{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,11,19]],"date-time":"2023-11-19T22:40:16Z","timestamp":1700433616287},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,4,12]],"date-time":"2022-04-12T00:00:00Z","timestamp":1649721600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,12]],"date-time":"2022-04-12T00:00:00Z","timestamp":1649721600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"This research was funded by National key research and development program of China\u00a0","award":["2018AAA0102702"],"award-info":[{"award-number":["2018AAA0102702"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s13042-022-01538-2","type":"journal-article","created":{"date-parts":[[2022,4,12]],"date-time":"2022-04-12T03:37:11Z","timestamp":1649734631000},"page":"2479-2493","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring correlation of relationship reasoning for scene graph generation"],"prefix":"10.1007","volume":"13","author":[{"given":"Peng","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Mo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laihao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,12]]},"reference":[{"key":"1538_CR1","doi-asserted-by":"crossref","unstructured":"Johnson J, Krishna R, Stark M et al (2015) Image retrieval using scene graphs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3668\u20133678","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"1538_CR2","doi-asserted-by":"crossref","unstructured":"Yatskar M, Zettlemoyer L, Farhadi A (2016) Situation recognition: visual semantic role labeling for image understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5534\u20135542","DOI":"10.1109\/CVPR.2016.597"},{"issue":"17","key":"1538_CR3","doi-asserted-by":"publisher","first-page":"22159","DOI":"10.1007\/s11042-018-5704-3","volume":"77","author":"Y Liu","year":"2018","unstructured":"Liu Y, Yu J, Han Y et al (2018) Understanding the effective receptive field in semantic image segmentation. Multimed Tools Appl 77(17):22159\u201322171","journal-title":"Multimed Tools Appl"},{"issue":"Apr. 26","key":"1538_CR4","first-page":"27","volume":"187","author":"M Yan","year":"2016","unstructured":"Yan M, Guo Y et al (2016) Deep learning for visual understanding: a review. Neurocomputing 187(Apr. 26):27\u201348","journal-title":"Neurocomputing"},{"key":"1538_CR5","doi-asserted-by":"crossref","unstructured":"Sun J, Li Y, Lu H et al (2020) Deep learning for visual segmentation: a review. In: Proceedings of 44th IEEE annual computers, software, and applications conference, pp 1256\u20131260","DOI":"10.1109\/COMPSAC48688.2020.00-84"},{"key":"1538_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_35","volume-title":"Computer vision ECCV 2014. Lecture notes in computer science, vol 8693","author":"T Scharw\u00e4chter","year":"2014","unstructured":"Scharw\u00e4chter T, Enzweiler M, Franke U et al (2014) Stixmantics: a medium-level model for real-time semantic scene understanding. Computer vision ECCV 2014. Lecture notes in computer science, vol 8693. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_35"},{"issue":"12","key":"1538_CR7","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"BA Vijay","year":"2017","unstructured":"Vijay BA et al (2017) SegNet: a deep convolutional encoder-decoder architecture for scene segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1538_CR8","doi-asserted-by":"publisher","unstructured":"Gadosey PK, Li Y, Zhang T et al (2020) SEB-Net: revisiting deep encoder-decoder networks for scene understanding. In: Proceedings of 6th international conference on computing and artificial intelligence, pp 542\u2013551. https:\/\/doi.org\/10.1145\/3404555.3404629","DOI":"10.1145\/3404555.3404629"},{"key":"1538_CR9","doi-asserted-by":"crossref","unstructured":"Xu DF, Zhu YK et al (2017) Scene graph generation by iterative message passing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5410\u20135419","DOI":"10.1109\/CVPR.2017.330"},{"key":"1538_CR10","doi-asserted-by":"crossref","unstructured":"Yang J, Lu J, Lee S et al (2018) Graph rcnn for scene graph generation. In: European conference on computer vision, pp 