{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:20:17Z","timestamp":1743016817758,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695439"},{"type":"electronic","value":"9783030695446"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69544-6_28","type":"book-chapter","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T11:05:00Z","timestamp":1614251100000},"page":"461-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score"],"prefix":"10.1007","author":[{"given":"He","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunta","family":"Saito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuta","family":"Kikuchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eiichi","family":"Matsumoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,26]]},"reference":[{"key":"28_CR1","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., et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"28_CR2","unstructured":"Woo, S., Kim, D., Cho, D., Kweon, I.S.: Linknet: Relational embedding for scene graph. In: Advances in Neural Information Processing Systems, pp. 560\u2013570 (2018)"},{"key":"28_CR3","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":"28_CR4","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"28_CR5","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":"28_CR6","doi-asserted-by":"crossref","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors, pp. 852\u2013869 (2016)","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10685\u201310694 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"28_CR8","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":"28_CR9","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":"28_CR10","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 Conference on Computer Vision and Pattern Recognition, pp. 6163\u20136171 (2019)","DOI":"10.1109\/CVPR.2019.00632"},{"key":"28_CR11","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":"28_CR12","doi-asserted-by":"crossref","unstructured":"Dai, B., Zhang, Y., Lin, D.: Detecting visual relationships with deep relational networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3076\u20133086 (2017)","DOI":"10.1109\/CVPR.2017.352"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"28_CR14","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)"},{"key":"28_CR15","unstructured":"Herzig, R., Raboh, M., Chechik, G., Berant, J., Globerson, A.: Mapping images to scene graphs with permutation-invariant structured prediction. In: Advances in Neural Information Processing Systems, pp. 7211\u20137221 (2018)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Shi, J., Zhang, C., Wang, X.: Factorizable net: an efficient subgraph-based framework for scene graph generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 335\u2013351 (2018)","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"28_CR17","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 1974\u20131982 (2017)","DOI":"10.1109\/ICCV.2017.121"},{"key":"28_CR18","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.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"28_CR19","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1969\u20131978 (2019)","DOI":"10.1109\/CVPR.2019.00207"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Qi, M., Li, W., Yang, Z., Wang, Y., Luo, J.: Attentive relational networks for mapping images to scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3957\u20133966 (2019)","DOI":"10.1109\/CVPR.2019.00408"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Wang, W., Wang, R., Shan, S., Chen, X.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00838"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Zhan, Y., Yu, J., Yu, T., Tao, D.: On exploring undetermined relationships for visual relationship detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00527"},{"key":"28_CR23","unstructured":"Buda, M., Maki, A., Mazurowski, M.A.: A systematic study of the class imbalance problem in convolutional neural networks. CoRR abs\/1710.05381 (2017)"},{"key":"28_CR24","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz, N., Stephen, S.: The class imbalance problem: a systematic study. Intell. Data Anal. 6, 429\u2013449 (2002)","journal-title":"Intell. Data Anal."},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Oksuz, K., Cam, B.C., Kalkan, S., Akbas, E.: Imbalance problems in object detection: a review. arXiv preprint arXiv:1909.00169 (2019)","DOI":"10.1109\/TPAMI.2020.2981890"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Rota Bulo, S., Neuhold, G., Kontschieder, P.: Loss max-pooling for semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2126\u20132135 (2017)","DOI":"10.1109\/CVPR.2017.749"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 761\u2013769 (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"28_CR28","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":"28_CR29","doi-asserted-by":"crossref","unstructured":"Qian, Q., Chen, L., Li, H., Jin, R.: Dr loss: improving object detection by distributional ranking. arXiv preprint arXiv:1907.10156 (2019)","DOI":"10.1109\/CVPR42600.2020.01218"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Chen, K., Li, J., Lin, W., See, J., Wang, J., Duan, L., Chen, Z., He, C., Zou, J.: Towards accurate one-stage object detection with AP-loss. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5119\u20135127 (2019)","DOI":"10.1109\/CVPR.2019.00526"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 539\u2013546. IEEE (2005)","DOI":"10.1109\/CVPR.2005.202"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Kim, M., Sahu, P., Gholami, B., Pavlovic, V.: Unsupervised visual domain adaptation: A deep max-margin gaussian process approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4380\u20134390 (2019)","DOI":"10.1109\/CVPR.2019.00451"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794\u20132802 (2015)","DOI":"10.1109\/ICCV.2015.320"},{"key":"28_CR34","unstructured":"Zhang, C., Jia, B., Gao, F., Zhu, Y., Lu, H., Zhu, S.C.: Learning perceptual inference by contrasting. In: Advances in Neural Information Processing Systems, pp. 1073\u20131085 (2019)"},{"key":"28_CR35","unstructured":"Elsayed, G., Krishnan, D., Mobahi, H., Regan, K., Bengio, S.: Large margin deep networks for classification. In: Advances in neural information processing systems, pp. 842\u2013852 (2018)"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Hayat, M., Khan, S., Zamir, S.W., Shen, J., Shao, L.: Gaussian affinity for max-margin class imbalanced learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6469\u20136479 (2019)","DOI":"10.1109\/ICCV.2019.00657"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, J., Shih, K.J., Elgammal, A., Tao, A., Catanzaro, B.: Graphical contrastive losses for scene graph generation. arXiv preprint arXiv:1903.02728 (2019)","DOI":"10.1109\/CVPR.2019.01180"},{"key":"28_CR38","unstructured":"Liu, T.Y., et al.: Learning to rank for information retrieval. Found. Trends\u00ae Inf. Retrieval 3, 225\u2013331 (2009)"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Sculley, D.: Combined regression and ranking. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, pp. 979\u2013988 (2010)","DOI":"10.1145\/1835804.1835928"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Ibrahim, O.A.S., Landa-Silva, D.: ES-rank: evolution strategy learning to rank approach. In: Proceedings of the Symposium on Applied Computing, ACM, pp. 944\u2013950 (2017)","DOI":"10.1145\/3019612.3019696"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Moon, T., Smola, A., Chang, Y., Zheng, Z.: Intervalrank: isotonic regression with listwise and pairwise constraints. In: Proceedings of the third ACM International Conference on Web Search and Data Mining, ACM, pp. 151\u2013160 (2010)","DOI":"10.1145\/1718487.1718507"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Hua, Y., Kodirov, E., Hu, G., Garnier, R., Robertson, N.M.: Ranked list loss for deep metric learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00535"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE 2009, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"28_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"28_CR45","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69544-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T21:12:33Z","timestamp":1724533953000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69544-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695439","9783030695446"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69544-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"26 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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","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","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 virtually.","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)"}}]}}