{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T19:26:30Z","timestamp":1777663590508,"version":"3.51.4"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T00:00:00Z","timestamp":1635552000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T00:00:00Z","timestamp":1635552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s00138-021-01257-8","type":"journal-article","created":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T17:02:28Z","timestamp":1635613348000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Object detection by crossing relational reasoning based on graph neural network"],"prefix":"10.1007","volume":"33","author":[{"given":"XiuTing","family":"You","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songhe","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Congyan","family":"Lang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"1257_CR1","unstructured":"Battaglia, PW., Hamrick, JB., Bapst, V., Sanchez-Gonzalez, A., Zambaldi, VF., Malinowski, M., Tacchetti, A., Raposo, D., Santoro, A., Faulkner, R., G\u00fcl\u00e7ehre, \u00c7., Song, HF., Ballard, AJ., Gilmer, J., Dahl, GE., Vaswani, A., Allen, KR., Nash, C., Langston, V., Dyer, C., Heess, N., Wierstra, D., Kohli, P., Botvinick, M., Vinyals, O., Li, Y., Pascanu, R.: (2018) Relational inductive biases, deep learning, and graph networks. CoRR arXiv:806.01261"},{"key":"1257_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: (2018) Cascade R-CNN: delving into high quality object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1257_CR3","unstructured":"Cao, J., Chen, Q., Guo, J., Shi, R.: (2020) Attention-guided context feature pyramid network for object detection. CoRR abs\/2005.11475"},{"key":"1257_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Li, L., Fei-Fei, L., Gupta, A.: (2018) Iterative visual reasoning beyond convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 7239\u20137248","DOI":"10.1109\/CVPR.2018.00756"},{"key":"1257_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wei, X., Wang, P., Guo, Y.: (2019) Multi-label image recognition with graph convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 5177\u20135186","DOI":"10.1109\/CVPR.2019.00532"},{"key":"1257_CR6","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: (2014) On the properties of neural machine translation: Encoder-decoder approaches. In: Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pp 103\u2013111","DOI":"10.3115\/v1\/W14-4012"},{"key":"1257_CR7","doi-asserted-by":"crossref","unstructured":"Cucchiara, R., Grana, C., Piccardi, M., Prati, A.: (2000) Statistic and knowledge-based moving object detection in traffic scenes. In: ITSC2000. 2000 IEEE Intelligent Transportation Systems. Proceedings (Cat. No. 00TH8493), pp 27\u201332","DOI":"10.1109\/ITSC.2000.881013"},{"key":"1257_CR8","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: (2016) R-FCN: object detection via region-based fully convolutional networks. In: Neural Information Processing Systems, pp 379\u2013387"},{"key":"1257_CR9","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: (2017) Deformable convolutional networks. In: IEEE International Conference on Computer Vision, pp 764\u2013773","DOI":"10.1109\/ICCV.2017.89"},{"key":"1257_CR10","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.neucom.2019.04.095","volume":"398","author":"S Ding","year":"2020","unstructured":"Ding, S., Qu, S., Xi, Y., Wan, S.: Stimulus-driven and concept-driven analysis for image caption generation. Neurocomputing 398, 520\u2013530 (2020a)","journal-title":"Neurocomputing"},{"issue":"10","key":"1257_CR11","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1007\/s10489-020-01665-9","volume":"50","author":"X Ding","year":"2020","unstructured":"Ding, X., Li, Q., Cheng, Y., Wang, J., Bian, W., Jie, B.: Local keypoint-based faster R-CNN. Appl Intell 50(10), 3007\u20133022 (2020b)","journal-title":"Appl Intell"},{"key":"1257_CR12","unstructured":"Du, X., Shi, X., Huang, R.: (2019) Repgn: Object detection with relational proposal graph network. CoRR abs\/1904.08959"},{"issue":"2","key":"1257_CR13","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2), 303\u2013338 (2010)","journal-title":"Int J Comput Vis"},{"issue":"3","key":"1257_CR14","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2021","unstructured":"Feng, D., Haase-Sch\u00fctz, C., Rosenbaum, L., Hertlein, H., Gl\u00e4ser, C., Timm, F., Wiesbeck, W., Dietmayer, K.: Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE Trans Intell Transp Syst 22(3), 1341\u20131360 (2021)","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1257_CR15","unstructured":"Fu, C., Liu, W., Ranga, A., Tyagi, A., Berg, AC.: (2017) DSSD : Deconvolutional single shot detector. CoRR arXiv:1701.06659"},{"key":"1257_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, RB.: (2015) Fast R-CNN. In: IEEE International Conference on Computer Vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"1257_CR17","doi-asserted-by":"crossref","unstructured":"Girshick, RB., Donahue, J., Darrell, T., Malik, J.: (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"1257_CR18","doi-asserted-by":"crossref","unstructured":"Harzallah, H., Jurie, F., Schmid, C.: (2009) Combining efficient object localization and image classification. In: IEEE International Conference on Computer Vision, pp 237\u2013244","DOI":"10.1109\/ICCV.2009.5459257"},{"key":"1257_CR19","doi-asserted-by":"crossref","unstructured":"He, C., Lai, S., Lam, K.: (2019) Improving object detection with relation graph inference. