{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T02:58:36Z","timestamp":1768273116023,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556755","type":"print"},{"value":"9789819556762","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\/978-981-95-5676-2_19","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:03Z","timestamp":1768249923000},"page":"277-291","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchy-Aware Harmonization Network for\u00a0Open-Vocabulary HOI Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1820-4764","authenticated-orcid":false,"given":"Chong","family":"Cao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2985-2786","authenticated-orcid":false,"given":"Mingliang","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Shu","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Wanquan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xiaodong","family":"Duan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"19_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":"19_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Yanai, K.: Qahoi: query-based anchors for human-object interaction detection. In: 2023 18th International Conference on Machine Vision and Applications (MVA), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.23919\/MVA57639.2023.10215534"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Dong, J., Yang, H., Pan, R.: Exploring interactive semantic alignment for efficient hoi detection with vision-language model. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10688344"},{"key":"19_CR5","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Gao, J., Yap, K.H., Wu, K., Phan, D.T., Garg, K., Han, B.S.: Contextual human object interaction understanding from pre-trained large language model. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 13436\u201313440. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447511"},{"key":"19_CR7","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Hou, Z., Yu, B., Qiao, Y., Peng, X., Tao, D.: Affordance transfer learning for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 495\u2013504 (2021)","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Hou, Z., Yu, B., Qiao, Y., Peng, X., Tao, D.: Detecting human-object interaction via fabricated compositional learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14646\u201314655 (2021)","DOI":"10.1109\/CVPR46437.2021.01441"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Iftekhar, A., Chen, H., Kundu, K., Li, X., Tighe, J., Modolo, D.: What to look at and where: semantic and spatial refined transformer for detecting human-object interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5353\u20135363 (2022)","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"19_CR11","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"},{"issue":"1\u20132","key":"19_CR12","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. Quarterly 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Quarterly"},{"key":"19_CR13","unstructured":"Lei, T., Yin, S., Chen, Q., Peng, Y., Liu, Y.: Open-vocabulary hoi detection with interaction-aware prompt and concept calibration. arXiv preprint arXiv:2508.03207 (2025)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Lei, T., Yin, S., Liu, Y.: Exploring the potential of large foundation models for open-vocabulary hoi detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16657\u201316667 (2024)","DOI":"10.1109\/CVPR52733.2024.01576"},{"key":"19_CR15","first-page":"5011","volume":"33","author":"YL Li","year":"2020","unstructured":"Li, Y.L., Liu, X., Wu, X., Li, Y., Lu, C.: Hoi analysis: integrating and decomposing human-object interaction. Adv. Neural. Inf. Process. Syst. 33, 5011\u20135022 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR16","unstructured":"Li, Y., Li, Z., Zeng, Q., Hou, Q., Cheng, M.M.: Cascade-clip: cascaded vision-language embeddings alignment for zero-shot semantic segmentation. arXiv preprint arXiv:2406.00670 (2024)"},{"key":"19_CR17","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":"19_CR18","doi-asserted-by":"crossref","unstructured":"Lin, X., Shi, C., Yang, Z., Tang, H., Zhou, Z.: SGC-net: stratified granular comparison network for open-vocabulary hoi detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4539\u20134549 (2025)","DOI":"10.1109\/CVPR52734.2025.00428"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, Y.L., Lu, C.: Highlighting object category immunity for the generalization of human-object interaction detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 1819\u20131827 (2022)","DOI":"10.1609\/aaai.v36i2.20075"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, Y.L., Wu, X., Tai, Y.W., Lu, C., Tang, C.K.: Interactiveness field in human-object interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20113\u201320122 (2022)","DOI":"10.1109\/CVPR52688.2022.01948"},{"issue":"4","key":"19_CR21","doi-asserted-by":"publisher","first-page":"2415","DOI":"10.1109\/TPAMI.2023.3331738","volume":"46","author":"S Ma","year":"2023","unstructured":"Ma, S., Wang, Y., Wang, S., Wei, Y.: Fgahoi: fine-grained anchors for human-object interaction detection. IEEE Trans. Patt. Anal. Mach. Intell. 46(4), 2415\u20132429 (2023)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Ning, S., Qiu, L., Liu, Y., He, X.: Hoiclip: efficient knowledge transfer for hoi detection with vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23507\u201323517 (2023)","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Park, J., Park, J.W., Lee, J.S.: Viplo: vision transformer based pose-conditioned self-loop graph for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17152\u201317162 (2023)","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"19_CR24","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":"19_CR25","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"19_CR26","unstructured":"Ren, S., He, K., Girshick, R., Sun, J., Faster, R.: Towards real-time object detection with region proposal networks, adv. Neural Inf. Process 28 (2015)"},{"key":"19_CR27","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":"19_CR28","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":"19_CR29","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\/CVF International Conference on Computer Vision, pp. 9469\u20139478 (2019)","DOI":"10.1109\/ICCV.2019.00956"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Wang, G., Guo, Y., Wong, Y., Kankanhalli, M.: Distance matters in human-object interaction detection. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4546\u20134554 (2022)","DOI":"10.1145\/3503161.3547793"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Wang, S., Duan, Y., Ding, H., Tan, Y.P., Yap, K.H., Yuan, J.: Learning transferable human-object interaction detector with natural language supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 939\u2013948 (2022)","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Wang, S., Yap, K.H., Ding, H., Wu, J., Yuan, J., Tan, Y.P.: Discovering human interactions with large-vocabulary objects via query and multi-scale detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13475\u201313484 (2021)","DOI":"10.1109\/ICCV48922.2021.01322"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Wu, E.Z., Li, Y., Wang, Y., Wang, S.: Exploring pose-aware human-object interaction via hybrid learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17815\u201317825 (2024)","DOI":"10.1109\/CVPR52733.2024.01687"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Wu, X., Li, Y.L., Liu, X., Zhang, J., Wu, Y., Lu, C.: Mining cross-person cues for body-part interactiveness learning in hoi detection. In: European Conference on Computer Vision, pp. 121\u2013136. Springer (2022)","DOI":"10.1007\/978-3-031-19772-7_8"},{"issue":"23","key":"19_CR35","doi-asserted-by":"publisher","first-page":"12492","DOI":"10.1007\/s10489-024-05774-7","volume":"54","author":"K Xue","year":"2024","unstructured":"Xue, K., et al.: Adaptive multimodal prompt for human-object interaction with local feature enhanced transformer. Appl. Intell. 54(23), 12492\u201312504 (2024)","journal-title":"Appl. Intell."},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Xue, M., Wang, S., Fu, B., Zhao, Z., Liu, T., Lai, L.: Segmenting key clues to induce human-object interaction detection. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 60\u201371. Springer (2023)","DOI":"10.1007\/978-981-99-8429-9_5"},{"key":"19_CR37","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":"19_CR38","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":"19_CR39","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"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Yuan, Y., Campbell, D., Zhong, Z., Gould, S.: Exploring predicate visual context in detecting of human-object interactions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10411\u201310421 (2023)","DOI":"10.1109\/ICCV51070.2023.00955"},{"key":"19_CR41","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3427800","volume-title":"Geometric features enhanced human-object interaction detection","author":"M Zhu","year":"2024","unstructured":"Zhu, M., Ho, E.S., Chen, S., Yang, L., Shum, H.P.: Geometric features enhanced human-object interaction detection. IEEE Trans. Instr, Measure (2024)"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Zong, D., Sun, S.: Zero-shot human-object interaction detection via similarity propagation. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3309104"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5676-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:12Z","timestamp":1768249932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5676-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556755","9789819556762"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5676-2_19","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":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}