{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T08:49:53Z","timestamp":1768121393337,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557608","type":"print"},{"value":"9789819557615","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\/978-981-95-5761-5_34","type":"book-chapter","created":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:52:23Z","timestamp":1768110743000},"page":"488-502","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Simultaneous Vision-Language Knowledge Transfer for\u00a0Zero-Shot Human-Object Interaction Detection"],"prefix":"10.1007","author":[{"given":"Binbin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"34_CR1","unstructured":"Cao, Y., Tang, Q., Su, X., Chen, S., You, S., Lu, X., Xu, C.: Detecting any human-object interaction relationship: Universal hoi detector with spatial prompt learning on foundation models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"34_CR2","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":"34_CR3","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":"34_CR4","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"34_CR5","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 \u2013 ECCV 2020","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":"34_CR6","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":"34_CR7","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":"34_CR8","doi-asserted-by":"publisher","unstructured":"Hou, Z., Yu, B., Tao, D.: Discovering human-object interaction concepts via self-compositional learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 461\u2013478. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_27","DOI":"10.1007\/978-3-031-19812-0_27"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Hu, W., Xu, Y., Li, Y., Li, W., Chen, Z., Tu, Z.: BLIVA: a simple multimodal LLM for better handling of text-rich visual questions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 2256\u20132264 (2024)","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, W., Ren, W., Tian, J., Qu, L., Wang, Z., Liu, H.: Exploring self-and cross-triplet correlations for human-object interaction detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 2543\u20132551 (2024)","DOI":"10.1609\/aaai.v38i3.28031"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1219\u20131228 (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"34_CR12","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":"34_CR13","doi-asserted-by":"crossref","unstructured":"Lei, T., Caba, F., Chen, Q., Jin, H., Peng, Y., Liu, Y.: Efficient adaptive human-object interaction detection with concept-guided memory. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6480\u20136490 (2023)","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"34_CR14","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"34_CR15","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: BOOTSTRAPPING LANGUAGE-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"34_CR16","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR17","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":"34_CR18","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":"34_CR19","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":"34_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"},{"key":"34_CR21","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":"34_CR22","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":"34_CR23","doi-asserted-by":"publisher","unstructured":"Peng, W., Chen, Q., Tang, K., Yang, Z., Xing, M., Fang, M.: MIT: multi-cue injected transformer for two-stage hoi detection. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV). pp. 481\u2013495. Springer (2024). https:\/\/doi.org\/10.1007\/978-981-97-8511-7_34","DOI":"10.1007\/978-981-97-8511-7_34"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Qu, X., Ding, C., Li, X., Zhong, X., Tao, D.: Distillation using oracle queries for transformer-based human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19558\u201319567 (2022)","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"34_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":"34_CR26","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":"34_CR27","doi-asserted-by":"crossref","unstructured":"Wang, B., Wu, T., Zhu, M., Du, P.: Interactive image synthesis with panoptic layout generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7783\u20137792 (2022)","DOI":"10.1109\/CVPR52688.2022.00763"},{"issue":"10","key":"34_CR28","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","volume":"40","author":"P Wang","year":"2017","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., Van Den Hengel, A.: FVQA: Fact-based Visual Question Answering. IEEE Trans. Pattern Anal. Mach. Intell. 40(10), 2413\u20132427 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"17","key":"34_CR29","doi-asserted-by":"publisher","first-page":"19157","DOI":"10.1109\/JSEN.2021.3089705","volume":"21","author":"X Weiyao","year":"2021","unstructured":"Weiyao, X., Muqing, W., Min, Z., Ting, X.: Fusion of skeleton and RGB features for RGB-D human action recognition. IEEE Sens. J. 21(17), 19157\u201319164 (2021)","journal-title":"IEEE Sens. J."},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Wu, M., Gu, J., Shen, Y., Lin, M., Chen, C., Sun, X.: End-to-end zero-shot hoi detection via vision and language knowledge distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2839\u20132846 (2023)","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Wu, M., Liu, Y., Ji, J., Sun, X., Ji, R.: Toward open-set human object interaction detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 6066\u20136073 (2024)","DOI":"10.1609\/aaai.v38i6.28422"},{"issue":"10","key":"34_CR32","doi-asserted-by":"publisher","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","volume":"45","author":"P Xu","year":"2023","unstructured":"Xu, P., Zhu, X., Clifton, D.A.: Multimodal learning with transformers: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 12113\u201312132 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR33","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":"34_CR34","first-page":"37416","volume":"35","author":"H Yuan","year":"2022","unstructured":"Yuan, H., et al.: RLIP: Relational Language-Image Pre-training for human-object interaction detection. Adv. Neural. Inf. Process. Syst. 35, 37416\u201337431 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR35","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":"34_CR36","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":"34_CR37","first-page":"36067","volume":"35","author":"H Zhang","year":"2022","unstructured":"Zhang, H., et al.: GLIPV2: unifying localization and vision-language understanding. Adv. Neural. Inf. Process. Syst. 35, 36067\u201336080 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, S., Xu, B., Jin, Q.: Open-category human-object interaction pre-training via language modeling framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19392\u201319402 (2023)","DOI":"10.1109\/CVPR52729.2023.01858"},{"key":"34_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhu, Y., Wang, H., Wen, H., Yan, Y., Liu, P.: Skeleton sequence and RGB frame based multi-modality feature fusion network for action recognition. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 18(3), 1\u201324 (2022)","DOI":"10.1145\/3491228"},{"key":"34_CR40","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","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5761-5_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:52:28Z","timestamp":1768110748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5761-5_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557608","9789819557615"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5761-5_34","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":"12 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"}}]}}