{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:51:18Z","timestamp":1743094278401,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819786190"},{"type":"electronic","value":"9789819786206"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-981-97-8620-6_15","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"216-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual Context Perception Transformer for\u00a0Referring Image Segmentation"],"prefix":"10.1007","author":[{"given":"Yuqiu","family":"Kong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuili","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"15_CR1","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: Conference on Computer Vision and Pattern Recognition. pp. 1280\u20131289 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"15_CR2","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186 (2019)"},{"key":"15_CR3","doi-asserted-by":"publisher","first-page":"2966","DOI":"10.1109\/TMM.2023.3305869","volume":"26","author":"H Ding","year":"2024","unstructured":"Ding, H., Zhang, S., Wu, Q., Yu, S., Hu, J., Cao, L., Ji, R.: Bilateral knowledge interaction network for referring image segmentation. IEEE Trans. Multimedia 26, 2966\u20132977 (2024)","journal-title":"IEEE Trans. Multimedia"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: International Conference on Computer Vision, pp. 16301\u201316310 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"issue":"6","key":"15_CR5","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":"15_CR6","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"15_CR7","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: Conference on Computer Vision and Pattern Recognition. pp. 15506\u201315515 (2021)","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, L., Wu, G.: Lip: Local importance-based pooling. In: International Conference on Computer Vision, pp. 3355\u20133364 (2019)","DOI":"10.1109\/ICCV.2019.00345"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Hu, Y., Wang, Q., Shao, W., Xie, E., Li, Z., Han, J., Luo, P.: Beyond one-to-one: Rethinking the referring image segmentation. In: International Conference on Computer Vision, pp. 4067\u20134077 (2023)","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Huang, S., Hui, T., Liu, S., Li, G., Wei, Y., Han, J., Liu, L., Li, B.: Referring image segmentation via cross-modal progressive comprehension. In: Conference on Computer Vision and Pattern Recognition, pp. 10485\u201310494 (2020)","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Hui, T., Liu, S., Huang, S., Li, G., Yu, S., Zhang, F., Han, J.: Linguistic structure guided context modeling for referring image segmentation. In: European Conference on Computer Vision, pp. 59\u201375 (2020)","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"15_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: Conference on Computer Vision and Pattern Recognition, pp. 9858\u20139867 (2021)","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr - modulated detection for end-to-end multi-modal understanding. In: International Conference on Computer Vision, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Kim, N., Kim, D., Lan, C., Zeng, W., Kwak, S.: Restr: convolution-free referring image segmentation using transformers. In: Conference on Computer Vision and Pattern Recognition, pp. 18145\u201318154 (2022)","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"15_CR15","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594 (2021)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Li, R., Li, K., Kuo, Y.C., Shu, M., Qi, X., Shen, X., Jia, J.: Referring image segmentation via recurrent refinement networks. In: Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2018)","DOI":"10.1109\/CVPR.2018.00602"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Sun, X., Meng, Y., Liang, J., Wu, F., Li, J.: Dice loss for data-imbalanced NLP tasks (2019). arXiv:1911.02855","DOI":"10.18653\/v1\/2020.acl-main.45"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Liu, S.A., Zhang, Y., Qiu, Z., Xie, H., Zhang, Y., Yao, T.: Caris: context-aware referring image segmentation. In: International Conference on Multimedia, pp. 779\u2013788 (2023)","DOI":"10.1145\/3581783.3612117"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"15_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Luo, G., Zhou, Y., Ji, R., Sun, X., Su, J., Lin, C.W., Tian, Q.: Cascade grouped attention network for referring expression segmentation. In: ACM International Conference on Multimedia, pp. 1274\u20131282 (2020)","DOI":"10.1145\/3394171.3414006"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Luo, G., Zhou, Y., Sun, X., Cao, L., Wu, C., Deng, C., Ji, R.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Conference on Computer Vision and Pattern Recognition, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Margffoy-Tuay, E., Perez, J.C., Botero, E., Arbelaez, P.: Dynamic multimodal instance segmentation guided by natural language queries. In: European Conference on Computer Vision, pp. 656\u2013672 (2018)","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"15_CR26","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: Clipcap: CLIP prefix for image captioning. CoRR (2021). arXiv:abs\/2111.09734"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Ouyang, S., Wang, H., Xie, S., Niu, Z., Tong, R., Chen, Y.W., Lin, L.: Slvit: scale-wise language-guided vision transformer for referring image segmentation. In: International Joint Conference on Artificial Intelligence, pp. 1294\u20131302 (2023)","DOI":"10.24963\/ijcai.2023\/144"},{"key":"15_CR28","unstructured":"Ridnik, T., Ben-Baruch, E., Noy, A., Zelnik-Manor, L.: Imagenet-21k pretraining for the masses (2021). arXiv:2104.10972"},{"key":"15_CR29","unstructured":"Shen, S., Li, L.H., Tan, H., Bansal, M., Rohrbach, A., Chang, K.W., Yao, Z., Keutzer, K.: How much can clip benefit vision-and-language tasks? In: International Conference on Learning Representations (2022)"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Shi, H., Li, H., Meng, F., Wu, Q.: Key-word-aware network for referring expression image segmentation. In: European Conference on Computer Vision, pp. 35\u201354 (2018)","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Tang, J., Zheng, G., Shi, C., Yang, S.: Contrastive grouping with transformer for referring image segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 23570\u201323580 (2023)","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"15_CR32","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Annual Conference on Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"15_CR33","unstructured":"Velikovi, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Le\u00a0Scao, T., Gugger, S., Drame, M., Lhoest, Q., Rush, A.M.: Transformers: state-of-the-art natural language processing. In: Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chen, Z., Zhang, Y., Song, Y., Wan, X., Li, G.: Bridging vision and language encoders: parameter-efficient tuning for referring image segmentation. In: International Conference on Computer Vision, pp. 17503\u201317512 (2023)","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"15_CR36","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: Conference on Computer Vision and Pattern Recognition, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: Semantics-aware dynamic localization and refinement for referring image segmentation. In: Conference on Artificial Intelligence, pp. 3222\u20133230 (2023)","DOI":"10.1609\/aaai.v37i3.25428"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Yu, L., Lin, Z., Shen, X., Yang, J., Lu, X., Bansal, M., Berg, T.L.: Mattnet: modular attention network for referring expression comprehension. In: Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: European Conference on Computer Vision, pp. 69\u201385 (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Yu, S., Seo, P.H., Son, J.: Zero-shot referring image segmentation with global-local context features. In: Conference on Computer Vision and Pattern Recognition, pp. 19456\u201319465 (2023)","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"15_CR42","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021)"}],"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\/978-981-97-8620-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:18:22Z","timestamp":1736885902000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","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":"Urumqi","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}