{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T09:32:11Z","timestamp":1790847131329,"version":"4.1.0"},"reference-count":90,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T00:00:00Z","timestamp":1686268800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T00:00:00Z","timestamp":1686268800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U21B2025"],"award-info":[{"award-number":["U21B2025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U19B2036"],"award-info":[{"award-number":["U19B2036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61922080"],"award-info":[{"award-number":["61922080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2021ZD0111901"],"award-info":[{"award-number":["2021ZD0111901"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11263-023-01817-7","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T14:06:06Z","timestamp":1686319566000},"page":"2489-2515","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Importance First: Generating Scene Graph of Human Interest"],"prefix":"10.1007","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4394-0145","authenticated-orcid":false,"given":"Wenbin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-2595","authenticated-orcid":false,"given":"Ruiping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8348-392X","authenticated-orcid":false,"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-4404","authenticated-orcid":false,"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,9]]},"reference":[{"key":"1817_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Lawrence\u00a0Zitnick, C., & Parikh, D. (2015). Vqa: Visual question answering. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 2425\u20132433).","DOI":"10.1109\/ICCV.2015.279"},{"key":"1817_CR2","doi-asserted-by":"crossref","unstructured":"Biederman, I. (2017). On the semantics of a glance at a scene. In: Perceptual Organization (pp. 213\u2013253). Routledge.","DOI":"10.4324\/9781315512372-8"},{"issue":"3","key":"1817_CR3","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1093\/qje\/qjs018","volume":"127","author":"P Bordalo","year":"2012","unstructured":"Bordalo, P., Gennaioli, N., & Shleifer, A. (2012). Salience theory of choice under risk. The Quarterly Journal of Economics, 127(3), 1243\u20131285.","journal-title":"The Quarterly Journal of Economics"},{"key":"1817_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Jin, Q., Wang, P., & Wu, Q. (2020). Say as you wish: Fine-grained control of image caption generation with abstract scene graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 9962\u20139971).","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"1817_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., & Lin, L. (2019). Knowledge-embedded routing network for scene graph generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 6163\u20136171).","DOI":"10.1109\/CVPR.2019.00632"},{"key":"1817_CR6","doi-asserted-by":"crossref","unstructured":"Chiou, M.J., Ding, H., Yan, H., Wang, C., Zimmermann, R., & Feng, J. (2021). Recovering the unbiased scene graphs from the biased ones. In Proceedings of the ACM International Conference on Multimedia (ACM-MM) (pp. 1581\u20131590).","DOI":"10.1145\/3474085.3475297"},{"key":"1817_CR7","unstructured":"Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. In: Advances in Neural Information Processing Systems (NIPS) Workshop on Deep Learning."},{"key":"1817_CR8","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 (CVPR) (pp. 3298\u20133308).","DOI":"10.1109\/CVPR.2017.352"},{"key":"1817_CR9","doi-asserted-by":"crossref","unstructured":"Deng, Z., Hu, X., Zhu, L., Xu, X., Qin, J., Han, G., & Heng, P.A. (2018). R3net: Recurrent residual refinement network for saliency detection. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (AAAI) (pp. 684\u2013690).","DOI":"10.24963\/ijcai.2018\/95"},{"key":"1817_CR10","doi-asserted-by":"crossref","unstructured":"Dhamo, H., Farshad, A., Laina, I., Navab, N., Hager, G.D., Tombari, F., & Rupprecht, C. (2020). Semantic image manipulation using scene graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5213\u20135222).","DOI":"10.1109\/CVPR42600.2020.00526"},{"key":"1817_CR11","doi-asserted-by":"crossref","unstructured":"Gu, J., Joty, S., Cai, J., Zhao, H., Yang, X., & Wang, G. (2019). Unpaired image captioning via scene graph alignments. