{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:47:49Z","timestamp":1777657669029,"version":"3.51.4"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726545","type":"print"},{"value":"9783031726552","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"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\/978-3-031-72655-2_9","type":"book-chapter","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T10:10:51Z","timestamp":1733393451000},"page":"148-165","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["OpenKD: Opening Prompt Diversity for\u00a0Zero- and\u00a0Few-Shot Keypoint Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1894-286X","authenticated-orcid":false,"given":"Changsheng","family":"Lu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3666-1778","authenticated-orcid":false,"given":"Zheyuan","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-5289","authenticated-orcid":false,"given":"Piotr","family":"Koniusz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,6]]},"reference":[{"key":"9_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"9_CR2","unstructured":"Banik, P., Li, L., Dong, X.: A novel dataset for keypoint detection of quadruped animals from images. arXiv preprint arXiv:2108.13958 (2021)"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Bohdal, O., et al.: Meta omnium: a benchmark for general-purpose learning-to-learn. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7693\u20137703 (2023)","DOI":"10.1109\/CVPR52729.2023.00743"},{"key":"9_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems 33, pp. 1877\u20131901 (2020)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Cao, J., Tang, H., Fang, H.S., Shen, X., Lu, C., Tai, Y.W.: Cross-domain adaptation for animal pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9498\u20139507 (2019)","DOI":"10.1109\/ICCV.2019.00959"},{"issue":"1","key":"9_CR6","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","volume":"43","author":"Z Cao","year":"2019","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172\u2013186 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimation with iterative error feedback. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4733\u20134742 (2016)","DOI":"10.1109\/CVPR.2016.512"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: HigherHRNet: scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5386\u20135395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"9_CR9","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/vicuna.lmsys.org. Accessed 14 Apr 2023"},{"key":"9_CR10","unstructured":"Derpanis, K.G.: The Harris corner detector, pp.\u00a02\u20133. York University (2004)"},{"key":"9_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., Lu, C.: RMPE: regional multi-person pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2334\u20132343 (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"9_CR13","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126\u20131135. PMLR (2017)"},{"key":"9_CR14","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1109\/TIP.2021.3131033","volume":"31","author":"Y Ge","year":"2021","unstructured":"Ge, Y., Zhang, R., Luo, P.: MetaCloth: learning unseen tasks of dense fashion landmark detection from a few samples. IEEE Trans. Image Process. 31, 1120\u20131133 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4367\u20134375 (2018)","DOI":"10.1109\/CVPR.2018.00459"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Honari, S., Molchanov, P., Tyree, S., Vincent, P., Pal, C., Kautz, J.: Improving landmark localization with semi-supervised learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1546\u20131555 (2018)","DOI":"10.1109\/CVPR.2018.00167"},{"key":"9_CR19","unstructured":"Jiao, B., et al.: Toward re-identifying any animal. In: Advances in Neural Information Processing Systems 36 (2024)"},{"key":"9_CR20","unstructured":"Koch, G., Zemel, R., Salakhutdinov, R., et\u00a0al.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, Lille, vol.\u00a02 (2015)"},{"issue":"7553","key":"9_CR21","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"9_CR22","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":"9_CR23","doi-asserted-by":"crossref","unstructured":"Li, S., Gunel, S., Ostrek, M., Ramdya, P., Fua, P., Rhodin, H.: Deformation-aware unpaired image translation for pose estimation on laboratory animals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13158\u201313168 (2020)","DOI":"10.1109\/CVPR42600.2020.01317"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"9_CR25","first-page":"91","volume":"2","author":"G Lowe","year":"2004","unstructured":"Lowe, G.: SIFT-the scale invariant feature transform. Int. J. 2, 91\u2013110 (2004)","journal-title":"Int. J."},{"key":"9_CR26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neucom.2020.05.020","volume":"409","author":"C Lu","year":"2020","unstructured":"Lu, C., Gu, C., Wu, K., Xia, S., Wang, H., Guan, X.: Deep transfer neural network using hybrid representations of domain discrepancy. Neurocomputing 409, 60\u201373 (2020)","journal-title":"Neurocomputing"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Lu, C., Koniusz, P.: Few-shot keypoint detection with uncertainty learning for unseen species. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19416\u201319426 (2022)","DOI":"10.1109\/CVPR52688.2022.01881"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Lu, C., Koniusz, P.: Detect any keypoints: an efficient light-weight few-shot keypoint detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 3882\u20133890 (2024)","DOI":"10.1609\/aaai.v38i4.28180"},{"key":"9_CR29","unstructured":"Lu, C., Zhu, H., Koniusz, P.: From saliency to DINO: saliency-guided vision transformer for few-shot keypoint detection. arXiv preprint arXiv:2304.03140 (2023)"},{"issue":"9","key":"9_CR30","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1038\/s41593-018-0209-y","volume":"21","author":"A Mathis","year":"2018","unstructured":"Mathis, A., et al.: DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nat. Neurosci. 