{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:43:38Z","timestamp":1770356618397,"version":"3.49.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730061","type":"print"},{"value":"9783031730078","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73007-8_7","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T19:02:40Z","timestamp":1727722960000},"page":"105-121","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Granularity Sparse Relationship Matrix Prediction Network for\u00a0End-to-End Scene Graph Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2023-0934","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5548-3634","authenticated-orcid":false,"given":"Zejian","family":"Yuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1710-3818","authenticated-orcid":false,"given":"Badong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"7_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Chen, C., Zhan, Y., Yu, B., Liu, L., Luo, Y., Du, B.: Resistance training using prior bias: toward unbiased scene graph generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 1, pp. 212\u2013220 (2022)","DOI":"10.1609\/aaai.v36i1.19896"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., Liao, Y., Liu, S., Chen, Z., Wang, F., Qian, C.: Reformulating hoi detection as adaptive set prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9004\u20139013 (2021)","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Jin, Q., Wang, P., Wu, Q.: Say as you wish: fine-grained control of image caption generation with abstract scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9962\u20139971 (2020)","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., Lin, L.: Knowledge-embedded routing network for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6163\u20136171 (2019)","DOI":"10.1109\/CVPR.2019.00632"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Cong, Y., Yang, M.Y., Rosenhahn, B.: RelTR: relation transformer for scene graph generation. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Dong, X., Gan, T., Song, X., Wu, J., Cheng, Y., Nie, L.: Stacked hybrid-attention and group collaborative learning for unbiased scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19427\u201319436 (2022)","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"7_CR8","unstructured":"Gao, L., et al.: Informative scene graph generation via debiasing. arXiv preprint arXiv:2308.05286 (2023)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1219\u20131228 (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.S., Kim, H.J.: HOTR: end-to-end human-object interaction detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 74\u201383 (2021)","DOI":"10.1109\/CVPR46437.2021.00014"},{"issue":"1","key":"7_CR13","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"issue":"1\u20132","key":"7_CR14","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Nav. Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Nav. Res. Logist. Q."},{"issue":"7","key":"7_CR15","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., He, X.: SGTR: end-to-end scene graph generation with transformer. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19486\u201319496 (2022)","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., Wan, B., He, X.: Bipartite graph network with adaptive message passing for unbiased scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11109\u201311119 (2021)","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, H., Bai, Q., Zhao, G., Jiang, N., Yuan, X.: PPDL: predicate probability distribution based loss for unbiased scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19447\u201319456 (2022)","DOI":"10.1109\/CVPR52688.2022.01884"},{"key":"7_CR19","unstructured":"Li, Y., Ma, T., Bai, Y., Duan, N., Wei, S., Wang, X.: PasteGAN: a semi-parametric method to generate image from scene graph. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., Tao, D.: GPS-Net: graph property sensing network for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3746\u20133753 (2020)","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., Yan, N., Mortazavi, M., Bhanu, B.: Fully convolutional scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11546\u201311556 (2021)","DOI":"10.1109\/CVPR46437.2021.01138"},{"key":"7_CR23","unstructured":"Lyu, X., et al.: Generalized unbiased scene graph generation. arXiv preprint arXiv:2308.04802 (2023)"},{"key":"7_CR24","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Schroeder, B., Tripathi, S.: Structured query-based image retrieval using scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 178\u2013179 (2020)","DOI":"10.1109\/CVPRW50498.2020.00097"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3716\u20133725 (2020)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6619\u20136628 (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., van Den\u00a0Hengel, A.: Graph-structured representations for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a01\u20139 (2017)","DOI":"10.1109\/CVPR.2017.344"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Seesaw loss for long-tailed instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9695\u20139704 (2021)","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Wen, Z., Li, X., Guo, Z., Yang, J., Liu, Z.: Pair then relation: pair-net for panoptic scene graph generation. arXiv preprint arXiv:2307.08699 (2023)","DOI":"10.1109\/TPAMI.2024.3442301"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Wang, L., Yuan, Z., Chen, B.: Learning to generate an unbiased scene graph by using attribute-guided predicate features. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2581\u20132589 (2023)","DOI":"10.1609\/aaai.v37i2.25356"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410\u20135419 (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Yang, G., Zhang, J., Zhang, Y., Wu, B., Yang, Y.: Probabilistic modeling of semantic ambiguity for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12527\u201312536 (2021)","DOI":"10.1109\/CVPR46437.2021.01234"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Yang, J., Lu, J., Lee, S., Batra, D., Parikh, D.: Graph R-CNN for scene graph generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 670\u2013685 (2018)","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Yu, J., Chai, Y., Wang, Y., Hu, Y., Wu, Q.: Cogtree: cognition tree loss for unbiased scene graph generation. In: Zhou, Z.H. (ed.) Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pp. 1274\u20131280. International Joint Conferences on Artificial Intelligence Organization, August 2021","DOI":"10.24963\/ijcai.2021\/176"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"7_CR37","doi-asserted-by":"publisher","unstructured":"Zhang, A. et al.: Fine-grained scene graph generation with data transfer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13687, pp. 409\u2013424. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_24","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., Chua, T.S.: Visual translation embedding network for visual relation detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5532\u20135540 (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, J., Shih, K.J., Elgammal, A., Tao, A., Catanzaro, B.: Graphical contrastive losses for scene graph parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11535\u201311543 (2019)","DOI":"10.1109\/CVPR.2019.01180"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, C., Lyu, X., Gao, L., Dai, B., Song, J.: Prototype-based embedding network for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22783\u201322792 (2023)","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"7_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-3-030-58568-6_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhong","year":"2020","unstructured":"Zhong, Y., Wang, L., Chen, J., Yu, D., Li, Y.: Comprehensive image captioning via scene graph decomposition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 211\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_13"},{"key":"7_CR42","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73007-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T19:05:52Z","timestamp":1727723152000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73007-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031730061","9783031730078"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73007-8_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}