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 10,323\u201310,332).","DOI":"10.1109\/ICCV.2019.01042"},{"key":"1817_CR12","doi-asserted-by":"crossref","unstructured":"Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., & Ling, M. (2019). Scene graph generation with external knowledge and image reconstruction. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1969\u20131978).","DOI":"10.1109\/CVPR.2019.00207"},{"key":"1817_CR13","doi-asserted-by":"crossref","unstructured":"Guo, Y., Gao, L., Wang, X., Hu, Y., Xu, X., Lu, X., Shen, H.T., & Song, J. (2021). From general to specific: Informative scene graph generation via balance adjustment. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 16,383\u201316,392).","DOI":"10.1109\/ICCV48922.2021.01607"},{"issue":"1","key":"1817_CR14","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/TPAMI.2008.65","volume":"31","author":"F Han","year":"2008","unstructured":"Han, F., & Zhu, S. C. (2008). Bottom-up\/top-down image parsing with attribute grammar. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 31(1), 59\u201373.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1817_CR15","doi-asserted-by":"crossref","unstructured":"He, S., Tavakoli, H.R., Borji, A., & Pugeault, N. (2019). Human attention in image captioning: Dataset and analysis. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 8529\u20138538).","DOI":"10.1109\/ICCV.2019.00862"},{"key":"1817_CR16","doi-asserted-by":"crossref","unstructured":"Herzig, R., Bar, A., Xu, H., Chechik, G., Darrell, T., & Globerson, A. (2020). Learning canonical representations for scene graph to image generation. In Proceedings of European Conference on Computer Vision (ECCV), vol. 12371, (pp. 210\u2013227). Springer.","DOI":"10.1007\/978-3-030-58574-7_13"},{"issue":"8","key":"1817_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"key":"1817_CR18","doi-asserted-by":"crossref","unstructured":"Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., & Torr, P. (2017). Deeply supervised salient object detection with short connections. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3203\u20133212).","DOI":"10.1109\/CVPR.2017.563"},{"issue":"11","key":"1817_CR19","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., & Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 20(11), 1254\u20131259.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1817_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., & Fei-Fei, L. (2018). Image generation from scene graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1219\u20131228).","DOI":"10.1109\/CVPR.2018.00133"},{"key":"1817_CR21","doi-asserted-by":"crossref","unstructured":"Johnson, J., Krishna, R., Stark, M., Li, L.J., Shamma, D., Bernstein, M., & Fei-Fei, L. (2015). Image retrieval using scene graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3668\u20133678).","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"1817_CR22","doi-asserted-by":"crossref","unstructured":"Kahneman, D., Slovic, S.P., Slovic, P., & Tversky, A. (1982). Judgment under uncertainty: Heuristics and biases. Cambridge University Press.","DOI":"10.1017\/CBO9780511809477"},{"key":"1817_CR23","doi-asserted-by":"crossref","unstructured":"Kim, D.J., Choi, J., Oh, T.H., & Kweon, I.S. (2019). Dense relational captioning: Triple-stream networks for relationship-based captioning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 6271\u20136280).","DOI":"10.1109\/CVPR.2019.00643"},{"key":"1817_CR24","doi-asserted-by":"crossref","unstructured":"Klein, D.A., & Frintrop, S. (2011). Center-surround divergence of feature statistics for salient object detection. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 2214\u20132219).","DOI":"10.1109\/ICCV.2011.6126499"},{"key":"1817_CR25","unstructured":"Koner, R., Sinhamahapatra, P., & Tresp, V. (2020). Relation transformer network. arXiv:2004.06193."},{"issue":"1","key":"1817_CR26","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., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L. J., Shamma, D. A., Bernstein, M. S., & Fei-Fei, L. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision (IJCV), 123(1), 32\u201373.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1817_CR27","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., & He, X. (2018). Stacked cross attention for image-text matching. In Proceedings of European Conference on Computer Vision (ECCV) vol. 11208, (pp. 201\u2013216). Springer.","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"1817_CR28","unstructured":"Li, G., & Yu, Y. (2015). Visual saliency based on multiscale deep features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5455\u20135463)."