{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:14:17Z","timestamp":1775578457954,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585198","type":"print"},{"value":"9783030585204","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\/978-3-030-58520-4_15","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"248-264","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["Contextual Heterogeneous Graph Network for Human-Object Interaction Detection"],"prefix":"10.1007","author":[{"given":"Hai","family":"Wang","sequence":"first","affiliation":[]},{"given":"Wei-shi","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Ling","family":"Yingbiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: WACV, pp. 381\u2013389 (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"15_CR3","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: ICCV, pp. 1017\u20131025 (2015)","DOI":"10.1109\/ICCV.2015.122"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: CVPR, pp. 1831\u20131840 (2017)","DOI":"10.1109\/CVPR.2017.601"},{"key":"15_CR5","unstructured":"Delaitre, V., Sivic, J., Laptev, I.: Learning person-object interactions for action recognition in still images. In: NIPS, pp. 1503\u20131511 (2011)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models for static human-object interactions. In: Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, pp. 9\u201316 (2010)","DOI":"10.1109\/CVPRW.2010.5543176"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Feng, W., Liu, W., Li, T., Peng, J., Qian, C., Hu, X.: Turbo learning framework for human-object interactions recognition and human pose estimation. arXiv preprint arXiv:1903.06355 (2019)","DOI":"10.1609\/aaai.v33i01.3301898"},{"key":"15_CR8","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":"15_CR9","unstructured":"Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML, pp. 1263\u20131272 (2017)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: CVPR, pp. 8359\u20138367 (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"issue":"10","key":"15_CR12","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta, A., Kembhavi, A., Davis, L.S.: Observing human-object interactions: using spatial and functional compatibility for recognition. PAMI 31(10), 1775\u20131789 (2009)","journal-title":"PAMI"},{"key":"15_CR13","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, T., Schwing, A., Hoiem, D.: No-frills human-object interaction detection: factorization, layout encodings, and training techniques. In: ICCV, pp. 9677\u20139685 (2019)","DOI":"10.1109\/ICCV.2019.00977"},{"key":"15_CR15","unstructured":"Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS, pp. 1024\u20131034 (2017)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Hu, J.F., Zheng, W.S., Lai, J., Gong, S., Xiang, T.: Recognising human-object interaction via exemplar based modelling. In: ICCV, pp. 3144\u20133151 (2013)","DOI":"10.1109\/ICCV.2013.390"},{"key":"15_CR17","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"issue":"1","key":"15_CR18","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(1), 32\u201373 (2017)","journal-title":"IJCV"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Lee, C.W., Fang, W., Yeh, C.K., Frank Wang, Y.C.: Multi-label zero-shot learning with structured knowledge graphs. In: CVPR, pp. 1576\u20131585 (2018)","DOI":"10.1109\/CVPR.2018.00170"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Chen, X., Zhang, Y., Wang, Y., Tian, Q.: Actional-structural graph convolutional networks for skeleton-based action recognition. In: CVPR, pp. 3595\u20133603 (2019)","DOI":"10.1109\/CVPR.2019.00371"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y.L., Zhou, S., Huang, X., Xu, L., Ma, Z., Fang, H.S., Wang, Y.F., Lu, C.: Transferable interactiveness prior for human-object interaction detection. arXiv preprint arXiv:1811.08264 (2018)","DOI":"10.1109\/CVPR.2019.00370"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"15_CR23","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":"15_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":"15_CR25","doi-asserted-by":"crossref","unstructured":"Peyre, J., Laptev, I., Schmid, C., Sivic, J.: Detecting unseen visual relations using analogies. In: ICCV, pp. 1981\u20131990 (2019)","DOI":"10.1109\/ICCV.2019.00207"},{"issue":"3","key":"15_CR26","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/TPAMI.2011.158","volume":"34","author":"A Prest","year":"2011","unstructured":"Prest, A., Schmid, C., Ferrari, V.: Weakly supervised learning of interactions between humans and objects. PAMI 34(3), 601\u2013614 (2011)","journal-title":"PAMI"},{"key":"15_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":"15_CR28","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"issue":"1","key":"15_CR29","first-page":"81","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: Computational capabilities of graph neural networks. TNN 20(1), 81\u2013102 (2008)","journal-title":"TNN"},{"key":"15_CR30","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: WACV, pp. 1568\u20131576 (2018)","DOI":"10.1109\/WACV.2018.00181"},{"key":"15_CR31","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"15_CR32","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: ICCV, pp. 9469\u20139478 (2019)","DOI":"10.1109\/ICCV.2019.00956"},{"key":"15_CR33","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":"15_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Ye, Y., Gupta, A.: Zero-shot recognition via semantic embeddings and knowledge graphs. In: CVPR, pp. 6857\u20136866 (2018)","DOI":"10.1109\/CVPR.2018.00717"},{"key":"15_CR35","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: CVPR, June 2019","DOI":"10.1109\/CVPR.2019.00212"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Grouplet: a structured image representation for recognizing human and object interactions. In: Computer Society Conference on Computer Vision and Pattern Recognition, pp. 9\u201316 (2010)","DOI":"10.1109\/CVPR.2010.5540234"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: Computer Society Conference on Computer Vision and Pattern Recognition, pp. 17\u201324 (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"15_CR38","unstructured":"Yu, W., Zhou, J., Yu, W., Liang, X., Xiao, N.: Heterogeneous graph learning for visual commonsense reasoning. In: NIPS, pp. 2765\u20132775 (2019)"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, P., Chi, M.: Relation parsing neural network for human-object interaction detection. In: ICCV, pp. 843\u2013851 (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\/978-3-030-58520-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:19:29Z","timestamp":1731889169000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58520-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585198","9783030585204"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58520-4_15","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":"19 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)"}}]}}