","unstructured":"Chen, J., et al.: Split matching for inductive zero-shot semantic segmentation. In: 36th British Machine Vision Conference 2025, BMVC 2025, Sheffield, UK, 24\u201327 November 2025. BMVA (2025)"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Chen, J., Zheng, X., Paudel, D.P., Van Gool, L., Murase, H., Deguchi, D.: Bixformer: a robust framework for maximizing modality effectiveness in multi-modal semantic segmentation, arXiv preprint arXiv:2506.03675 (2025)","DOI":"10.1109\/TMM.2026.3703333"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Dai, M., et al.: DeRIS: aecoupling perception and cognition for enhanced referring image segmentation through loopback synergy. arXiv preprint arXiv:2507.01738 (2025)","DOI":"10.1109\/ICCV51701.2025.01854"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"issue":"6","key":"41_CR12","doi-asserted-by":"publisher","first-page":"7900","DOI":"10.1109\/TPAMI.2022.3217852","volume":"45","author":"H Ding","year":"2022","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. 45(6), 7900\u20137916 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR13","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, pp. 10488\u201310497 (2020)","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"41_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-030-58607-2_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Hui","year":"2020","unstructured":"Hui, T., et al.: Linguistic structure guided context modeling for referring image segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 59\u201375. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_4"},{"key":"41_CR15","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":"41_CR16","unstructured":"Kim, S., Kang, M., Park, J.: RISCLIP: referring image segmentation framework using clip, CoRR (2023)"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: LISA: reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9579\u20139589 (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"41_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: generalized referring expression segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23592\u201323601 (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"41_CR20","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, pp. 18653\u201318663 (2023)","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"issue":"9","key":"41_CR22","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":"41_CR23","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":"41_CR24","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10034\u201310043 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"Nguyen-Truong, H., Nguyen, E.R., Vu, T.A., Tran, M.T., Hua, B.S., Yeung, S.K.: Vision-aware text features in referring image segmentation: from object understanding to context understanding. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4988\u20134998. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00488"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18082\u201318091 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: PixelLM: pixel reasoning with large multimodal model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26374\u201326383 (2024)","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Shang, C., Song, Z., Qiu, H., Wang, L., Meng, F., Li, H.: Prompt-driven referring image segmentation with instance contrasting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4124\u20134134 (2024)","DOI":"10.1109\/CVPR52733.2024.00395"},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Su, W., et al.: Language adaptive weight generation for multi-task visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10857\u201310866 (2023)","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"41_CR30","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":"41_CR31","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Sun, P., Yuan, Z., Luo, P.: Language as queries for referring video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4974\u20134984 (2022)","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Yan, B., et al.: Universal instance perception as object discovery and retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15325\u201315336 (2023)","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"41_CR33","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":"41_CR34","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"},{"key":"41_CR35","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"},{"issue":"9","key":"41_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. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, C., et al.: SeqTR: a simple yet universal network for visual grounding. In: European Conference on Computer Vision, pp. 598\u2013615. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"41_CR38","doi-asserted-by":"crossref","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. In: NeurIPS (2023)","DOI":"10.52202\/075280-0868"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31673-8_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T04:26:46Z","timestamp":1785644806000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31673-8_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316721","9783032316738"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31673-8_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}