},{"key":"1817_CR29","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., Wan, B., & He, X. (2021). Bipartite graph network with adaptive message passing for unbiased scene graph generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 11,109\u201311,119).","DOI":"10.1109\/CVPR46437.2021.01096"},{"issue":"8","key":"1817_CR30","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.1109\/TMM.2019.2896516","volume":"21","author":"X Li","year":"2019","unstructured":"Li, X., & Jiang, S. (2019). Know more say less: Image captioning based on scene graphs. IEEE Transactions on Multimedia (TMM), 21(8), 2117\u20132130.","journal-title":"IEEE Transactions on Multimedia (TMM)"},{"key":"1817_CR31","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Wang, X., & Tang, X. (2017). Vip-cnn: Visual phrase guided convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7244\u20137253).","DOI":"10.1109\/CVPR.2017.766"},{"key":"1817_CR32","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Shi, J., Zhang, C., & Wang, X. (2018) Factorizable net: an efficient subgraph-based framework for scene graph generation. In Proceedings of European Conference on Computer Vision (ECCV) vol. 11205, (pp. 346\u2013363). Springer.","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"1817_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Wang, K., & Wang, X. (2017). Scene graph generation from objects, phrases and region captions. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 1261\u20131270).","DOI":"10.1109\/ICCV.2017.142"},{"key":"1817_CR34","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Xing, E.P. (2017). Deep variation-structured reinforcement learning for visual relationship and attribute detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4408\u20134417).","DOI":"10.1109\/CVPR.2017.469"},{"key":"1817_CR35","doi-asserted-by":"crossref","unstructured":"Liang, Y., Bai, Y., Zhang, W., Qian, X., Zhu, L., & Mei, T. (2019). Vrr-vg: Refocusing visually-relevant relationships. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 10,403\u201310,412).","DOI":"10.1109\/ICCV.2019.01050"},{"key":"1817_CR36","doi-asserted-by":"crossref","unstructured":"Lin, L., Wang, G., Zhang, R., Zhang, R., Liang, X., & Zuo, W. (2016). Deep structured scene parsing by learning with image descriptions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2276\u20132284).","DOI":"10.1109\/CVPR.2016.250"},{"key":"1817_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014). Microsoft coco: Common objects in context. In Proceedings of European Conference on Computer Vision (ECCV) vol. 8693, (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1817_CR38","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., & Tao, D. (2020). Gps-net: Graph property sensing network for scene graph generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3746\u20133755).","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"1817_CR39","doi-asserted-by":"crossref","unstructured":"Liu, N., Han, J., & Yang, M.H. (2018). Picanet: Learning pixel-wise contextual attention for saliency detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3089\u20133098).","DOI":"10.1109\/CVPR.2018.00326"},{"key":"1817_CR40","doi-asserted-by":"crossref","unstructured":"Lu, C., Krishna, R., Bernstein, M., & Fei-Fei, L. (2016). Visual relationship detection with language priors. In: Proceedings of European Conference on Computer Vision (ECCV) vol. 9905, (pp. 852\u2013869). Springer.","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"1817_CR41","doi-asserted-by":"crossref","unstructured":"Lu, Y., Rai, H., Chang, J., Knyazev, B., Yu, G., Shekhar, S., Taylor, G.W., & Volkovs, M. (2021). Context-aware scene graph generation with seq2seq transformers. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 15,931\u201315,941).","DOI":"10.1109\/ICCV48922.2021.01563"},{"key":"1817_CR42","unstructured":"Lv, J., Xiao, Q., & Zhong, J. (2020). Avr: Attention based salient visual relationship detection. arXiv:2003.07012."},{"issue":"11","key":"1817_CR43","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1992","unstructured":"Miller, G. A. (1992). Wordnet: A lexical database for English. Communication of the ACM, 38(11), 39\u201341.","journal-title":"Communication of the ACM"},{"issue":"3","key":"1817_CR44","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/0010-0285(77)90012-3","volume":"9","author":"D Navon","year":"1977","unstructured":"Navon, D. (1977). Forest before trees: The precedence of global features in visual perception. Cognitive Psychology, 9(3), 353\u2013383.","journal-title":"Cognitive Psychology"},{"key":"1817_CR45","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Tripathi, S., Du, B., Guha, T., & Nguyen, T.Q. (2021) In defense of scene graphs for image captioning. