{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:25:25Z","timestamp":1740122725978,"version":"3.37.3"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T00:00:00Z","timestamp":1645574400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T00:00:00Z","timestamp":1645574400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012165","name":"key technologies research and development program","doi-asserted-by":"publisher","award":["2018YFB0204300"],"award-info":[{"award-number":["2018YFB0204300"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s11063-022-10766-0","type":"journal-article","created":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T13:03:19Z","timestamp":1645621399000},"page":"3249-3261","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fixed-Size Objects Encoding for Visual Relationship Detection"],"prefix":"10.1007","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-7401","authenticated-orcid":false,"given":"Hengyue","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,23]]},"reference":[{"key":"10766_CR1","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Man\u00e9 D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Vi\u00e9gas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: Large-scale machine learning on heterogeneous systems. https:\/\/www.tensorflow.org\/, software available from tensorflow.org"},{"key":"10766_CR2","first-page":"8110","volume":"33","author":"Y Bin","year":"2019","unstructured":"Bin Y, Yang Y, Tao C, Huang Z, Li J, Shen HT (2019) Mr-net: Exploiting mutual relation for visual relationship detection. Proceed AAAI Conf Artificial Intell 33:8110\u20138117","journal-title":"Proceed AAAI Conf Artificial Intell"},{"key":"10766_CR3","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, Ieee, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10766_CR4","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"issue":"9","key":"10766_CR5","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10766_CR6","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"10766_CR7","doi-asserted-by":"crossref","unstructured":"Jung J, Park J (2018) Visual relationship detection with language prior and softmax. In: 2018 IEEE international conference on image processing, applications and systems (IPAS), IEEE, pp 143\u2013148","DOI":"10.1109\/IPAS.2018.8708855"},{"key":"10766_CR8","doi-asserted-by":"crossref","unstructured":"Jung J, Park J (2019) Improving visual relationship detection using linguistic and spatial cues. ETRI J","DOI":"10.4218\/etrij.2019-0093"},{"key":"10766_CR9","doi-asserted-by":"crossref","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li LJ, Shamma DA, Bernstein M, Fei-Fei L (2016) Visual genome: Connecting language and vision using crowdsourced dense image annotations. arXiv:1602.07332","DOI":"10.1007\/s11263-016-0981-7"},{"key":"10766_CR10","doi-asserted-by":"crossref","unstructured":"Kukleva A, Tapaswi M, Laptev I (2020) Learning interactions and relationships between movie characters. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00987"},{"key":"10766_CR11","doi-asserted-by":"crossref","unstructured":"Liang K, Guo Y, Chang H, Chen X (2018) Visual relationship detection with deep structural ranking. In: Thirty-Second AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v32i1.12274"},{"key":"10766_CR12","doi-asserted-by":"crossref","unstructured":"Liao W, Rosenhahn B, Shuai L, Ying\u00a0Yang M (2019) Natural language guided visual relationship detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","DOI":"10.1109\/CVPRW.2019.00058"},{"key":"10766_CR13","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10766_CR14","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10766_CR15","doi-asserted-by":"crossref","unstructured":"Lu C, Krishna R, Bernstein M, Fei-Fei L (2016) Visual relationship detection with language priors. In: European Conference on Computer Vision","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"10766_CR16","doi-asserted-by":"crossref","unstructured":"Mi L, Chen Z (2020) Hierarchical graph attention network for visual relationship detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.01390"},{"key":"10766_CR17","unstructured":"Mizzi N, Muscat A (2019) Optimising the input image to improve visual relationship detection. arXiv preprint arXiv:1903.11029"},{"key":"10766_CR18","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"key":"10766_CR19","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"10766_CR20","doi-asserted-by":"publisher","unstructured":"Xu D, Zhu Y, Choy CB, Fei-Fei L (2017) Scene graph generation by iterative message passing. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3097\u20133106, https:\/\/doi.org\/10.1109\/CVPR.2017.330","DOI":"10.1109\/CVPR.2017.330"},{"key":"10766_CR21","doi-asserted-by":"crossref","unstructured":"Yin G, Sheng L, Liu B, Yu N, Wang X, Shao J, Change\u00a0Loy C (2018) Zoom-net: mining deep feature interactions for visual relationship recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 322\u2013338","DOI":"10.1007\/978-3-030-01219-9_20"},{"key":"10766_CR22","doi-asserted-by":"crossref","unstructured":"Yu R, Li A, Morariu VI, Davis LS (2017) Visual relationship detection with internal and external linguistic knowledge distillation. In: Proceedings of the IEEE international conference on computer vision, pp 1974\u20131982","DOI":"10.1109\/ICCV.2017.121"},{"key":"10766_CR23","doi-asserted-by":"crossref","unstructured":"Zhang S, Jiang H, Xu M, Hou J, Dai LR (2015) The fixed-size ordinally-forgetting encoding method for neural network language models. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp 495\u2013500","DOI":"10.3115\/v1\/P15-2081"},{"key":"10766_CR24","doi-asserted-by":"crossref","unstructured":"Zhou H, Zhang C, Hu C (2019) Visual relationship detection with relative location mining. In: Proceedings of the 27th ACM International Conference on Multimedia, pp 30\u201338","DOI":"10.1145\/3343031.3351024"},{"key":"10766_CR25","doi-asserted-by":"crossref","unstructured":"Zhu Y, Jiang S (2018) Deep structured learning for visual relationship detection. In: Thirty-Second AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v32i1.12271"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10766-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-10766-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10766-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T17:30:46Z","timestamp":1660239046000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-10766-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,23]]},"references-count":25,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["10766"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-10766-0","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2022,2,23]]},"assertion":[{"value":"4 February 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}