{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:38:47Z","timestamp":1782833927423,"version":"3.54.5"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585549","type":"print"},{"value":"9783030585556","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58555-6_35","type":"book-chapter","created":{"date-parts":[[2020,11,15]],"date-time":"2020-11-15T21:04:21Z","timestamp":1605474261000},"page":"584-600","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":133,"title":["Visual Compositional Learning for Human-Object Interaction Detection"],"prefix":"10.1007","author":[{"given":"Zhi","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojiang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,16]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Alfassy, A., et al.: LaSo: label-set operations networks for multi-label few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6548\u20136557 (2019)","DOI":"10.1109\/CVPR.2019.00671"},{"key":"35_CR2","unstructured":"Azadi, S., Pathak, D., Ebrahimi, S., Darrell, T.: Compositional GAN: Learning conditional image composition. arXiv preprint arXiv:1807.07560 (2018)"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Bansal, A., Rambhatla, S.S., Shrivastava, A., Chellappa, R.: Detecting human-object interactions via functional generalization. arXiv preprint arXiv:1904.03181 (2019)","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"35_CR4","unstructured":"Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)"},{"issue":"8","key":"35_CR5","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR6","unstructured":"Burgess, C.P., et al.: Monet: Unsupervised scene decomposition and representation. arXiv preprint arXiv:1901.11390 (2019)"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 381\u2013389. IEEE (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Wang, Z., He, Y., Wang, J., Deng, J.: HICO: a benchmark for recognizing human-object interactions in images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1017\u20131025 (2015)","DOI":"10.1109\/ICCV.2015.122"},{"key":"35_CR9","unstructured":"Gao, C., Zou, Y., Huang, J.B.: iCAN: Instance-centric attention network for human-object interaction detection. arXiv preprint arXiv:1808.10437 (2018)"},{"key":"35_CR10","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.cobeha.2018.12.010","volume":"29","author":"M Garnelo","year":"2019","unstructured":"Garnelo, M., Shanahan, M.: Reconciling deep learning with symbolic artificial intelligence: representing objects and relations. Current Opin. Behav. Sci. 29, 17\u201323 (2019)","journal-title":"Current Opin. Behav. Sci."},{"key":"35_CR11","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, T., Schwing, A., Hoiem, D.: No-frills human-object interaction detection: Factorization, appearance and layout encodings, and training techniques. arXiv preprint arXiv:1811.05967 (2018)","DOI":"10.1109\/ICCV.2019.00977"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5","key":"35_CR14","first-page":"6","volume":"2","author":"I Higgins","year":"2017","unstructured":"Higgins, I., et al.: beta-VAE: Learning basic visual concepts with a constrained variational framework. ICLR 2(5), 6 (2017)","journal-title":"ICLR"},{"key":"35_CR15","unstructured":"Higgins, I., et al.: Scan: Learning hierarchical compositional visual concepts. arXiv preprint arXiv:1707.03389 (2017)"},{"key":"35_CR16","unstructured":"Hoffman, D.D., Richards, W.: Parts of recognition (1983)"},{"issue":"5","key":"35_CR17","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(5), 429\u2013449 (2002)","journal-title":"Intell. Data Anal."},{"key":"35_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-030-01264-9_15","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Kato","year":"2018","unstructured":"Kato, K., Li, Y., Gupta, A.: Compositional learning for human object interaction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 247\u2013264. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_15"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40 (2017)","DOI":"10.1017\/S0140525X16001837"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Transferable interactiveness prior for human-object interaction detection. arXiv preprint arXiv:1811.08264 (2018)","DOI":"10.1109\/CVPR.2019.00370"},{"key":"35_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2537\u20132546 (2019)","DOI":"10.1109\/CVPR.2019.00264"},{"key":"35_CR23","unstructured":"Locatello, F., Bauer, S., Lucic, M., Gelly, S., Sch\u00f6lkopf, B., Bachem, O.: Challenging common assumptions in the unsupervised learning of disentangled representations. arXiv preprint arXiv:1811.12359 (2018)"},{"key":"35_CR24","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. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"35_CR25","unstructured":"van den Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579\u20132605 (2008)"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Peyre, J., Laptev, I., Schmid, C., Sivic, J.: Detecting unseen visual relations using analogies. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00207"},{"key":"35_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/978-3-030-01240-3_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Qi","year":"2018","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.-C.: Learning human-object interactions by graph parsing neural networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 407\u2013423. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_25"},{"key":"35_CR28","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":"35_CR29","doi-asserted-by":"crossref","unstructured":"Shen, L., Yeung, S., Hoffman, J., Mori, G., Fei-Fei, L.: Scaling human-object interaction recognition through zero-shot learning. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1568\u20131576. IEEE (2018)","DOI":"10.1109\/WACV.2018.00181"},{"issue":"1","key":"35_CR30","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1207\/s15516709cog1401_3","volume":"14","author":"ES Spelke","year":"1990","unstructured":"Spelke, E.S.: Principles of object perception. Cogn. Sci. 14(1), 29\u201356 (1990)","journal-title":"Cogn. Sci."},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Wan, B., Zhou, D., Liu, Y., Li, R., He, X.: Pose-aware multi-level feature network for human object interaction detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9469\u20139478 (2019)","DOI":"10.1109\/ICCV.2019.00956"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Deep contextual attention for human-object interaction detection. arXiv preprint arXiv:1910.07721 (2019)","DOI":"10.1109\/ICCV.2019.00579"},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y.X., Girshick, R., Hebert, M., Hariharan, B.: Low-shot learning from imaginary data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7278\u20137286 (2018)","DOI":"10.1109\/CVPR.2018.00760"},{"issue":"9","key":"35_CR34","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","volume":"41","author":"Y Xian","year":"2018","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning\u2013a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2251\u20132265 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning-the good, the bad and the ugly. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4582\u20134591 (2017)","DOI":"10.1109\/CVPR.2017.328"},{"key":"35_CR36","doi-asserted-by":"crossref","unstructured":"Xu, B., Wong, Y., Li, J., Zhao, Q., Kankanhalli, M.S.: Learning to detect human-object interactions with knowledge. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00212"},{"key":"35_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-01258-8_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Yang","year":"2018","unstructured":"Yang, X., Zhang, H., Cai, J.: Shuffle-then-assemble: learning object-agnostic visual relationship features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 38\u201354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_3"},{"key":"35_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, P., Chi, M.: Relation parsing neural network for human-object interaction detection. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00093"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58555-6_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:15:54Z","timestamp":1731629754000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58555-6_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585549","9783030585556"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58555-6_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"16 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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 due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}