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 1407\u20131416).","DOI":"10.1109\/ICCV48922.2021.00144"},{"key":"1817_CR46","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C. (2014). Glove: Global vectors for word representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1532\u20131543).","DOI":"10.3115\/v1\/D14-1162"},{"key":"1817_CR47","doi-asserted-by":"crossref","unstructured":"Peyre, J., Laptev, I., Schmid, C., & Sivic, J. (2017). Weakly-supervised learning of visual relations. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 5179\u20135188).","DOI":"10.1109\/ICCV.2017.554"},{"key":"1817_CR48","doi-asserted-by":"crossref","unstructured":"Pont-Tuset, J., Uijlings, J., Changpinyo, S., Soricut, R., & Ferrari, V. (2020). Connecting vision and language with localized narratives. In Proceedings of European Conference on Computer Vision (ECCV) vol. 12350, (pp. 647\u2013664). Springer.","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"1817_CR49","doi-asserted-by":"crossref","unstructured":"Qi, M., Li, W., Yang, Z., Wang, Y., & Luo, J. (2019). Attentive relational networks for mapping images to scene graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3957\u20133966).","DOI":"10.1109\/CVPR.2019.00408"},{"key":"1817_CR50","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 (NIPS) (pp. 91\u201399)."},{"key":"1817_CR51","doi-asserted-by":"crossref","unstructured":"Schuster, S., Krishna, R., Chang, A., Fei-Fei, L., & Manning, C.D. (2015) Generating semantically precise scene graphs from textual descriptions for improved image retrieval. In Proceedings of the Fourth Workshop on Vision and Language (pp. 70\u201380).","DOI":"10.18653\/v1\/W15-2812"},{"key":"1817_CR52","doi-asserted-by":"crossref","unstructured":"Sharma, A., Tuzel, O., & Jacobs, D.W. (2015). Deep hierarchical parsing for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 530\u2013538).","DOI":"10.1109\/CVPR.2015.7298651"},{"key":"1817_CR53","doi-asserted-by":"crossref","unstructured":"Shi, J., Zhang, H., & Li, J. (2019). Explainable and explicit visual reasoning over scene graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 8376\u20138384).","DOI":"10.1109\/CVPR.2019.00857"},{"key":"1817_CR54","unstructured":"Socher, R., Lin, C.C., Manning, C., & Ng, A.Y. (2011). Parsing natural scenes and natural language with recursive neural networks. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 129\u2013136)."},{"key":"1817_CR55","doi-asserted-by":"crossref","unstructured":"Suhail, M., Mittal, A., Siddiquie, B., Broaddus, C., Eledath, J., Medioni, G., Sigal, L. (2021). Energy-based learning for scene graph generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 13,936\u201313,945).","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"1817_CR56","doi-asserted-by":"crossref","unstructured":"Tai, K.S., Socher, R., Manning, C.D. (2015). Improved semantic representations from tree-structured long short-term memory networks. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (pp. 1556\u20131566).","DOI":"10.3115\/v1\/P15-1150"},{"key":"1817_CR57","unstructured":"Tang, C., Xie, L., Zhang, X., Hu, X., Tian, Q. (2022). Visual recognition by request. arXiv:2207.14227."},{"key":"1817_CR58","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H. (2020). Unbiased scene graph generation from biased training. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3716\u20133725).","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"1817_CR59","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W. (2019). Learning to compose dynamic tree structures for visual contexts. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 6619\u20136628).","DOI":"10.1109\/CVPR.2019.00678"},{"key":"1817_CR60","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (NIPS) (pp. 5998\u20136008)."},{"key":"1817_CR61","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., & Bengio, Y. (2018). Graph attention networks. In International Conference on Learning Representations (ICLR)."