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp 2537\u20132541","DOI":"10.1109\/ICASSP.2019.8682335"},{"key":"1257_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: IEEE International Conference on Computer Vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"1257_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, RB.: (2017) Mask R-CNN. In: IEEE International Conference on Computer Vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.322"},{"key":"1257_CR22","first-page":"340","volume":"7574","author":"D Hoiem","year":"2012","unstructured":"Hoiem, D., Chodpathumwan, Y., Dai, Q.: Diagnosing error in object detectors. European Conference on Computer Vision 7574, 340\u2013353 (2012)","journal-title":"European Conference on Computer Vision"},{"key":"1257_CR23","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: (2018) Relation networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 3588\u20133597","DOI":"10.1109\/CVPR.2018.00378"},{"key":"1257_CR24","unstructured":"Kipf, TN., Welling, M.: (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations"},{"key":"1257_CR25","unstructured":"LeCun, Y., Bengio, Y,: et al. (1995) Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks 3361(10):1995"},{"key":"1257_CR26","doi-asserted-by":"crossref","unstructured":"Lee, J., Bang, J., Yang, S.: (2017) Object detection with sliding window in images including multiple similar objects. In: International Conference on Information and Communication Technology Convergence, pp 803\u2013806","DOI":"10.1109\/ICTC.2017.8190786"},{"key":"1257_CR27","doi-asserted-by":"crossref","unstructured":"Li, B., Liu, Y., Wang, X.: (2019) Gradient harmonized single-stage detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 8577\u20138584","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"1257_CR28","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, Y., Zhao, Q., Shen, T., Lin, Z., Liu, H.: (2020a) Spatial pyramid based graph reasoning for semantic segmentation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8947\u20138956","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"1257_CR29","doi-asserted-by":"crossref","unstructured":"Li, Z., Du, X., Cao, Y.: (2020b) GAR: graph assisted reasoning for object detection. In: IEEE Winter Conference on Applications of Computer Vision, pp 1284\u20131293","DOI":"10.1109\/WACV45572.2020.9093559"},{"key":"1257_CR30","first-page":"740","volume":"8693","author":"T Lin","year":"2014","unstructured":"Lin, T., Maire, M., Belongie, S.J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. IEEE international conference on computer vision 8693, 740\u2013755 (2014)","journal-title":"IEEE international conference on computer vision"},{"key":"1257_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, RB., He, K., Doll\u00e1r, P.: (2017) Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, pp 2999\u20133007","DOI":"10.1109\/ICCV.2017.324"},{"key":"1257_CR32","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s11263-015-0844-7","volume":"9905","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.E., Fu, C., Berg, A.C.: SSD: single shot multibox detector. IEEE international conference on computer vision 9905, 21\u201337 (2016)","journal-title":"IEEE international conference on computer vision"},{"key":"1257_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, R., Shan, S., Chen, X.: (2018) Structure inference net: Object detection using scene-level context and instance-level relationships. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 6985\u20136994","DOI":"10.1109\/CVPR.2018.00730"},{"key":"1257_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Jiang, Z., Wei, F.: (2019) OD-GCN object detection by knowledge graph with GCN. CoRR arXiv:1908.04385","DOI":"10.1109\/ICMEW46912.2020.9105952"},{"key":"1257_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., Ouyang, W.: (2020) Disentangling and unifying graph convolutions for skeleton-based action recognition. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 140\u2013149","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"1257_CR36","unstructured":"Liu H, Wang T, Li Y, Lang C, Jin Y, Ling H (2021) Joint graph learning and matching for semantic feature correspondence. arXiv preprint arXiv:2109.00240"},{"key":"1257_CR37","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: (2019) Libra R-CNN: towards balanced learning for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 821\u2013830","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1257_CR38","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, CD.: (2014) Glove: Global vectors for word representation. In: Moschitti A, Pang B, Daelemans W (eds) Proceedings of the 2014 conference on empirical methods in natural language processing, pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"issue":"12","key":"1257_CR39","doi-asserted-by":"publisher","first-page":"3039","DOI":"10.1109\/TMM.2020.2971175","volume":"22","author":"H Qiu","year":"2020","unstructured":"Qiu, H., Li, H., Wu, Q., Meng, F., Xu, L., Ngan, K.N., Shi, H.: Hierarchical context features embedding for object detection. IEEE Trans Multim 22(12), 3039\u20133050 (2020)","journal-title":"IEEE Trans Multim"},{"key":"1257_CR40","unstructured":"Redmon, J., Farhadi, A.: (2018) Yolov3: An incremental improvement. CoRR arXiv:1804.02767"},{"key":"1257_CR41","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, SK., Girshick, RB., Farhadi, A.: (2016) You only look once: Unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"1257_CR42","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.