{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:45:49Z","timestamp":1742960749861,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756148"},{"type":"electronic","value":"9789819756155"}],"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\/978-981-97-5615-5_23","type":"book-chapter","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T13:12:02Z","timestamp":1722604322000},"page":"278-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Referring Image Segmentation Without Text Annotations"],"prefix":"10.1007","author":[{"given":"Jing","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huajie","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yandong","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongli","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,3]]},"reference":[{"key":"23_CR1","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":"23_CR2","doi-asserted-by":"crossref","unstructured":"Pathak, D., et al.: Zero-shot visual imitation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2050\u20132053 (2018)","DOI":"10.1109\/CVPRW.2018.00278"},{"key":"23_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":"23_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107885","volume":"115","author":"J Zhang","year":"2021","unstructured":"Zhang, J., et al.: LCU-Net: a novel low-cost u-net for environmental microorganism image segmentation. Pattern Recogn. 115, 107885 (2021)","journal-title":"Pattern Recogn."},{"key":"23_CR5","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":"23_CR6","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":"23_CR7","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":"23_CR8","unstructured":"Feng, G., Zhang, L., Hu, Z., Lu, H.: Learning from box annotations for referring image segmentation. IEEE Trans. Neural Networks Learn. Syst. (2022)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yu, X., Li, A., Song, P., Liu, B., Dai, Y.: Weakly-supervised salient object detection via scribble annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12546\u201312555 (2020)","DOI":"10.1109\/CVPR42600.2020.01256"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Yu, S., Zhang, B., Xiao, J., Lim, E.G.: Structure-consistent weakly supervised salient object detection with local saliency coherence. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 3234\u20133242 (2021)","DOI":"10.1609\/aaai.v35i4.16434"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, B., Parkhi, O., Kirillov, A.: Pointly-supervised instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2617\u20132626 (2022)","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"23_CR12","unstructured":"Strudel, R., Laptev, I., Schmid, C.: Weakly-supervised segmentation of referring expressions. arXiv preprint arXiv:2205.04725 (2022)"},{"key":"23_CR13","first-page":"10326","volume":"34","author":"W Zhang","year":"2021","unstructured":"Zhang, W., Pang, J., Chen, K., Loy, C.C.: K-net: Towards unified image segmentation. Adv. Neural. Inf. Process. Syst. 34, 10326\u201310338 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR14","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":"23_CR15","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"23_CR16","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"23_CR17","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, PMLR, pp. 8748\u20138763 (2021)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Hsia, H.-A., et al.: CLIPCAM: a simple baseline for zero-shot text-guided object and action localization. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4453\u20134457. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747841"},{"key":"23_CR19","doi-asserted-by":"publisher","unstructured":"Chen, L., Zheng, Y., Xiao, J.: Rethinking data augmentation for robust visual question answering. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 95\u2013112. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_6","DOI":"10.1007\/978-3-031-20059-5_6"},{"key":"23_CR20","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":"23_CR21","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_CR22","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":"23_CR23","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4424\u20134433 (2020)","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"23_CR24","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":"23_CR25","doi-asserted-by":"crossref","unstructured":"Yu, S., Seo, P.H., Son, J.: Zero-shot referring image segmentation with global-local context features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19456\u201319465 (2023)","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"23_CR26","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":"23_CR27","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, PMLR, pp. 4904\u20134916 (2021)"},{"key":"23_CR28","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Bertini, M., Uricchio, T., Del Bimbo, A.: Effective conditioned and composed image retrieval combining clip-based features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21466\u201321474 (2022)","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"23_CR30","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: ClipCap: clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Subramanian, S., Merrill, W., Darrell, T., Gardner, M., Singh, S., Rohrbach, A.: ReCLIP: a strong zero-shot baseline for referring expression comprehension. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5198\u20135215 (2022)","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"23_CR32","unstructured":"Li, J., Shakhnarovich, G., Yeh, R.A.: Adapting clip for phrase localization without further training, arXiv preprint arXiv:2204.03647 13 (2022)"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"23_CR34","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 Conference on Empirical Methods in Natural Language Processing, pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"23_CR35","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_CR36","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":"23_CR37","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization, arXiv preprint arXiv:1711.05101 (2017)"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-Cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"23_CR39","doi-asserted-by":"publisher","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from CLIP. In: Avidan, S., et al. (eds.) ECCV 2022. LNCS, vol.13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40","DOI":"10.1007\/978-3-031-19815-1_40"}],"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\/978-981-97-5615-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T11:05:42Z","timestamp":1731150342000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5615-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756148","9789819756155"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5615-5_23","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":"3 August 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"}}]}}