{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T11:10:09Z","timestamp":1747998609002,"version":"3.41.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031918551","type":"print"},{"value":"9783031918568","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91856-8_19","type":"book-chapter","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T10:35:10Z","timestamp":1747996510000},"page":"326-342","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Segment, Select, Correct: A Framework for\u00a0Weakly-Supervised Referring Segmentation"],"prefix":"10.1007","author":[{"given":"Francisco","family":"Eiras","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kemal","family":"Oksuz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adel","family":"Bibi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip H. S.","family":"Torr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puneet K.","family":"Dokania","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"19_CR1","first-page":"33781","volume":"35","author":"H Bangalath","year":"2022","unstructured":"Bangalath, H., Maaz, M., Khattak, M.U., Khan, S.H., Shahbaz Khan, F.: Bridging the gap between object and image-level representations for open-vocabulary detection. Adv. Neural. Inf. Process. Syst. 35, 33781\u201333794 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR2","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":"19_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Shen, Y., Gao, J., Liu, J., Liu, X.: Language-based image editing with recurrent attentive models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8721\u20138729 (2018)","DOI":"10.1109\/CVPR.2018.00909"},{"key":"19_CR4","unstructured":"Chen, J., et al.: Exploring open-vocabulary semantic segmentation without human labels. arXiv preprint arXiv:2306.00450 (2023)"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"19_CR6","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":"19_CR7","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16321\u201316330 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"19_CR8","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":"19_CR9","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Honnibal, M., Johnson, M.: An improved non-monotonic transition system for dependency parsing. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1373\u20131378 (2015)","DOI":"10.18653\/v1\/D15-1162"},{"key":"19_CR11","series-title":"Lecture Notes in Computer Science","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.) ECCV 2016. LNCS, vol. 9905, pp. 108\u2013124. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_7"},{"key":"19_CR12","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9858\u20139867 (2021)","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Kim, D., Kim, N., Lan, C., Kwak, S.: Shatter and gather: learning referring image segmentation with text supervision. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01425"},{"key":"19_CR14","unstructured":"Kirillov, A., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"19_CR15","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":"19_CR16","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":"19_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: Referring image segmentation using text supervision. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.02022"},{"key":"19_CR19","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":"19_CR20","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: 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"},{"key":"19_CR21","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":"19_CR22","doi-asserted-by":"crossref","unstructured":"Loper, E., Bird, S.: NLTK: the natural language toolkit. arXiv preprint cs\/0205028 (2002)","DOI":"10.3115\/1118108.1118117"},{"key":"19_CR23","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Margffoy-Tuay, E., P\u00e9rez, J.C., Botero, E., Arbel\u00e1ez, P.: Dynamic multimodal instance segmentation guided by natural language queries. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 630\u2013645 (2018)","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"19_CR25","unstructured":"Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. arXiv preprint arXiv:2306.09683 (2023)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Mukhoti, J., et al.: Open vocabulary semantic segmentation with patch aligned contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19413\u201319423 (2023)","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"19_CR27","series-title":"Lecture Notes in Computer Science","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.) ECCV 2016. LNCS, vol. 9908, pp. 792\u2013807. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_48"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Ouyang, S., et al.: Slvit: scale-wise language-guided vision transformer for referring image segmentation. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 1294\u20131302. International Joint Conferences on Artificial Intelligence Organization (2023)","DOI":"10.24963\/ijcai.2023\/144"},{"key":"19_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"19_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-319-46466-4_19","volume-title":"Computer Vision \u2013 ECCV 2016","author":"B Romera-Paredes","year":"2016","unstructured":"Romera-Paredes, B., Torr, P.: Recurrent instance segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 312\u2013329. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_19"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Shtedritski, A., Rupprecht, C., Vedaldi, A.: What does clip know about a red circle? visual prompt engineering for vlms. arXiv preprint arXiv:2304.06712 (2023)","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"19_CR32","unstructured":"Strudel, R., Laptev, I., Schmid, C.: Weakly-supervised segmentation of referring expressions. arXiv preprint arXiv:2205.04725 (2022)"},{"key":"19_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"19_CR34","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":"19_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Freesolo: learning to segment objects without annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14176\u201314186 (2022)","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., Girdhar, R., Yu, S.X., Misra, I.: Cut and learn for unsupervised object detection and instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3124\u20133134 (2023)","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"19_CR37","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":"19_CR38","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"},{"key":"19_CR39","unstructured":"Wu, J., Li, X., Li, X., Ding, H., Tong, Y., Tao, D.: Towards robust referring image segmentation. arXiv preprint arXiv:2209.09554 (2022)"},{"key":"19_CR40","unstructured":"Yang, L., Wang, Y., Li, X., Wang, X., Yang, J.: Fine-grained visual prompting. arXiv preprint arXiv:2306.04356 (2023)"},{"key":"19_CR41","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":"19_CR42","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, pp. 10502\u201310511 (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"19_CR43","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":"19_CR44","doi-asserted-by":"crossref","unstructured":"Yu, S., Seo, P.H., Son, J.: Zero-shot referring image segmentation with global-local context features. arXiv preprint arXiv:2303.17811 (2023)","DOI":"10.1109\/CVPR52729.2023.01864"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91856-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T10:35:33Z","timestamp":1747996533000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91856-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031918551","9783031918568"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91856-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}