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"1257_CR43","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Li, F.: Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3), 211\u2013252 (2015)","journal-title":"Int J Comput Vis"},{"key":"1257_CR44","unstructured":"Szegedy, C., Toshev, A., Erhan, D.: (2013) Deep neural networks for object detection. In: Neural Information Processing Systems, pp 2553\u20132561"},{"key":"1257_CR45","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, AN., Kaiser, L., Polosukhin, I.: (2017) Attention is all you need. In: Neural Information Processing Systems, pp 5998\u20136008"},{"key":"1257_CR46","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: (2018) Graph attention networks. In: International Conference on Learning Representations"},{"issue":"6","key":"1257_CR47","doi-asserted-by":"publisher","first-page":"1494","DOI":"10.1109\/TPAMI.2017.2716350","volume":"40","author":"T Wang","year":"2018","unstructured":"Wang, T., Ling, H.: Gracker: A graph-based planar object tracker. IEEE Trans Pattern Anal Mach Intell 40(6), 1494\u20131501 (2018)","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"1257_CR48","doi-asserted-by":"publisher","first-page":"2853","DOI":"10.1109\/TPAMI.2017.2767591","volume":"40","author":"T Wang","year":"2018","unstructured":"Wang, T., Ling, H., Lang, C., Feng, S.: Graph matching with adaptive and branching path following. IEEE Trans Pattern Anal Mach Intell 40(12), 2853\u20132867 (2018)","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1257_CR49","doi-asserted-by":"crossref","unstructured":"Wang, T., Liu, H., Li, Y., Jin, Y., Hou, X., Ling, H.: (2020) Learning combinatorial solver for graph matching. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pp 7565\u20137574","DOI":"10.1109\/CVPR42600.2020.00759"},{"key":"1257_CR50","doi-asserted-by":"crossref","unstructured":"Xie, G., Liu, L., Zhu, F., Zhao, F., Zhang, Z., Yao, Y., Qin, J., Shao, L.: (2020) Region graph embedding network for zero-shot learning. In: Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part IV, pp 562\u2013580","DOI":"10.1007\/978-3-030-58548-8_33"},{"key":"1257_CR51","doi-asserted-by":"crossref","unstructured":"Xie, G., Liu, J., Xiong, H., Shao, L.: (2021) Scale-aware graph neural network for few-shot semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021, pp 5475\u20135484","DOI":"10.1109\/CVPR46437.2021.00543"},{"key":"1257_CR52","doi-asserted-by":"crossref","unstructured":"Xu, H., Jiang, C., Liang, X., Li, Z.: (2019a) Spatial-aware graph relation network for large-scale object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 9298\u20139307","DOI":"10.1109\/CVPR.2019.00952"},{"key":"1257_CR53","doi-asserted-by":"crossref","unstructured":"Xu, H., Jiang, C., Liang, X., Lin, L., Li, Z.: (2019b) Reasoning-rcnn: Unifying adaptive global reasoning into large-scale object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 6419\u20136428","DOI":"10.1109\/CVPR.2019.00658"},{"key":"1257_CR54","doi-asserted-by":"crossref","unstructured":"Yi, H., Shi, S., Ding, M., Sun, J., Xu, K., Zhou, H., Wang, Z., Li, S., Wang, G.: (2020) Segvoxelnet: Exploring semantic context and depth-aware features for 3d vehicle detection from point cloud. In: IEEE International Conference on Robotics and Automation, pp 2274\u20132280","DOI":"10.1109\/ICRA40945.2020.9196556"},{"key":"1257_CR55","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1016\/j.neucom.2021.08.092","volume":"464","author":"G Zhao","year":"2021","unstructured":"Zhao, G., Wang, T., Li, Y., Jin, Y., Lang, C.: Entropy-aware self-training for graph convolutional networks. Neurocomputing 464, 394\u2013407 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2021.08.092","journal-title":"Neurocomputing"},{"key":"1257_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: (2019) Deformable convnets V2: more deformable, better results. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 9308\u20139316","DOI":"10.1109\/CVPR.2019.00953"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-021-01257-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-021-01257-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-021-01257-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,4]],"date-time":"2022-02-04T16:47:57Z","timestamp":1643993277000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-021-01257-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,30]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["1257"],"URL":"https:\/\/doi.org\/10.1007\/s00138-021-01257-8","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,30]]},"assertion":[{"value":"17 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"1"}}