{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T02:21:24Z","timestamp":1772936484716,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819564255","type":"print"},{"value":"9789819564262","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-6426-2_1","type":"book-chapter","created":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T08:07:02Z","timestamp":1772870822000},"page":"3-14","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-relational Context Learning with\u00a0Cross-Attention Augmentation for\u00a0Human Object Interaction Detection"],"prefix":"10.1007","author":[{"given":"Wuyou","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7940-7801","authenticated-orcid":false,"given":"Jiaying","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8209-1775","authenticated-orcid":false,"given":"Jing","family":"Shan","sequence":"additional","affiliation":[]},{"given":"Xiaoxu","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"1_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 \u2013 ECCV 2020","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":"1_CR2","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":"1_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9004\u20139013 (2021)","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, Y., Shao, D., Lu, C.: Dirv: dense interaction region voting for end-to-end human-object interaction detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1291\u20131299 (2021)","DOI":"10.1609\/aaai.v35i2.16217"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-030-58610-2_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Gao","year":"2020","unstructured":"Gao, C., Xu, J., Zou, Y., Huang, J.-B.: DRG: dual relation graph for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 696\u2013712. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_41"},{"key":"1_CR6","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":"1_CR7","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 \u2013 ECCV 2020","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":"1_CR8","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 74\u201383 (2021)","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Kim, B., Mun, J., On, K.W., Shin, M., Lee, J., Kim, E.S.: Mstr: multi-scale transformer for end-to-end human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19578\u201319587 (2022)","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Kim, S., Jung, D., Cho, M.: Relational context learning for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2925\u20132934 (2023)","DOI":"10.1109\/CVPR52729.2023.00286"},{"key":"1_CR11","doi-asserted-by":"crossref","first-page":"21158","DOI":"10.52202\/075280-0924","volume":"36","author":"L Li","year":"2023","unstructured":"Li, L., Wei, J., Wang, W., Yang, Y.: Neural-logic human-object interaction detection. Adv. Neural. Inf. Process. Syst. 36, 21158\u201321171 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Transferable interactiveness knowledge for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3585\u20133594 (2019)","DOI":"10.1109\/CVPR.2019.00370"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Liao, Y., Zhang, A., Lu, M., Wang, Y., Li, X., Liu, S.: Gen-vlkt: simplify association and enhance interaction understanding for hoi detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20123\u201320132 (2022)","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"1_CR14","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":"1_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yuan, J., Chen, C.W.: Consnet: learning consistency graph for zero-shot human-object interaction detection. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4235\u20134243 (2020)","DOI":"10.1145\/3394171.3413600"},{"key":"1_CR16","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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 401\u2013417 (2018)","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"1_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"1_CR18","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10410\u201310419 (2021)","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"1_CR19","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13617\u201313626 (2020)","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"1_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Wang, G., Guo, Y., Xu, Z., Kankanhalli, M.: Bilateral adaptation for human-object interaction detection with occlusion-robustness. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27970\u201327980 (2024)","DOI":"10.1109\/CVPR52733.2024.02642"},{"key":"1_CR22","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 \u2013 ECCV 2020","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":"1_CR23","doi-asserted-by":"publisher","unstructured":"Wang, J., Cao, L., Shan, J., Song, X., Jiang, J.: Dual learning model of code summary and generation based on transformer. In: International Conference on Web Information Systems and Applications, pp. 41\u201352. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-981-97-7707-5_4","DOI":"10.1007\/978-981-97-7707-5_4"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Wang, J., Hao, S., Shan, J., Song, X.: Visual language\u2013let the product say what you want. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 23841\u201323843 (2024)","DOI":"10.1609\/aaai.v38i21.30583"},{"key":"1_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114557","volume":"171","author":"J Wang","year":"2021","unstructured":"Wang, J., Shan, J., Santos, O.E., Bao, J.: High quality error-tolerant phrase mining on text corpus. Expert Syst. Appl. 171, 114557 (2021)","journal-title":"Expert Syst. Appl."},{"key":"1_CR26","doi-asserted-by":"publisher","unstructured":"Wang, J., Yang, H., Shan, J., Song, X., Jiang, J.: Attention-based spatial-temporal fusion networks for traffic flow prediction. In: International Conference on Web Information Systems and Applications, pp. 500\u2013511. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-981-97-7707-5_41","DOI":"10.1007\/978-981-97-7707-5_41"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, B., Zeng, A., Zhang, L., Zhang, R.: Open-world human-object interaction detection via multi-modal prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16954\u201316964 (2024)","DOI":"10.1109\/CVPR52733.2024.01604"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: Rlipv2: fast scaling of relational language-image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21649\u201321661 (2023)","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"1_CR29","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. Adv. Neural. Inf. Process. Syst. 34, 17209\u201317220 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Spatially conditioned graphs for detecting human-object interactions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13319\u201313327 (2021)","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20104\u201320112 (2022)","DOI":"10.1109\/CVPR52688.2022.01947"},{"issue":"1","key":"1_CR32","doi-asserted-by":"publisher","first-page":"218","DOI":"10.3390\/electronics12010218","volume":"12","author":"R Zhen","year":"2023","unstructured":"Zhen, R., Song, W., He, Q., Cao, J., Shi, L., Luo, J.: Human-computer interaction system: a survey of talking-head generation. Electronics 12(1), 218 (2023)","journal-title":"Electronics"},{"key":"1_CR33","first-page":"107633","volume":"37","author":"F Zhu","year":"2024","unstructured":"Zhu, F., Yang, J., Jiang, H.: Towards flexible visual relationship segmentation. Adv. Neural. Inf. Process. Syst. 37, 107633\u2013107661 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Zou, C., et\u00a0al.: End-to-end human object interaction detection with hoi transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11825\u201311834 (2021)","DOI":"10.1109\/CVPR46437.2021.01165"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6426-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T08:07:11Z","timestamp":1772870831000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6426-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819564255","9789819564262"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6426-2_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WISA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Information Systems and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wisa22025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ccf.org.cn\/Chapters\/TC\/TC_Listing\/TCIS_\/tzzw\/2025-02-21\/838214.shtml","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}