670\u2013685","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"1538_CR11","doi-asserted-by":"crossref","unstructured":"Li Y, Ouyang W, Zhou B et al (2018) Factorizable net: an efficient sub graph-based framework for scene graph generation. In: European conference on computer vision, pp 335\u2013351","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"1538_CR12","unstructured":"Cong WL, Wang WL, Lee CW (2018) Scene graph generation via conditional random fields. arXiv:1811.08075 (arXiv preprint)"},{"key":"1538_CR13","unstructured":"Mohamed KB (2020) After all, only the last neuron matters: comparing multi-modal fusion functions for scene graph generation. arXiv:2011.04779 (arXiv preprint)"},{"key":"1538_CR14","doi-asserted-by":"crossref","unstructured":"Li Y, Ouyang W, Zhou B et al (2017) Scene graph generation from objects, phrases and region captions. In: Proceedings of the IEEE international conference on computer vision, pp 1261\u20131270","DOI":"10.1109\/ICCV.2017.142"},{"issue":"1","key":"1538_CR15","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O et al (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis 123(1):32\u201373","journal-title":"Int J Comput Vis"},{"key":"1538_CR16","doi-asserted-by":"crossref","unstructured":"Zellers R, Yatskar M, Thomson S et al (2018) Neural motifs: scene graph parsing with global context. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5831\u20135840","DOI":"10.1109\/CVPR.2018.00611"},{"key":"1538_CR17","doi-asserted-by":"crossref","unstructured":"Zitnick C, Parikh, Vanderwende L (2013) Learning the visual interpretation of sentences. In: Proceedings of the IEEE international conference on computer vision, pp 1681\u20131688","DOI":"10.1109\/ICCV.2013.211"},{"key":"1538_CR18","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s10044-018-00770-3","volume":"23","author":"S Sah","year":"2020","unstructured":"Sah S, Nguyen T, Ptucha R (2020) Understanding temporal structure for video captioning. Pattern Anal Appl 23:147\u2013159. https:\/\/doi.org\/10.1007\/s10044-018-00770-3","journal-title":"Pattern Anal Appl"},{"key":"1538_CR19","doi-asserted-by":"crossref","unstructured":"Wang W, Wang R, Shan S et al (2019) Exploring context and visual pattern of relationship for scene graph generation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8188\u20138197","DOI":"10.1109\/CVPR.2019.00838"},{"key":"1538_CR20","doi-asserted-by":"publisher","first-page":"7781","DOI":"10.1007\/s10489-020-02115-2","volume":"51","author":"P Tian","year":"2021","unstructured":"Tian P, Mo HW, Jiang LH (2021) Scene graph generation by multi-level semantic tasks. Appl Intell 51:7781\u20137793. https:\/\/doi.org\/10.1007\/s10489-020-02115-2","journal-title":"Appl Intell"},{"issue":"4","key":"1538_CR21","doi-asserted-by":"publisher","first-page":"511","DOI":"10.3390\/sym12040511","volume":"12","author":"S Li","year":"2020","unstructured":"Li S, Tang M, Zhang J et al (2020) Attentive gated graph neural network for image scene graph generation. Symmetry 12(4):511","journal-title":"Symmetry"},{"key":"1538_CR22","doi-asserted-by":"crossref","unstructured":"Zhang H, Kyaw Z, Chang S-F et al (2017) Visual translation embedding network for visual relation detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5532\u20135540","DOI":"10.1109\/CVPR.2017.331"},{"key":"1538_CR23","doi-asserted-by":"crossref","unstructured":"Lu C, Krishna R, Bernstein M, Li F-F (2016) Visual relationship detection with language priors. In: European conference on computer vision, pp 852\u2013869","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"1538_CR24","doi-asserted-by":"crossref","unstructured":"Dai B, Zhang Y, Lin D (2017) Detecting visual relationships with deep relational networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3076\u20133086","DOI":"10.1109\/CVPR.2017.352"},{"key":"1538_CR25","unstructured":"Tao H, Gao L, Song JK et al (2020) Learning from the scene and borrowing from the rich: tackling the long tail in scene graph generation. arXiv:2006.07585 (arXiv preprint)"},{"key":"1538_CR26","doi-asserted-by":"crossref","unstructured":"Wan H, Luo YH et al (2018) Representation