{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:38:27Z","timestamp":1740166707192,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T00:00:00Z","timestamp":1690588800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T00:00:00Z","timestamp":1690588800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61873274"],"award-info":[{"award-number":["61873274"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s13735-023-00282-9","type":"journal-article","created":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T10:01:56Z","timestamp":1690624916000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical bidirectional aggregation with prior guided transformer for few-shot segmentation"],"prefix":"10.1007","volume":"12","author":[{"given":"Qiuyu","family":"Kong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,29]]},"reference":[{"key":"282_CR1","doi-asserted-by":"publisher","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440. https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"2","key":"282_CR2","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vision 88(2):303\u2013338. https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int J Comput Vision"},{"key":"282_CR3","doi-asserted-by":"publisher","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223. https:\/\/doi.org\/10.1109\/CVPR.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"key":"282_CR4","doi-asserted-by":"publisher","DOI":"10.5244\/c.31.167","author":"A Shaban","year":"2017","unstructured":"Shaban A, Bansal S, Liu Z, Essa I, Boots B (2017). One-shot learning for semantic segmentation. https:\/\/doi.org\/10.5244\/c.31.167","journal-title":"One-shot learning for semantic segmentation"},{"key":"282_CR5","doi-asserted-by":"crossref","unstructured":"Wang K, Liew J.H, Zou Y, Zhou D, Feng J (2019) Panet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9197\u20139206","DOI":"10.1109\/ICCV.2019.00929"},{"key":"282_CR6","doi-asserted-by":"publisher","unstructured":"Li G, Jampani V, Sevilla-Lara L, Sun D, Kim J, Kim J (2021) Adaptive prototype learning and allocation for few-shot segmentation. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr46437.2021.00823","DOI":"10.1109\/cvpr46437.2021.00823"},{"key":"282_CR7","doi-asserted-by":"publisher","unstructured":"Liu Y, Zhang X, Zhang S, He X (2020) Part-aware prototype network for few-shot semantic segmentation. In: Computer vision\u2014ECCV 2020, pp 142\u2013158. https:\/\/doi.org\/10.1007\/978-3-030-58545-7_9","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"282_CR8","doi-asserted-by":"publisher","unstructured":"Zhang C, Lin G, Liu F, Yao R, Shen C (2019) CANet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr.2019.00536","DOI":"10.1109\/cvpr.2019.00536"},{"key":"282_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/pami.2020.3013717","author":"Z Tian","year":"2020","unstructured":"Tian Z, Zhao H, Shu M, Yang Z, Li R, Jia J (2020) Prior guided feature enrichment network for few-shot segmentation. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/pami.2020.3013717","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"282_CR10","unstructured":"Luo X, Tian Z, Zhang T, Yu B, Tang Y.Y, Jia J (2021) Pfenet++: Boosting few-shot semantic segmentation with the noise-filtered context-aware prior mask. arXiv:2109.13788"},{"key":"282_CR11","doi-asserted-by":"crossref","unstructured":"Lu Z, He S, Zhu X, Zhang L, Song Y.-Z, Xiang T (2021) Simpler is better: few-shot semantic segmentation with classifier weight transformer. arXiv:2108.03032","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"282_CR12","first-page":"21984","volume":"34","author":"G Zhang","year":"2021","unstructured":"Zhang G, Kang G, Yang Y, Wei Y (2021) Few-shot segmentation via cycle-consistent transformer. Adv Neural Inf Process Syst 34:21984\u201321996","journal-title":"Adv Neural Inf Process Syst"},{"key":"282_CR13","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P (2021) Segformer: simple and efficient design for semantic segmentation with transformers. Adv Neural Inf Process Syst 34:12077\u201312090","journal-title":"Adv Neural Inf Process Syst"},{"key":"282_CR14","doi-asserted-by":"publisher","first-page":"166109","DOI":"10.1109\/access.2019.2953465","volume":"7","author":"Z Cao","year":"2019","unstructured":"Cao Z, Zhang T, Diao W, Zhang Y, Lyu X, Fu K, Sun X (2019) Meta-seg: a generalized meta-learning framework for multi-class few-shot semantic segmentation. IEEE Access 7:166109\u2013166121. https:\/\/doi.org\/10.1109\/access.2019.2953465","journal-title":"IEEE Access"},{"key":"282_CR15","doi-asserted-by":"publisher","unstructured":"Li X, Wei T, Chen Y.P, Tai Y.