},{"key":"1817_CR62","doi-asserted-by":"crossref","unstructured":"Wang, L., Lu, H., Ruan, X., & Yang, M.H. (2015). Deep networks for saliency detection via local estimation and global search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3183\u20133192).","DOI":"10.1109\/CVPR.2015.7298938"},{"key":"1817_CR63","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, R., Yao, Z., Shan, S., & Chen, X. (2020). Cross-modal scene graph matching for relationship-aware image-text retrieval. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV) (pp. 1508\u20131517).","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"1817_CR64","doi-asserted-by":"crossref","unstructured":"Wang, T., Borji, A., Zhang, L., Zhang, P., & Lu, H. (2017). A stagewise refinement model for detecting salient objects in images. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 4019\u20134028).","DOI":"10.1109\/ICCV.2017.433"},{"key":"1817_CR65","doi-asserted-by":"crossref","unstructured":"Wang, W., Wang, R., & Chen, X. (2021). Topic scene graph generation by attention distillation from caption. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 15,900\u201315,910).","DOI":"10.1109\/ICCV48922.2021.01560"},{"key":"1817_CR66","doi-asserted-by":"crossref","unstructured":"Wang, W., Wang, R., Shan, S., & Chen, X. (2019). Exploring context and visual pattern of relationship for scene graph generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 8188\u20138197).","DOI":"10.1109\/CVPR.2019.00838"},{"key":"1817_CR67","doi-asserted-by":"crossref","unstructured":"Wang, W., Wang, R., Shan, S., & Chen, X. (2020). Sketching image gist: Human-mimetic hierarchical scene graph generation. In Proceedings of European Conference on Computer Vision (ECCV) vol. 12358, (pp. 222\u2013239). Springer.","DOI":"10.1007\/978-3-030-58601-0_14"},{"key":"1817_CR68","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5987\u20135995).","DOI":"10.1109\/CVPR.2017.634"},{"issue":"5","key":"1817_CR69","first-page":"1689","volume":"22","author":"Y Xie","year":"2012","unstructured":"Xie, Y., Lu, H., & Yang, M. H. (2012). Bayesian saliency via low and mid level cues. IEEE Transactions on Image Processing (TIP), 22(5), 1689\u20131698.","journal-title":"IEEE Transactions on Image Processing (TIP)"},{"key":"1817_CR70","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., & Fei-Fei, L. (2017). Scene graph generation by iterative message passing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5410\u20135419).","DOI":"10.1109\/CVPR.2017.330"},{"key":"1817_CR71","doi-asserted-by":"crossref","unstructured":"Xu, N., Liu, A. A., Liu, J., Nie, W., & Su, Y. (2019). Scene graph captioner: Image captioning based on structural visual representation. Journal of Visual Communication and Image Representation, 58, 477\u2013485.","DOI":"10.1016\/j.jvcir.2018.12.027"},{"key":"1817_CR72","doi-asserted-by":"crossref","unstructured":"Yan, S., Shen, C., Jin, Z., Huang, J., Jiang, R., Chen, Y., & Hua, X.S. (2020). Pcpl: Predicate-correlation perception learning for unbiased scene graph generation. In Proceedings of the ACM International Conference on Multimedia (ACM-MM) (pp. 265\u2013273).","DOI":"10.1145\/3394171.3413722"},{"key":"1817_CR73","doi-asserted-by":"crossref","unstructured":"Yang, J., Lu, J., Lee, S., Batra, D., Parikh, D. (2018). Graph r-cnn for scene graph generation. In Proceedings of European Conference on Computer Vision (ECCV) vol. 11205, (pp. 690\u2013706). Springer.","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"1817_CR74","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., & Cai, J. (2019). Auto-encoding scene graphs for image captioning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 10,685\u201310,694).","DOI":"10.1109\/CVPR.2019.01094"},{"key":"1817_CR75","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., & Mei, T. (2018). Exploring visual relationship for image captioning. In Proceedings of European Conference on Computer Vision (ECCV) vol. 11218, (pp. 711\u2013727). Springer.","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"1817_CR76","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., & Mei, T. (2019). Hierarchy parsing for image captioning. