{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T10:16:01Z","timestamp":1781518561493,"version":"3.54.1"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197710","type":"print"},{"value":"9783031197727","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19772-7_6","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"87-103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Iwin: Human-Object Interaction Detection via\u00a0Transformer with\u00a0Irregular Windows"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9632-9131","authenticated-orcid":false,"given":"Danyang","family":"Tu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9583-0055","authenticated-orcid":false,"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1235-598X","authenticated-orcid":false,"given":"Wei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"6_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"6_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 (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., Liao, Y., Liu, S., Chen, Z., Wang, F., Qian, C.: Reformulating hoi detection as adaptive set prediction. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Gao, C., Xu, J., Zou, Y., Huang, J.B.: Drg: Dual relation graph for human-object interaction detection. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"6_CR6","unstructured":"Gao, C., Zou, Y., Huang, J.B.: iCAN: instance-centric attention network for human-object interaction detection. In: BMVC (2018)"},{"key":"6_CR7","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":"6_CR8","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"6_CR9","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":"6_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV. pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"6_CR11","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":"6_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1007\/978-3-030-58555-6_35","volume-title":"Computer Vision","author":"Z Hou","year":"2020","unstructured":"Hou, Z., Peng, X., Qiao, Yu., Tao, D.: Visual compositional learning for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 584\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_35"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Hou, Z., Yu, B., Qiao, Y., Peng, X., Tao, D.: Affordance transfer learning for human-object interaction detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"6_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-030-58555-6_30","volume-title":"Computer Vision","author":"B Kim","year":"2020","unstructured":"Kim, B., Choi, T., Kang, J., Kim, H.J.: UnionDet: union-level detector towards real-time human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 498\u2013514. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_30"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.S., Kim, H.J.: Hotr: end-to-end human-object interaction detection with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"6_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/978-3-030-58589-1_43","volume-title":"Computer Vision","author":"D-J Kim","year":"2020","unstructured":"Kim, D.-J., Sun, X., Choi, J., Lin, S., Kweon, I.S.: Detecting human-object interactions with action co-occurrence priors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 718\u2013736. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_43"},{"issue":"1\u20132","key":"6_CR17","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Detailed 2d\u20133d joint representation for human-object interaction. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Pastanet: toward human activity knowledge engine. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"6_CR20","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":"6_CR21","doi-asserted-by":"crossref","unstructured":"Liao, Y., Liu, S., Wang, F., Chen, Y., Qian, C., Feng, J.: Ppdm: parallel point detection and matching for real-time human-object interaction detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"6_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 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Lin, X., Zou, Q., Xu, X.: Action-guided attention mining and relation reasoning network for human-object interaction detection. In: IJCAI (2020)","DOI":"10.24963\/ijcai.2020\/154"},{"key":"6_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-030-58568-6_15","volume-title":"Computer Vision","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Chen, Q., Zisserman, A.: Amplifying key cues for human-object-interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 248\u2013265. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_15"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)"},{"key":"6_CR28","unstructured":"MacQueen, J., et al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley Symposium on Mathematical Statistics and Probability (1967)"},{"key":"6_CR29","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: ICML (2010)"},{"key":"6_CR30","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":"6_CR31","doi-asserted-by":"crossref","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.C.: Learning human-object interactions by graph parsing neural networks. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"6_CR32","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR33","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":"6_CR34","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Tamura, M., Ohashi, H., Yoshinaga, T.: Qpic: query-based pairwise human-object interaction detection with image-wide contextual information. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Ulutan, O., Iftekhar, A., Manjunath, B.S.: Vsgnet: spatial attention network for detecting human object interactions using graph convolutions. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"6_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"6_CR38","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":"6_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-030-58520-4_15","volume-title":"Computer Vision","author":"H Wang","year":"2020","unstructured":"Wang, H., Zheng, W., Yingbiao, L.: Contextual heterogeneous graph network for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 248\u2013264. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_15"},{"key":"6_CR40","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":"6_CR41","doi-asserted-by":"crossref","unstructured":"Wang, T., Yang, T., Danelljan, M., Khan, F.S., Zhang, X., Sun, J.: Learning human-object interaction detection using interaction points. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Xu, B., Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S.: Interact as you intend: Intention-driven human-object interaction detection. In: TMM (2019)","DOI":"10.1109\/TMM.2019.2943753"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Yang, D., Zou, Y.: A graph-based interactive reasoning for human-object interaction detection. In: IJCAI (2020)","DOI":"10.24963\/ijcai.2020\/155"},{"key":"6_CR44","first-page":"17209","volume":"34","author":"A Zhang","year":"2021","unstructured":"Zhang, A., et al.: Mining the benefits of two-stage and one-stage hoi detection. NIPs 34, 17209\u201317220 (2021)","journal-title":"NIPs"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Spatially conditioned graphs for detecting human-object interactions. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Zhong, X., Ding, C., Qu, X., Tao, D.: Polysemy deciphering network for robust human-object interaction detection. In: ICCV (2021)","DOI":"10.1007\/s11263-021-01458-8"},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Zhong, X., Qu, X., Ding, C., Tao, D.: Glance and gaze: inferring action-aware points for one-stage human-object interaction detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"6_CR48","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"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, W., Qi, S., Ling, H., Shen, J.: Cascaded human-object interaction recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00432"},{"key":"6_CR50","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. In: ICLR (2020)"},{"key":"6_CR51","doi-asserted-by":"crossref","unstructured":"Zou, C., et al.: End-to-end human object interaction detection with hoi transformer. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01165"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19772-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:48:59Z","timestamp":1710262139000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19772-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197710","9783031197727"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19772-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"28 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}