{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:04:06Z","timestamp":1766124246679,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819698554"},{"type":"electronic","value":"9789819698561"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9856-1_14","type":"book-chapter","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T12:39:21Z","timestamp":1753187961000},"page":"157-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Classifier Recalibration for Human-Object Interaction Detection"],"prefix":"10.1007","author":[{"given":"Shuwei","family":"Yan","sequence":"first","affiliation":[]},{"given":"Shuang","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Kenan","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Baihua","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Chi","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Shengjie","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,23]]},"reference":[{"key":"14_CR1","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, pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10688344"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, F., Yuan, Y., Campbell, D., Zhong, Z., Gould, S.: Exploring predicate visual context in detecting of human-object interactions. In: 2023 IEEE\/CVF International Conference on Computer Vision, pp. 10411\u201310421 (2023)","DOI":"10.1109\/ICCV51070.2023.00955"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Pan, Y., Yao, T., Huang, R., Mei, T., Chen, C.: Exploring structure-aware transformer over interaction proposals for human-object interaction detection. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19548\u201319557 (2022)","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"14_CR4","unstructured":"Mao, Y., Deng, J., Zhou, W., Li, L., Fang, Y., Li, H.: Clip4hoi: towards adapting clip for practical zero-shot hoi detection. In: Advances in Neural Information Processing Systems, vol. 36, pp. 45895\u201345906 (2023)"},{"key":"14_CR5","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: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20123\u201320132 (2022)","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"14_CR6","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: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23507\u201323517 (2023)","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Gao, J., Liang, K., Wei, T., Chen, W., Ma, Z., Guo, J.: Dual-prior augmented decoding network for long tail distribution in hoi detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 1806\u20131814 (2024)","DOI":"10.1609\/aaai.v38i3.27949"},{"key":"14_CR8","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 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10410\u201310419 (2021)","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"14_CR9","unstructured":"Zhang, A., et al.: Mining the benefits of two-stage and one-stage hoi detection. In: Advances in Neural Information Processing Systems, vol. 34, pp. 17209\u201317220 (2021)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Li, J., Lai, H., Ma, J., Wang, T., Quan, H., Chen, D.: Efficient guided query network for human-object interaction detection. In: 2024 IEEE International Conference on Multimedia and Expo, pp. 1\u20136 (2024)","DOI":"10.1109\/ICME57554.2024.10687644"},{"key":"14_CR11","unstructured":"Li, L., Wei, J., Wang, W., Yang, Y.: Neural-logic human-object interaction detection. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"14_CR12","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":"14_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, X., Ding, C., Xu, X.: Disentangled pre-training for human-object interaction detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28191\u201328201 (2024)","DOI":"10.1109\/CVPR52733.2024.02663"},{"key":"14_CR14","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR, pp. 8748\u20138763 (2021)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Tang, K., Tao, M., Qi, J., Liu, Z., Zhang, H.: Invariant feature learning for generalized long-tailed classification. In: European Conference on Computer Vision, pp. 709\u2013726. Springer (2022)","DOI":"10.1007\/978-3-031-20053-3_41"},{"key":"14_CR16","unstructured":"Zhan, Y., Liu, F., Luo, X., Nie, L., Xu, X., Kankanhalli, M.: Generating human-centric visual cues for human-object interaction detection via large vision-language models. arXiv preprint arXiv:2311.16475 (2023)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Wu, X., Li, Y., 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. Springer, pp. 121\u2013136 (2022)","DOI":"10.1007\/978-3-031-19772-7_8"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Kim. B., Mun, J., On, K., Shin, M., Lee, J., Kim, E.: MSTR: multi-scale transformer for end-to-end human-object interaction detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19578\u201319587 (2022)","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Xie, C., Zeng, F., Hu, Y., Liang, S., Wei, Y.: Category query learning for human-object interaction classification. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15275\u201315284 (2023)","DOI":"10.1109\/CVPR52729.2023.01466"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Wang, P., Han, K., Wei, X., Zhang, L., Wang, L.: Contrastive learning based hybrid networks for long-tailed image classification. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 943\u2013952 (2021)","DOI":"10.1109\/CVPR46437.2021.00100"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Zhu, J., Wang, Z., Chen, J., Chen, Y.P., Jiang, Y.: Balanced contrastive learning for long-tailed visual recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6908\u20136917 (2022)","DOI":"10.1109\/CVPR52688.2022.00679"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Cui, J., Zhong, Z., Liu, S., Yu, B., Jia, J.: Parametric contrastive learning. In: IEEE\/CVF International Conference on Computer Vision, pp. 715\u2013724 (2021)","DOI":"10.1109\/ICCV48922.2021.00075"},{"key":"14_CR23","unstructured":"Goodge, A., Hooi, B., Ng, W.S.: When text and images don\u2019t mix: Bias-correcting language-image similarity scores for anomaly detection. arXiv preprint arXiv:2407.17083 (2024)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Chao, Y., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: 2018 IEEE Winter Conference on Applications of Computer Vision, pp. 381\u2013389 (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"14_CR25","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9856-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T05:59:59Z","timestamp":1766123999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9856-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698554","9789819698561"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9856-1_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}