{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:12:42Z","timestamp":1742926362207,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985395"},{"type":"electronic","value":"9789819985401"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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\/978-981-99-8540-1_23","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:01:32Z","timestamp":1703440892000},"page":"284-295","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Global Selection and\u00a0Local Attention Network for\u00a0Referring Image Segmentation"],"prefix":"10.1007","author":[{"given":"Haixin","family":"Ding","sequence":"first","affiliation":[]},{"given":"Shengchuan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Liujuan","family":"Cao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"23_CR1","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":"23_CR2","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Referring image segmentation via recurrent refinement networks. In: 2018 CVPR, pp. 5745\u20135753 (2018)","DOI":"10.1109\/CVPR.2018.00602"},{"key":"23_CR3","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: 2019 ICCV, pp. 7453\u20137462 (2019)","DOI":"10.1109\/ICCV.2019.00755"},{"key":"23_CR4","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 (2020)","DOI":"10.1145\/3394171.3414006"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Hui, T., et al.: Linguistic structure guided context modeling for referring image segmentation arXiv arXiv:2010.00515 (2020)","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Jiao, Y., et al.: Two-stage visual cues enhancement network for referring image segmentation. In: Proceedings of the 29th ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475222"},{"key":"23_CR7","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Semantics-aware dynamic localization and refinement for referring image segmentation. arXiv arXiv:2303.06345 (2023)","DOI":"10.1609\/aaai.v37i3.25428"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Margffoy-Tuay, E., P\u00e9rez, J., Botero, E., Arbel\u00e1ez, P.: Dynamic multimodal instance segmentation guided by natural language queries. arXiv arXiv:1807.02257 (2018)","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"23_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-01231-1_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Shi","year":"2018","unstructured":"Shi, H., Li, H., Meng, F., Wu, Q.: Key-word-aware network for referring expression image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 38\u201354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_3"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: 2019 CVPR, pp. 10494\u201310503 (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: 2020 CVPR, pp. 10031\u201310040 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"23_CR13","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: 2020 CVPR, pp. 4423\u20134432 (2020)","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"23_CR14","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: 2021 CVPR, pp. 15501\u201315510 (2021)","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"23_CR15","doi-asserted-by":"publisher","first-page":"3657","DOI":"10.1109\/TMM.2022.3163578","volume":"25","author":"C Liu","year":"2023","unstructured":"Liu, C., Jiang, X., Ding, H.: Instance-specific feature propagation for referring segmentation. IEEE Trans. Multimedia 25, 3657\u20133667 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: generalized referring expression segmentation (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: 2021 ICCV, pp. 16301\u201316310 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Misra, I., Synnaeve, G., Carion, N.: MDETR - modulated detection for end-to-end multi-modal understanding. In: 2021 ICCV, pp. 1760\u20131770 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: clip-driven referring image segmentation (2021)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Kim, N.H., Kim, D., Lan, C., Zeng, W., Kwak, S.: ReSTR: convolution-free referring image segmentation using transformers. arXiv arXiv:2203.16768 (2022)","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: LAVT: language-aware vision transformer for referring image segmentation. arXiv arXiv:2112.02244 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"23_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv arXiv:1706.03762 (2023)"},{"key":"23_CR23","doi-asserted-by":"publisher","first-page":"3054","DOI":"10.1109\/TIP.2023.3277791","volume":"32","author":"C Liu","year":"2023","unstructured":"Liu, C., Ding, H., Zhang, Y., Jiang, X.: Multi-modal mutual attention and iterative interaction for referring image segmentation. IEEE Trans. Image Process. 32, 3054\u20133065 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR24","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"23_CR25","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. arXiv arXiv:2010.11929 (2020)"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: modular attention network for referring expression comprehension. In: 2018 CVPR, pp. 1307\u20131315 (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Referring image segmentation via cross-modal progressive comprehension. In: 2020 CVPR, pp. 10485\u201310494 (2020)","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"23_CR28","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: 2021 CVPR, pp. 9853\u20139862 (2021)","DOI":"10.1109\/CVPR46437.2021.00973"},{"issue":"6","key":"23_CR29","doi-asserted-by":"publisher","first-page":"7900","DOI":"10.1109\/TPAMI.2022.3217852","volume":"45","author":"H Ding","year":"2023","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 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR30","unstructured":"D. P. Kingma, J. Ba, Adam: A method for stochastic optimization, CoRR abs\/1412.6980"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. arXiv arXiv:1608.00272 (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O.-M., Yuille, A. L., Murphy, K.P.: Generation and comprehension of unambiguous object descriptions. In: 2016 CVPR, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"23_CR33","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":"23_CR34","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.L.: ReferItGame: referring to objects in photographs of natural scenes. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z.L., Shen, X., Yang, J., Lu, X., Yuille, A.L.: Recurrent multimodal interaction for referring image segmentation. In: 2017 ICCV, pp. 1280\u20131289 (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: 2017 ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"23_CR37","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"}],"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\/978-981-99-8540-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:04:49Z","timestamp":1703441089000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8540-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819985395","9789819985401"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8540-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","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":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}