21(9), 1281\u20131289 (2018)","journal-title":"Nat. Neurosci."},{"key":"9_CR31","unstructured":"Moskvyak, O., Maire, F., Dayoub, F., Baktashmotlagh, M.: Semi-supervised keypoint localization. arXiv preprint arXiv:2101.07988 (2021)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Mukhoti, J., et al.: Open vocabulary semantic segmentation with patch aligned contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19413\u201319423 (2023)","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"9_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VIII. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"issue":"1","key":"9_CR34","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1038\/s41592-018-0234-5","volume":"16","author":"TD Pereira","year":"2019","unstructured":"Pereira, T.D., et al.: Fast animal pose estimation using deep neural networks. Nat. Methods 16(1), 117\u2013125 (2019)","journal-title":"Nat. Methods"},{"key":"9_CR35","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":"9_CR36","unstructured":"Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175 (2017)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199\u20131208 (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Tang, L., Wertheimer, D., Hariharan, B.: Revisiting pose-normalization for fine-grained few-shot recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14352\u201314361 (2020)","DOI":"10.1109\/CVPR42600.2020.01436"},{"key":"9_CR40","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems 27 (2014)"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., et al.: Building a bird recognition app and large scale dataset with citizen scientists: the fine print in fine-grained dataset collection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 595\u2013604 (2015)","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"9_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"9_CR44","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems 29, pp. 3630\u20133638 (2016)"},{"key":"9_CR45","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset. Technical Report CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"9_CR46","unstructured":"Wang, C., et al.: Pseudo-labeled auto-curriculum learning for semi-supervised keypoint localization. arXiv preprint arXiv:2201.08613 (2022)"},{"key":"9_CR47","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/TIP.2019.2925285","volume":"29","author":"L Wang","year":"2019","unstructured":"Wang, L., Huynh, D.Q., Koniusz, P.: A comparative review of recent kinect-based action recognition algorithms. IEEE Trans. Image Process. 29, 15\u201328 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"9_CR48","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems 35, pp. 24824\u201324837 (2022)"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Wu, Z., Su, L., Huang, Q.: Stacked cross refinement network for edge-aware salient object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7264\u20137273 (2019)","DOI":"10.1109\/ICCV.2019.00736"},{"key":"9_CR50","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/978-3-031-20068-7_23","volume-title":"European Conference on Computer Vision 2022","author":"L Xu","year":"2022","unstructured":"Xu, L., et al.: Pose for everything: towards category-agnostic pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 398\u2013416. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_23"},{"key":"9_CR51","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose+: vision transformer foundation model for generic body pose estimation. arXiv preprint arXiv:2212.04246 (2022)"},{"key":"9_CR52","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: TransPose: keypoint localization via transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11802\u201311812 (2021)","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"9_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-030-87196-3_17","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Q Yao","year":"2021","unstructured":"Yao, Q., Quan, Q., Xiao, L., Kevin Zhou, S.: One-shot medical landmark detection. In: de Bruijne, M., et al. (eds.) MICCAI 2021, Part II. LNCS, vol. 12902, pp. 177\u2013188. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_17"},{"key":"9_CR54","unstructured":"Zhang, H., et al.: Language-driven open-vocabulary keypoint detection for animal body and face. arXiv preprint arXiv:2310.05056 (2023)"},{"key":"9_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10590-1_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Zhang","year":"2014","unstructured":"Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_54"},{"key":"9_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wang, W., Chen, Z., Xu, Y., Zhang, J., Tao, D.: CLAMP: prompt-based contrastive learning for connecting language and animal pose. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23272\u201323281 (2023)","DOI":"10.1109\/CVPR52729.2023.02229"},{"issue":"11","key":"9_CR57","doi-asserted-by":"publisher","first-page":"2908","DOI":"10.1007\/s11263-023-01837-3","volume":"131","author":"S Zhao","year":"2023","unstructured":"Zhao, S., Gong, M., Zhao, H., Zhang, J., Tao, D.: Deep corner. Int. J. Comput. Vis. 131(11), 2908\u20132932 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"9_CR58","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena (2023)"},{"key":"9_CR59","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72655-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T11:29:11Z","timestamp":1733398151000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72655-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"ISBN":["9783031726545","9783031726552"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72655-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,6]]},"assertion":[{"value":"6 December 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}