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 2621\u20132629).","DOI":"10.1109\/ICCV.2019.00271"},{"key":"1817_CR77","doi-asserted-by":"crossref","unstructured":"Yin, G., Sheng, L., Liu, B., Yu, N., Wang, X., Shao, J., & Loy, C.C. (2018). Zoom-net: Mining deep feature interactions for visual relationship recognition. In Proceedings of European Conference on Computer Vision (ECCV) vol. 11207, (pp. 330\u2013347). Springer.","DOI":"10.1007\/978-3-030-01219-9_20"},{"key":"1817_CR78","doi-asserted-by":"crossref","unstructured":"Yu, J., Chai, Y., Wang, Y., Hu, Y., & Wu, Q. (2021). Cogtree: Cognition tree loss for unbiased scene graph generation. In Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI) (pp. 1274\u20131280).","DOI":"10.24963\/ijcai.2021\/176"},{"key":"1817_CR79","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Morariu, V.I., & Davis, L.S. (2017). Visual relationship detection with internal and external linguistic knowledge distillation. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 1974\u20131982).","DOI":"10.1109\/ICCV.2017.121"},{"key":"1817_CR80","doi-asserted-by":"crossref","unstructured":"Zareian, A., Karaman, S., & Chang, S.F. (2020a). Bridging knowledge graphs to generate scene graphs. In Proceedings of European Conference on Computer Vision (ECCV) vol. 12368, (pp. 606\u2013623). Springer.","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"1817_CR81","doi-asserted-by":"crossref","unstructured":"Zareian, A., Karaman, S., & Chang, S.F. (2020b). Weakly supervised visual semantic parsing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3736\u20133745).","DOI":"10.1109\/CVPR42600.2020.00379"},{"key":"1817_CR82","doi-asserted-by":"crossref","unstructured":"Zareian, A., You, H., Wang, Z., & Chang, S.F. (2020c). Learning visual commonsense for robust scene graph generation. In Proceedings of European Conference on Computer Vision (ECCV) vol. 12368, (pp. 642\u2013657). Springer.","DOI":"10.1007\/978-3-030-58592-1_38"},{"key":"1817_CR83","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., & Choi, Y. (2018). Neural motifs: Scene graph parsing with global context. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5831\u20135840).","DOI":"10.1109\/CVPR.2018.00611"},{"key":"1817_CR84","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., & Chua, T.S. (2017a) Visual translation embedding network for visual relation detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 5532\u20135540).","DOI":"10.1109\/CVPR.2017.331"},{"key":"1817_CR85","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Yu, J., & Chang, S.F. (2017b). Ppr-fcn: Weakly supervised visual relation detection via parallel pairwise r-fcn. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 4233\u20134241).","DOI":"10.1109\/ICCV.2017.454"},{"key":"1817_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, J., Kalantidis, Y., Rohrbach, M., Paluri, M., Elgammal, A., & Elhoseiny, M. (2019). Large-scale visual relationship understanding. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (pp. 9185\u20139194).","DOI":"10.1609\/aaai.v33i01.33019185"},{"key":"1817_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, J., Shih, K.J., Elgammal, A., Tao, A., & Catanzaro, B. (2019). Graphical contrastive losses for scene graph parsing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 11,535\u201311,543).","DOI":"10.1109\/CVPR.2019.01180"},{"key":"1817_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, J., Lin, Z., Lu, H., & He, Y. (2019).Capsal: Leveraging captioning to boost semantics for salient object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 6024\u20136033).","DOI":"10.1109\/CVPR.2019.00618"},{"key":"1817_CR89","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Wang, L., Chen, J., Yu, D., & Li, Y.(2020). Comprehensive image captioning via scene graph decomposition. In Proceedings of European Conference on Computer Vision (ECCV) vol. 12359, (pp. 211\u2013229). Springer.","DOI":"10.1007\/978-3-030-58568-6_13"},{"issue":"2","key":"1817_CR90","first-page":"359","volume":"34","author":"L Zhu","year":"2011","unstructured":"Zhu, L., Chen, Y., Lin, Y., Lin, C., & Yuille, A. (2011). Recursive segmentation and recognition templates for image parsing. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 34(2), 359\u2013371.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01817-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01817-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01817-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T02:06:37Z","timestamp":1692410797000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01817-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,9]]},"references-count":90,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1817"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01817-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,9]]},"assertion":[{"value":"24 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}