learning for scene graph completion via jointly structural and visual embedding. In: Proceedings of the twenty-seventh international joint conference on artificial intelligence, pp 949\u2013956","DOI":"10.24963\/ijcai.2018\/132"},{"key":"1538_CR27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2020.2977911","volume":"99","author":"ZS Hung","year":"2020","unstructured":"Hung ZS, Mallya A, Lazebnik S (2020) Contextual translation embedding for visual relationship detection and scene graph generation. IEEE Trans Pattern Anal Mach Intell 99:1\u20131","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1538_CR28","doi-asserted-by":"crossref","unstructured":"Wei M, Yuan C, Yue X et al (2020) HOSE-Net: higher order structure embedded network for scene graph generation. arXiv:2008.05156 (arXiv preprint)","DOI":"10.1145\/3394171.3413575"},{"key":"1538_CR29","doi-asserted-by":"crossref","unstructured":"Zhu Y, Jiang S (2018) Deep structured learning for visual relationship detection. In: AAAI conference on artificial intelligence, pp 7623\u20137630","DOI":"10.1609\/aaai.v32i1.12271"},{"key":"1538_CR30","unstructured":"Zhang J, Zhang Y, Wu B et al (2020) Dual ResGCN for balanced scene graph generation. arXiv:2011.04234 (arXiv preprint)"},{"key":"1538_CR31","doi-asserted-by":"crossref","unstructured":"Lin X, Ding C, Zeng J et al (2020) GPS-Net: graph property sensing network for scene graph generation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3746\u20133753","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"1538_CR32","doi-asserted-by":"crossref","unstructured":"Chen T, Yu W, Chen R et al (2019) Knowledge-embedded routing network for scene graph generation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6163\u20136171","DOI":"10.1109\/CVPR.2019.00632"},{"key":"1538_CR33","unstructured":"Zhou Y, Sun S, Zhang C et al (2020) Exploring the hierarchy in relation labels for scene graph generation. arXiv:2009.05834 (arXiv preprint)"},{"key":"1538_CR34","doi-asserted-by":"crossref","unstructured":"Sharifzadeh S, Baharlou S M, Tresp V (2020) Classification by attention: scene graph classification with prior knowledge. arXiv:2011.1008 (arXiv preprint)","DOI":"10.1609\/aaai.v35i6.16636"},{"key":"1538_CR35","unstructured":"Li Y, Tarlow D, Brockschmidt M et al (2016) Gated graph sequence neural networks. In: Proceedings of the IEEE international conference on learning representations, pp 1\u201320"},{"key":"1538_CR36","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"issue":"6","key":"1538_CR37","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1538_CR38","unstructured":"Bochkovskiy A, Wang CY, Liao HY (2020)YOLOv4: optimal speed and accuracy of object detection. arXiv:2004.10934 (arXiv preprint)"},{"key":"1538_CR39","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D et al (2016) SSD: single shot multibox detector. In: European conference on computer vision, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1538_CR40","doi-asserted-by":"crossref","unstructured":"Desai C, Ramanan D (2012) Detecting actions, poses, and objects with relational phraselets. In: European conference on computer vision, pp 158\u2013172","DOI":"10.1007\/978-3-642-33765-9_12"},{"key":"1538_CR41","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/s11263-014-0779-4","volume":"112","author":"W Choi","year":"2015","unstructured":"Choi W, Chao YW, Pantofaru C et al (2015) Indoor scene understanding with geometric and semantic contexts. Int J Comput Vis 112:204\u2013220","journal-title":"Int J Comput Vis"},{"key":"1538_CR42","doi-asserted-by":"crossref","unstructured":"Li Y, Ouyang W, Wang X et al (2017) ViP-CNN: visual phrase guided convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1347\u20131356","DOI":"10.1109\/CVPR.2017.766"},{"key":"1538_CR43","doi-asserted-by":"crossref","unstructured":"Che W, Fan X, Xiong R et al (2018) Paragraph generation network with visual relationship detection. In: Proceedings of the 26th IEEE ACM international conference, pp 1435\u20131443","DOI":"10.1145\/3240508.3240695"},{"issue":"28","key":"1538_CR44","first-page":"55","volume":"434","author":"L