-W, Tang C.-K (2020) FSS-1000: A 1000-class dataset for few-shot segmentation. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00294","DOI":"10.1109\/cvpr42600.2020.00294"},{"key":"282_CR16","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"282_CR17","doi-asserted-by":"publisher","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"282_CR18","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848. https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"282_CR19","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929"},{"key":"282_CR20","doi-asserted-by":"crossref","unstructured":"Zheng S, Lu J, Zhao H, Zhu X, Luo Z, Wang Y, Fu Y, Feng J, Xiang T, Torr PH (2021)Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6881\u20136890","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"282_CR21","doi-asserted-by":"crossref","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille A.L, Zhou Y (2021) Transunet: Transformers make strong encoders for medical image segmentation. arXiv:2102.04306","DOI":"10.1109\/IGARSS46834.2022.9883628"},{"issue":"9","key":"282_CR22","doi-asserted-by":"publisher","first-page":"3855","DOI":"10.1109\/tcyb.2020.2992433","volume":"50","author":"X Zhang","year":"2020","unstructured":"Zhang X, Wei Y, Yang Y, Huang TS (2020) SG-one: similarity guidance network for one-shot semantic segmentation. IEEE Trans Cybernet 50(9):3855\u20133865. https:\/\/doi.org\/10.1109\/tcyb.2020.2992433","journal-title":"IEEE Trans Cybernet"},{"key":"282_CR23","doi-asserted-by":"crossref","unstructured":"Yang L, Zhuo W, Qi L, Shi Y, Gao Y (2021) Mining latent classes for few-shot segmentation arXiv:2103.15402 [cs.CV]","DOI":"10.1109\/ICCV48922.2021.00860"},{"key":"282_CR24","doi-asserted-by":"crossref","unstructured":"Zhang S, Wu T, Wu S, Guo G (2022) Catrans: context and affinity transformer for few-shot segmentation. arXiv:2204.12817","DOI":"10.24963\/ijcai.2022\/231"},{"key":"282_CR25","unstructured":"Zhou D, Kang B, Jin X, Yang L, Lian X, Jiang Z, Hou Q, Feng J (2021) Deepvit: towards deeper vision transformer. arXiv:2103.11886"},{"key":"282_CR26","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Fan D.-P, Song K, Liang D, Lu T, Luo P, Shao L (2021) Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 568\u2013578","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"282_CR27","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"282_CR28","doi-asserted-by":"crossref","unstructured":"Yuan K, Guo S, Liu Z, Zhou A, Yu F, Wu W (2021) Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 579\u2013588","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"282_CR29","doi-asserted-by":"crossref","unstructured":"Guo J, Han K, Wu H, Tang Y, Chen X, Wang Y, Xu C (2022) Cmt: convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12175\u201312185","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"282_CR30","doi-asserted-by":"crossref","unstructured":"Graham B, El-Nouby A, Touvron H, Stock P, Joulin A, J\u00e9gou H, Douze M (2021) Levit: a vision transformer in convnet\u2019s clothing for faster inference. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 12259\u201312269","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"282_CR31","unstructured":"Li Y, Yuan G, Wen Y, Hu J, Evangelidis G, Tulyakov S, Wang Y, Ren J (2022)Efficientformer: vision transformers at mobilenet speed. In: Advances in neural information processing systems, vol 35, pp 12934\u201312949"},{"key":"282_CR32","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y (2021) Transformer in transformer. Adv Neural Inf Process Syst 34:15908\u201315919","journal-title":"Adv Neural Inf Process Syst"},{"key":"282_CR33","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision. Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"282_CR34","doi-asserted-by":"crossref","unstructured":"Chen X, Wang D, Li D, Lu H (2022) Efficient visual tracking via hierarchical cross-attention transformer","DOI":"10.1109\/ICCE-Taiwan55306.2022.9869107"},{"key":"282_CR35","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"282_CR36","doi-asserted-by":"publisher","unstructured":"Wang H, Yang Y, Cao X, Zhen X, Snoek C, Shao L (2021) Variational prototype inference for few-shot semantic segmentation, pp 525\u2013534. https:\/\/doi.org\/10.1109\/WACV48630.2021.00057","DOI":"10.1109\/WACV48630.2021.00057"},{"key":"282_CR37","doi-asserted-by":"publisher","unstructured":"Boudiaf M, Kervadec H, Masud ZI, Piantanida P, Ayed IB, Dolz J Few-shot segmentation without meta-learning: a good transductive inference is all you need? In 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr46437.2021.01376","DOI":"10.1109\/cvpr46437.2021.01376"},{"key":"282_CR38","doi-asserted-by":"crossref","unstructured":"Liu Y, Liu N, Cao Q, Yao X, Han J, Shao L (2022) Learning non-target knowledge for few-shot semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11573\u201311582","DOI":"10.1109\/CVPR52688.2022.01128"},{"key":"282_CR39","doi-asserted-by":"crossref","unstructured":"Shi X, Wei D, Zhang Y, Lu D, Ning M, Chen J, Ma K, Zheng Y (2022) Dense cross-query-and-support attention weighted mask aggregation for few-shot segmentation. ECCV","DOI":"10.1007\/978-3-031-20044-1_9"},{"key":"282_CR40","doi-asserted-by":"publisher","unstructured":"Hariharan B, Arbelaez P, Bourdev L, Maji S, Malik J (2011) Semantic contours from inverse detectors. In: 2011 International conference on computer vision, pp 991\u2013998 . https:\/\/doi.org\/10.1109\/iccv.2011.6126343","DOI":"10.1109\/iccv.2011.6126343"},{"key":"282_CR41","doi-asserted-by":"crossref","unstructured":"Min J, Kang D, Cho M (2021) Hypercorrelation squeeze for few-shot segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"282_CR42","doi-asserted-by":"crossref","unstructured":"Fan Q, Pei W, Tai Y.-W, Tang C-K (2022) Self-support few-shot semantic segmentation","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"282_CR43","unstructured":"Hong S, Cho S, Nam J, Kim S (2021) Cost aggregation is all you need for few-shot segmentation. arXiv:2112.11685"},{"key":"282_CR44","doi-asserted-by":"crossref","unstructured":"Kang D, Cho M (2022) Integrative few-shot learning for classification and segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9979\u20139990","DOI":"10.1109\/CVPR52688.2022.00974"},{"key":"282_CR45","doi-asserted-by":"crossref","unstructured":"Wang H, Zhang X, Hu Y, Yang Y, Cao X, Zhen X (2020) Few-shot semantic segmentation with democratic attention networks. In: European conference on computer vision. Springer, pp 730\u2013746","DOI":"10.1007\/978-3-030-58601-0_43"},{"key":"282_CR46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187855","author":"W Liu","year":"2022","unstructured":"Liu W, Zhang C, Ding H, Hung T-Y, Lin G (2022) Few-shot segmentation with optimal transport matching and message flow. IEEE Trans Multim. https:\/\/doi.org\/10.1109\/TMM.2022.3187855","journal-title":"IEEE Trans Multim"},{"key":"282_CR47","doi-asserted-by":"crossref","unstructured":"Azad R, Fayjie A.R, Kauffmann C, Ben\u00a0Ayed I, Pedersoli M, Dolz J (2021) On the texture bias for few-shot cnn segmentation. In: Proceedings of the IEEE\/CVF Winter conference on applications of computer vision, pp 2674\u20132683","DOI":"10.1109\/WACV48630.2021.00272"},{"key":"282_CR48","doi-asserted-by":"crossref","unstructured":"Yang B, Liu C, Li B, Jiao J, Ye Q (2020) Prototype mixture models for few-shot semantic segmentation. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings. Part VIII 16. Springer, pp 763\u2013778","DOI":"10.1007\/978-3-030-58598-3_45"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-023-00282-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-023-00282-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-023-00282-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T14:10:50Z","timestamp":1701526250000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-023-00282-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,29]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["282"],"URL":"https:\/\/doi.org\/10.1007\/s13735-023-00282-9","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"type":"print","value":"2192-6611"},{"type":"electronic","value":"2192-662X"}],"subject":[],"published":{"date-parts":[[2023,7,29]]},"assertion":[{"value":"20 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interests and this paper does not contain any studies with human participants or animals by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}],"article-number":"17"}}