{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:26:38Z","timestamp":1781292398184,"version":"3.54.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030865191","type":"print"},{"value":"9783030865207","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86520-7_29","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T15:25:48Z","timestamp":1631201148000},"page":"466-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Zero-Shot Scene Graph Relation Prediction Through Commonsense Knowledge Integration"],"prefix":"10.1007","author":[{"given":"Xuan","family":"Kan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hejie","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carl","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"29_CR1","first-page":"2653","volume":"18","author":"A Benavoli","year":"2017","unstructured":"Benavoli, A., Corani, G., Dem\u0161ar, J., Zaffalon, M.: Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis. JMLR 18, 2653\u20132688 (2017)","journal-title":"JMLR"},{"key":"29_CR2","unstructured":"Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML (2017)"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Wang, G., Chen, T.: Stack-captioning: coarse-to-fine learning for image captioning. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., Ling, M.: Scene graph generation with external knowledge and image reconstruction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00207"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR7","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"29_CR8","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. IJCV 123, 32\u201373 (2017)","journal-title":"IJCV"},{"key":"29_CR9","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. In: NeurIPS (2019)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Torr, P., Lukasiewicz, T.: Lightweight generative adversarial networks for text-guided image manipulation. In: NeurIPS (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Torr, P., Lukasiewicz, T.: ManiGAN: text-guided image manipulation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"29_CR12","unstructured":"Li, G., Su, H., Zhu, W.: Incorporating external knowledge to answer open-domain visual questions with dynamic memory networks (2017)"},{"key":"29_CR13","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d","volume":"22","author":"H Liu","year":"2004","unstructured":"Liu, H., Singh, P.: ConceptNet \u2013 a practical commonsense reasoning tool-kit. BT Technol. J. 22, 211\u2013226 (2004)","journal-title":"BT Technol. J."},{"key":"29_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"29_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"29_CR16","unstructured":"Murphy, K., Weiss, Y., Jordan, M.I.: Loopy belief propagation for approximate inference: an empirical study. In: UAI (1999)"},{"key":"29_CR17","unstructured":"Newell, A., Deng, J.: Pixels to graphs by associative embedding. In: NeurIPS (2017)"},{"key":"29_CR18","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv (2018)"},{"key":"29_CR19","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Speer, R., Chin, J., Havasi, C.: ConceptNet 5.5: an open multilingual graph of general knowledge. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., van Den Hengel, A.: Graph-structured representations for visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.344"},{"issue":"6","key":"29_CR23","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TPAMI.2017.2708709","volume":"40","author":"Q Wu","year":"2018","unstructured":"Wu, Q., Shen, C., Wang, P., Dick, A., van den Hengel, A.: Image captioning and visual question answering based on attributes and external knowledge. TPAMI 40(6), 1367\u20131381 (2018)","journal-title":"TPAMI"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"29_CR25","unstructured":"Yang, C.: Multi-facet graph mining with contextualized projections. Ph.D. thesis (2020)"},{"key":"29_CR26","unstructured":"Yang, C., Xiao, Y., Zhang, Y., Sun, Y., Han, J.: Heterogeneous network representation learning: a unified framework with survey and benchmark. TKDE (2020)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: Multisage: empowering graphsage with contextualized multi-embedding on web-scale multipartite networks. In: KDD (2020)","DOI":"10.1145\/3394486.3403293"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhang, J., Han, J.: Co-embedding network nodes and hierarchical labels with taxonomy based generative adversarial networks. In: ICDM (2020)","DOI":"10.1109\/ICDM50108.2020.00081"},{"key":"29_CR29","unstructured":"Yang, C., Zhuang, P., Shi, W., Luu, A., Pan, L.: Conditional structure generation through graph variational generative adversarial nets. In: NeurIPS (2019)"},{"key":"29_CR30","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.isprsjprs.2017.07.010","volume":"131","author":"MY Yang","year":"2017","unstructured":"Yang, M.Y., Liao, W., Ackermann, H., Rosenhahn, B.: On support relations and semantic scene graphs. ISPRS J. Photogramm. Remote Sens. 131, 15\u201325 (2017)","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"29_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/978-3-030-01264-9_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Yao","year":"2018","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 711\u2013727. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_42"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Morariu, V.I., Davis, L.S.: Visual relationship detection with internal and external linguistic knowledge distillation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.121"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural Motifs: scene graph parsing with global context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"29_CR36","unstructured":"Zhu, Y., Zhang, C., R\u00e9, C., Fei-Fei, L.: Building a large-scale multimodal knowledge base system for answering visual queries. arXiv preprint arXiv:1507.05670 (2015)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86520-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:07:25Z","timestamp":1757369245000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86520-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865191","9783030865207"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86520-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"10 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"869","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"210","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}