Wang","year":"2021","unstructured":"Wang L, Lin P, Cheng J et al (2021) Visual relationship detection with recurrent attention and negative sampling. Neurocomputing 434(28):55\u201366","journal-title":"Neurocomputing"},{"key":"1538_CR45","doi-asserted-by":"crossref","unstructured":"Mou L, Hua Y, Zhu XX (2019) Spatial relational reasoning in networks for improving semantic segmentation of aerial images. In: Proceedings of the IEEE international conference on geoscience and remote sensing symposium, pp 5232\u20135235","DOI":"10.1109\/IGARSS.2019.8900224"},{"key":"1538_CR46","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/978-3-030-28954-6_15","volume-title":"Explainable AI: interpreting, explaining and visualizing deep learning. Lecture notes in computer science","author":"M Hofmarcher","year":"2019","unstructured":"Hofmarcher M, Unterthiner T, Arjona-Medina J et al (2019) Visual scene understanding for autonomous driving using semantic segmentation. Explainable AI: interpreting, explaining and visualizing deep learning. Lecture notes in computer science, vol 11700. Springer, Cham, pp 285\u2013296"},{"key":"1538_CR47","unstructured":"Vincent SC, Paroma V, Ranjay K et al (2019) Scene graph prediction with limited labels. In: Proceedings of the IEEE international conference on computer vision, pp 2580\u20132590"},{"key":"1538_CR48","doi-asserted-by":"crossref","unstructured":"Zareian A, Karaman S, Chang SF (2020) Bridging knowledge graphs to generate scene graphs. In: European conference on computer vision, pp 606\u2013623","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"1538_CR49","doi-asserted-by":"crossref","unstructured":"Dornadula A, Narcomey A, Krishna R et al (2019) Learning predicates as functions to enable few-shot scene graph prediction. arXiv:1906.04876 (arXiv preprint)","DOI":"10.1109\/ICCVW.2019.00214"},{"key":"1538_CR50","doi-asserted-by":"crossref","unstructured":"Qi X, Liao R, Jia J et al (2017) 3D graph neural networks for RGBD semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5199\u20135208","DOI":"10.1109\/ICCV.2017.556"},{"key":"1538_CR51","unstructured":"Kenneth M, Ruslan S, Abhinav G (2017) The more you know: using knowledge graphs for image classification. arXiv:1612.04844 (arXiv preprint)"},{"key":"1538_CR52","doi-asserted-by":"crossref","unstructured":"Li R, Tapaswi M, Liao R et al (2017) Situation recognition with graph neural networks. In: Proceedings of the IEEE international conference on computer vision, pp 4173\u20134182","DOI":"10.1109\/ICCV.2017.448"},{"key":"1538_CR53","unstructured":"Pezeshki M (2015) Sequence modeling using gated recurrent neural networks. arXiv:1501.00299 (arXiv preprint)"},{"key":"1538_CR54","doi-asserted-by":"crossref","unstructured":"Zhou J, Cui G, Zhang Z et al (2020) Graph neural networks: a review of methods and applications. AI Open, pp 57\u201381","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"1538_CR55","doi-asserted-by":"crossref","unstructured":"Chen ZM, Wei XS, Wang P et al (2019) Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5172\u20135181","DOI":"10.1109\/CVPR.2019.00532"},{"key":"1538_CR56","unstructured":"Mazari A, Sahbi H (2019) Human action recognition with multi-laplacian graph convolutional networks. arXiv:1910.06934 (arXiv preprint)"},{"key":"1538_CR57","unstructured":"Jin-Hwa K, Kyoung-Woon O, Woosang L et al (2016) Hadamard product for low-rank bilinear pooling. arXiv:1610.04325 (arXiv preprint)"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-022-01538-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-022-01538-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-022-01538-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,19]],"date-time":"2023-11-19T22:08:49Z","timestamp":1700431729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-022-01538-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,12]]},"references-count":57,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["1538"],"URL":"https:\/\/doi.org\/10.1007\/s13042-022-01538-2","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,12]]},"assertion":[{"value":"30 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}