{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T19:23:13Z","timestamp":1793128993691,"version":"4.5.0"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729454","type":"print"},{"value":"9783031729461","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"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\/978-3-031-72946-1_1","type":"book-chapter","created":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T19:02:08Z","timestamp":1727809328000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Open-Set Recognition in\u00a0the\u00a0Age of\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Dimity","family":"Miller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niko","family":"S\u00fcnderhauf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Kenna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keita","family":"Mason","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,2]]},"reference":[{"key":"1_CR1","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 23716\u201323736 (2022)"},{"key":"1_CR2","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Man\u00e9, D.: Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Bao, W., Yu, Q., Kong, Y.: Evidential deep learning for open set action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13349\u201313358 (2021)","DOI":"10.1109\/ICCV48922.2021.01310"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Bendale, A., Boult, T.E.: Towards open set deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1563\u20131572 (2016)","DOI":"10.1109\/CVPR.2016.173"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1007\/978-3-030-58580-8_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Bolya","year":"2020","unstructured":"Bolya, D., Foley, S., Hays, J., Hoffman, J.: TIDE: a general toolbox for identifying object detection errors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part III. LNCS, vol. 12348, pp. 558\u2013573. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_33"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Cen, J., Yun, P., Cai, J., Wang, M.Y., Liu, M.: Deep metric learning for open world semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15333\u201315342 (2021)","DOI":"10.1109\/ICCV48922.2021.01505"},{"issue":"11","key":"1_CR7","first-page":"8065","volume":"44","author":"G Chen","year":"2021","unstructured":"Chen, G., Peng, P., Wang, X., Tian, Y.: Adversarial reciprocal points learning for open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 8065\u20138081 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Cho, E., Kim, J., Kim, H.J.: Distribution-aware prompt tuning for vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22004\u201322013 (2023)","DOI":"10.1109\/ICCV51070.2023.02011"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Dhamija, A., Gunther, M., Ventura, J., Boult, T.: The overlooked elephant of object detection: open set. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 1021\u20131030 (2020)","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G.: Learning to prompt for open-vocabulary object detection with vision-language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14084\u201314093 (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"1_CR12","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/978-3-031-20077-9_41","volume-title":"European Conference on Computer Vision 2022","author":"C Feng","year":"2022","unstructured":"Feng, C., et al.: PromptDet: towards open-vocabulary detection using uncurated images. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 701\u2013717. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_41"},{"issue":"10","key":"1_CR13","doi-asserted-by":"publisher","first-page":"3614","DOI":"10.1109\/TPAMI.2020.2981604","volume":"43","author":"C Geng","year":"2020","unstructured":"Geng, C., Huang, S., Chen, S.: Recent advances in open set recognition: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3614\u20133631 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind: one embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15180\u201315190 (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"1_CR15","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: International Conference on Learning Representations (2022)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Han, J., Ren, Y., Ding, J., Pan, X., Yan, K., Xia, G.S.: Expanding low-density latent regions for open-set object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9591\u20139600 (2022)","DOI":"10.1109\/CVPR52688.2022.00937"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Hwang, J., Oh, S.W., Lee, J.Y., Han, B.: Exemplar-based open-set panoptic segmentation network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1175\u20131184 (2021)","DOI":"10.1109\/CVPR46437.2021.00123"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: MAP: multimodal uncertainty-aware vision-language pre-training model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23262\u201323271 (2023)","DOI":"10.1109\/CVPR52729.2023.02228"},{"key":"1_CR19","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 4904\u20134916. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/jia21b.html"},{"key":"1_CR20","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A.: F-VLM: open-vocabulary object detection upon frozen vision and language models. In: International Conference on Learning Representations (2023)"},{"key":"1_CR21","unstructured":"Li, H., et al.: Learning domain-aware detection head with prompt tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"1_CR22","unstructured":"Lin, C., et al.: Learning object-language alignments for open-vocabulary object detection. In: International Conference on Learning Representations (2023)"},{"key":"1_CR23","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, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"1_CR24","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-031-20056-4_9","volume-title":"European Conference on Computer Vision 2022","author":"YC Liu","year":"2022","unstructured":"Liu, Y.C., et al.: Open-set semi-supervised object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13690, pp. 143\u2013159. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_9"},{"issue":"4","key":"1_CR25","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.1109\/LRA.2024.3366013","volume":"9","author":"A Maalouf","year":"2024","unstructured":"Maalouf, A., et al.: Follow anything: open-set detection, tracking, and following in real-time. IEEE Robot. Autom. Lett. 9(4), 3283\u20133290 (2024)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Miller, D., Nicholson, L., Dayoub, F., S\u00fcnderhauf, N.: Dropout sampling for robust object detection in open-set conditions. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 3243\u20133249. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460700"},{"issue":"1","key":"1_CR27","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1109\/LRA.2021.3123374","volume":"7","author":"D Miller","year":"2022","unstructured":"Miller, D., S\u00fcnderhauf, N., Milford, M., Dayoub, F.: Uncertainty for identifying open-set errors in visual object detection. IEEE Robot. Autom. Lett. 7(1), 215\u2013222 (2022). https:\/\/doi.org\/10.1109\/LRA.2021.3123374","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Oza, P., Patel, V.M.: C2AE: class conditioned auto-encoder for open-set recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2307\u20132316 (2019)","DOI":"10.1109\/CVPR.2019.00241"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Panareda\u00a0Busto, P., Gall, J.: Open set domain adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 754\u2013763 (2017)","DOI":"10.1109\/ICCV.2017.88"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Perera, P., et al.: Generative-discriminative feature representations for open-set recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11814\u201311823 (2020)","DOI":"10.1109\/CVPR42600.2020.01183"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Pham, C., Vu, T., Nguyen, K.: LP-OVOD: open-vocabulary object detection by linear probing. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 779\u2013788 (2024)","DOI":"10.1109\/WACV57701.2024.00083"},{"key":"1_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01249-6_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Pham","year":"2018","unstructured":"Pham, T., Vijay Kumar, B.G., Do, T.-T., Carneiro, G., Reid, I.: Bayesian semantic instance segmentation in open set world. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 3\u201318. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_1"},{"key":"1_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"1_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Saito, K., Yamamoto, S., Ushiku, Y., Harada, T.: Open set domain adaptation by backpropagation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 153\u2013168 (2018)","DOI":"10.1007\/978-3-030-01228-1_10"},{"issue":"3","key":"1_CR36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432","volume":"10","author":"T Saito","year":"2015","unstructured":"Saito, T., Rehmsmeier, M.: The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE 10(3), e0118432 (2015)","journal-title":"PLoS ONE"},{"issue":"7","key":"1_CR37","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1109\/TPAMI.2012.256","volume":"35","author":"WJ Scheirer","year":"2013","unstructured":"Scheirer, W.J., de Rezende Rocha, A., Sapkota, A., Boult, T.E.: Toward open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1757\u20131772 (2013). https:\/\/doi.org\/10.1109\/TPAMI.2012.256","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4\u20135","key":"1_CR38","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1177\/0278364918770733","volume":"37","author":"N S\u00fcnderhauf","year":"2018","unstructured":"S\u00fcnderhauf, N., et al.: The limits and potentials of deep learning for robotics. Int. J. Robot. Res. 37(4\u20135), 405\u2013420 (2018)","journal-title":"Int. J. Robot. Res."},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Upadhyay, U., Karthik, S., Mancini, M., Akata, Z.: ProbVLM: probabilistic adapter for frozen vison-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1899\u20131910 (2023)","DOI":"10.1109\/ICCV51070.2023.00182"},{"key":"1_CR40","unstructured":"Vaze, S., Han, K., Vedaldi, A., Zisserman, A.: Open-set recognition: a good closed-set classifier is all you need? In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Open-vocabulary object detection with an open corpus. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6759\u20136769 (2023)","DOI":"10.1109\/ICCV51070.2023.00622"},{"issue":"7","key":"1_CR42","doi-asserted-by":"publisher","first-page":"5092","DOI":"10.1109\/TPAMI.2024.3361862","volume":"46","author":"J Wu","year":"2024","unstructured":"Wu, J., et al.: Towards open vocabulary learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(7), 5092\u20135113 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Wu, S., Zhang, W., Jin, S., Liu, W., Loy, C.C.: Aligning bag of regions for open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15254\u201315264 (2023)","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Wu, X., Zhu, F., Zhao, R., Li, H.: CORA: adapting CLIP for open-vocabulary detection with region prompting and anchor pre-matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7031\u20137040 (2023)","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Yoshihashi, R., Shao, W., Kawakami, R., You, S., Iida, M., Naemura, T.: Classification-reconstruction learning for open-set recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4016\u20134025 (2019)","DOI":"10.1109\/CVPR.2019.00414"},{"key":"1_CR46","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. Trans. Mach. Learn. Res. (2022). https:\/\/openreview.net\/forum?id=Ee277P3AYC"},{"key":"1_CR47","unstructured":"Yuan, L., et al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"1_CR48","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-031-20077-9_7","volume-title":"European Conference on Computer Vision 2022","author":"Y Zang","year":"2022","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary DETR with conditional matching. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 106\u2013122. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_7"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Zara, G., Roy, S., Rota, P., Ricci, E.: AutoLabel: CLIP-based framework for open-set video domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11504\u201311513 (2023)","DOI":"10.1109\/CVPR52729.2023.01107"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: LiT: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: Sigmoid loss for language image pre-training. In: International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"1_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-030-58580-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Li, A., Guo, J., Guo, Y.: Hybrid models for open set recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part III. LNCS, vol. 12348, pp. 102\u2013117. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_7"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: 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"},{"key":"1_CR55","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-031-20077-9_21","volume-title":"European Conference on Computer Vision 2022","author":"X Zhou","year":"2022","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 350\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21"},{"issue":"3","key":"1_CR56","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1109\/LRA.2023.3242169","volume":"8","author":"Z Zhou","year":"2023","unstructured":"Zhou, Z., Yang, Y., Wang, Y., Xiong, R.: Open-set object detection using classification-free object proposal and instance-level contrastive learning. IEEE Robot. Autom. Lett. 8(3), 1691\u20131698 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, B., Niu, Y., Han, Y., Wu, Y., Zhang, H.: Prompt-aligned gradient for prompt tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15659\u201315669 (2023)","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"1_CR58","unstructured":"Zhu, B., et al.: LanguageBind: extending video-language pretraining to n-modality by language-based semantic alignment. In: International Conference on Learning Representations (2023)"}],"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\/978-3-031-72946-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T19:02:37Z","timestamp":1727809357000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72946-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"ISBN":["9783031729454","9783031729461"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72946-1_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,2]]},"assertion":[{"value":"2 October 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"}}]}}