{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T10:15:13Z","timestamp":1781518513026,"version":"3.54.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585648","type":"print"},{"value":"9783030585655","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\/978-3-030-58565-5_5","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"69-85","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Polysemy Deciphering Network for Human-Object Interaction Detection"],"prefix":"10.1007","author":[{"given":"Xubin","family":"Zhong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changxing","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian","family":"Qu","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":[[2020,11,12]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Ashual, O., Wolf, L.: Specifying object attributes and relations in interactive scene generation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00466"},{"key":"5_CR2","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":"5_CR3","doi-asserted-by":"crossref","unstructured":"Cadene, R., Ben-Younes, H., Cord, M., Thome, N.: MUREL: multimodal relational reasoning for visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00209"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: WACV (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., Lin, L.: Knowledge-embedded routing network for scene graph generation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00632"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"5_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-01249-6_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H-S Fang","year":"2018","unstructured":"Fang, H.-S., Cao, J., Tai, Y.-W., Lu, C.: Pairwise body-part attention for recognizing human-object interactions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 52\u201368. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_4"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., Lu, C.: RMPE: regional multi-person pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"5_CR9","unstructured":"Gao, C., Zou, Y., Huang, J.B.: iCAN: instance-centric attention network for human-object interaction detection. In: BMVC (2018)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Dynamic fusion with intra-and inter-modality attention flow for visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00680"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"5_CR12","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":"5_CR13","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"5_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 (2019)","DOI":"10.1109\/ICCV.2019.00977"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"He, S., Tavakoli, H.R., Borji, A., Pugeault, N.: Human attention in image captioning: dataset and analysis. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00862"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Transferable interactiveness knowledge for human-object interaction detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00370"},{"key":"5_CR17","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":"5_CR18","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., Tao, D.: GPS-Net: graph property sensing network for scene graph generation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"5_CR19","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":"5_CR20","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"5_CR21","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS (2013)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Peyre, J., Laptev, I., Schmid, C., Sivic, J.: Detecting unseen visual relations using analogies. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00207"},{"key":"5_CR23","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":"5_CR24","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Shen, L., Yeung, S., Hoffman, J., Mori, G., Li, F.F.: Scaling human-object interaction recognition through zero-shot learning. In: WACV (2018)","DOI":"10.1109\/WACV.2018.00181"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Shrestha, R., Kafle, K., Kanan, C.: Answer them all! toward universal visual question answering models. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01072"},{"key":"5_CR27","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 (2019)","DOI":"10.1109\/ICCV.2019.00956"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Wan, H., Luo, Y., Peng, B., Zheng, W.S.: Representation learning for scene graph completion via jointly structural and visual embedding. In: IJCAI (2018)","DOI":"10.24963\/ijcai.2018\/132"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Deep contextual attention for human-object interaction detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00579"},{"key":"5_CR30","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00838"},{"key":"5_CR31","doi-asserted-by":"publisher","unstructured":"Xu, B., Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S.: Interact as you intend: intention-driven human-object interaction detection. IEEE Trans. Multimed., 1 (2019). https:\/\/doi.org\/10.1109\/TMM.2019.2943753","DOI":"10.1109\/TMM.2019.2943753"},{"key":"5_CR32","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 (2019)","DOI":"10.1109\/CVPR.2019.00212"},{"key":"5_CR33","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":"5_CR34","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Hierarchy parsing for image captioning. arXiv preprint arXiv:1909.03918 (2019)","DOI":"10.1109\/ICCV.2019.00271"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, P., Chi, M.: Relation parsing neural network for human-object interaction detection. In: ICCV (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\/978-3-030-58565-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:03:44Z","timestamp":1731283424000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_5","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":"12 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.","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)"}}]}}