{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:17:05Z","timestamp":1775578625024,"version":"3.50.1"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726903","type":"print"},{"value":"9783031726910","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-72691-0_1","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:02:28Z","timestamp":1730570548000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Elevating All Zero-Shot Sketch-Based Image Retrieval Through Multimodal Prompt Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7615-2575","authenticated-orcid":false,"given":"Mainak","family":"Singha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1063-8978","authenticated-orcid":false,"given":"Ankit","family":"Jha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7294-3739","authenticated-orcid":false,"given":"Divyam","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3812-8517","authenticated-orcid":false,"given":"Pranav","family":"Singla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8371-8138","authenticated-orcid":false,"given":"Biplab","family":"Banerjee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"1_CR1","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/978-3-031-19836-6_10","volume-title":"ECCV 2022","author":"AK Bhunia","year":"2022","unstructured":"Bhunia, A.K., et al.: Adaptive fine-grained sketch-based image retrieval. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 163\u2013181. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_10"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bose, S., Jha, A., Fini, E., Singha, M., Ricci, E., Banerjee, B.: STYLIP: multi-scale style-conditioned prompt learning for clip-based domain generalization. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5542\u20135552 (2024)","DOI":"10.1109\/WACV57701.2024.00545"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: LASP: text-to-text optimization for language-aware soft prompting of vision & language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23232\u201323241 (2023)","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Chaudhuri, A., Bhunia, A.K., Song, Y.Z., Dutta, A.: Data-free sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12084\u201312093 (2023)","DOI":"10.1109\/CVPR52729.2023.01163"},{"key":"1_CR5","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.neucom.2022.09.104","volume":"514","author":"U Chaudhuri","year":"2022","unstructured":"Chaudhuri, U., Chavan, R., Banerjee, B., Dutta, A., Akata, Z.: BDA-SketRet: bi-level domain adaptation for zero-shot SBIR. Neurocomputing 514, 245\u2013255 (2022)","journal-title":"Neurocomputing"},{"key":"1_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Dey, S., Riba, P., Dutta, A., Llados, J., Song, Y.Z.: Doodle to search: practical zero-shot sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2179\u20132188 (2019)","DOI":"10.1109\/CVPR.2019.00228"},{"key":"1_CR8","unstructured":"Dong, S., Zhu, M., Wang, N., Yang, H., Gao, X.: Adapt and align to improve zero-shot sketch-based image retrieval. arXiv preprint arXiv:2305.05144 (2023)"},{"key":"1_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. CoRR abs\/2010.11929 (2020). https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Dutta, A., Akata, Z.: Semantically tied paired cycle consistency for zero-shot sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5089\u20135098 (2019)","DOI":"10.1109\/CVPR.2019.00523"},{"key":"1_CR11","doi-asserted-by":"publisher","first-page":"2833","DOI":"10.1109\/TMM.2020.3017918","volume":"23","author":"T Dutta","year":"2020","unstructured":"Dutta, T., Singh, A., Biswas, S.: StyleGuide: zero-shot sketch-based image retrieval using style-guided image generation. IEEE Trans. Multimed. 23, 2833\u20132842 (2020)","journal-title":"IEEE Trans. Multimed."},{"issue":"4","key":"1_CR12","first-page":"1","volume":"31","author":"M Eitz","year":"2012","unstructured":"Eitz, M., Hays, J., Alexa, M.: How do humans sketch objects? ACM Trans. Graph. (TOG) 31(4), 1\u201310 (2012)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"11","key":"1_CR13","doi-asserted-by":"publisher","first-page":"1624","DOI":"10.1109\/TVCG.2010.266","volume":"17","author":"M Eitz","year":"2010","unstructured":"Eitz, M., Hildebrand, K., Boubekeur, T., Alexa, M.: Sketch-based image retrieval: benchmark and bag-of-features descriptors. IEEE Trans. Visual Comput. Graph. 17(11), 1624\u20131636 (2010)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Ge, C., Wang, J., Qi, Q., Sun, H., Xu, T., Liao, J.: Semi-transductive learning for generalized zero-shot sketch-based image retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 7678\u20137686 (2023)","DOI":"10.1609\/aaai.v37i6.25931"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, S., Chaudhuri, U., Banerjee, B., Kumar, S.: Zero-shot sketch based image retrieval using graph transformer. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 1685\u20131691. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956095"},{"key":"1_CR16","unstructured":"Ha, D., Eck, D.: A neural representation of sketch drawings. arXiv preprint arXiv:1704.03477 (2017)"},{"issue":"7","key":"1_CR17","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1016\/j.cviu.2013.02.005","volume":"117","author":"R Hu","year":"2013","unstructured":"Hu, R., Collomosse, J.: A performance evaluation of gradient field hog descriptor for sketch based image retrieval. Comput. Vis. Image Underst. 117(7), 790\u2013806 (2013)","journal-title":"Comput. Vis. Image Underst."},{"key":"1_CR18","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Wasim, S.T., Naseer, M., Khan, S., Yang, M.H., Khan, F.S.: Self-regulating prompts: foundational model adaptation without forgetting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15190\u201315200 (2023)","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"1_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"1_CR22","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Hospedales, T., Song, Y.Z., Gong, S.: Fine-grained sketch-based image retrieval by matching deformable part models. In: Proceedings of the British Machine Vision Conference, BMVC 2014 (2014)","DOI":"10.5244\/C.28.115"},{"issue":"7","key":"1_CR24","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1007\/s00138-018-0953-8","volume":"29","author":"Y Li","year":"2018","unstructured":"Li, Y., Li, W.: A survey of sketch-based image retrieval. Mach. Vis. Appl. 29(7), 1083\u20131100 (2018)","journal-title":"Mach. Vis. Appl."},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Lin, F., Li, M., Li, D., Hospedales, T., Song, Y.Z., Qi, Y.: Zero-shot everything sketch-based image retrieval, and in explainable style. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23349\u201323358 (2023)","DOI":"10.1109\/CVPR52729.2023.02236"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Liu, L., Shen, F., Shen, Y., Liu, X., Shao, L.: Deep sketch hashing: fast free-hand sketch-based image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2862\u20132871 (2017)","DOI":"10.1109\/CVPR.2017.247"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Q., Xie, L., Wang, H., Yuille, A.L.: Semantic-aware knowledge preservation for zero-shot sketch-based image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3662\u20133671 (2019)","DOI":"10.1109\/ICCV.2019.00376"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Lyou, E., Lee, D., Kim, J., Lee, J.: Modality-aware representation learning for zero-shot sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5646\u20135655 (2024)","DOI":"10.1109\/WACV57701.2024.00555"},{"key":"1_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Pang, K., et al.: Generalising fine-grained sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 677\u2013686 (2019)","DOI":"10.1109\/CVPR.2019.00077"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Pang, K., Song, Y.Z., Xiang, T., Hospedales, T.M.: Cross-domain generative learning for fine-grained sketch-based image retrieval. In: BMVC, pp. 1\u201312 (2017)","DOI":"10.5244\/C.31.46"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Pang, K., Yang, Y., Hospedales, T.M., Xiang, T., Song, Y.Z.: Solving mixed-modal jigsaw puzzle for fine-grained sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10347\u201310355 (2020)","DOI":"10.1109\/CVPR42600.2020.01036"},{"key":"1_CR33","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":"1_CR34","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training (2018)"},{"key":"1_CR35","unstructured":"Ribeiro, L.S.F., Ponti, M.A.: Sketch-an-anchor: sub-epoch fast model adaptation for zero-shot sketch-based image retrieval. arXiv preprint arXiv:2303.16769 (2023)"},{"key":"1_CR36","unstructured":"Roy, S., Etemad, A.: Consistency-guided prompt learning for vision-language models. arXiv preprint arXiv:2306.01195 (2023)"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Sain, A., et al.: Clip for all things zero-shot sketch-based image retrieval, fine-grained or not. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2765\u20132775 (2023)","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Sain, A., et al.: Exploiting unlabelled photos for stronger fine-grained SBIR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6873\u20136883 (2023)","DOI":"10.1109\/CVPR52729.2023.00664"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Sain, A., Bhunia, A.K., Potlapalli, V., Chowdhury, P.N., Xiang, T., Song, Y.Z.: Sketch3T: test-time training for zero-shot SBIR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7462\u20137471 (2022)","DOI":"10.1109\/CVPR52688.2022.00731"},{"key":"1_CR40","unstructured":"Sain, A., Bhunia, A.K., Yang, Y., Xiang, T., Song, Y.Z.: Cross-modal hierarchical modelling for fine-grained sketch based image retrieval. arXiv preprint arXiv:2007.15103 (2020)"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Sain, A., Bhunia, A.K., Yang, Y., Xiang, T., Song, Y.Z.: StyleMeUp: towards style-agnostic sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8504\u20138513 (2021)","DOI":"10.1109\/CVPR46437.2021.00840"},{"issue":"4","key":"1_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925954","volume":"35","author":"P Sangkloy","year":"2016","unstructured":"Sangkloy, P., Burnell, N., Ham, C., Hays, J.: The sketchy database: learning to retrieve badly drawn bunnies. ACM Trans. Graph. (TOG) 35(4), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR43","unstructured":"Shankar, S., Piratla, V., Chakrabarti, S., Chaudhuri, S., Jyothi, P., Sarawagi, S.: Generalizing across domains via cross-gradient training. arXiv preprint arXiv:1804.10745 (2018)"},{"key":"1_CR44","unstructured":"Singha, M., Jha, A., Banerjee, B.: GOPro: generate and optimize prompts in clip using self-supervised learning. arXiv preprint arXiv:2308.11605 (2023)"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Singha, M., Jha, A., Bose, S., Nair, A., Abdar, M., Banerjee, B.: Unknown prompt the only lacuna: unveiling clip\u2019s potential for open domain generalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13309\u201313319 (2024)","DOI":"10.1109\/CVPR52733.2024.01264"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Singha, M., Pal, H., Jha, A., Banerjee, B.: Ad-clip: adapting domains in prompt space using clip. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4355\u20134364 (2023)","DOI":"10.1109\/ICCVW60793.2023.00470"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Song, J., Yu, Q., Song, Y.Z., Xiang, T., Hospedales, T.M.: Deep spatial-semantic attention for fine-grained sketch-based image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5551\u20135560 (2017)","DOI":"10.1109\/ICCV.2017.592"},{"issue":"10","key":"1_CR48","doi-asserted-by":"publisher","first-page":"7177","DOI":"10.1109\/TCSVT.2022.3171972","volume":"32","author":"H Sun","year":"2022","unstructured":"Sun, H., Xu, J., Wang, J., Qi, Q., Ge, C., Liao, J.: DLI-net: dual local interaction network for fine-grained sketch-based image retrieval. IEEE Trans. Circuits Syst. Video Technol. 32(10), 7177\u20137189 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Tian, J., Xu, X., Shen, F., Yang, Y., Shen, H.T.: TVT: three-way vision transformer through multi-modal hypersphere learning for zero-shot sketch-based image retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2370\u20132378 (2022)","DOI":"10.1609\/aaai.v36i2.20136"},{"key":"1_CR50","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"12","key":"1_CR51","doi-asserted-by":"publisher","first-page":"9181","DOI":"10.1109\/TPAMI.2021.3123315","volume":"44","author":"H Wang","year":"2021","unstructured":"Wang, H., Deng, C., Liu, T., Tao, D.: Transferable coupled network for zero-shot sketch-based image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9181\u20139194 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Wang, K., Wang, Y., Xu, X., Liu, X., Ou, W., Lu, H.: Prototype-based selective knowledge distillation for zero-shot sketch based image retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 601\u2013609 (2022)","DOI":"10.1145\/3503161.3548382"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, H., Yan, J., Wu, A., Deng, C.: Domain-smoothing network for zero-shot sketch-based image retrieval. arXiv preprint arXiv:2106.11841 (2021)","DOI":"10.24963\/ijcai.2021\/158"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Yelamarthi, S.K., Reddy, S.K., Mishra, A., Mittal, A.: A zero-shot framework for sketch based image retrieval. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 300\u2013317 (2018)","DOI":"10.1007\/978-3-030-01225-0_19"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Yu, Q., Liu, F., Song, Y.Z., Xiang, T., Hospedales, T.M., Loy, C.C.: Sketch me that shoe. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 799\u2013807 (2016)","DOI":"10.1109\/CVPR.2016.93"},{"key":"1_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cheng, D., Jiang, H., Liu, J., Kou, Q.: Task-like training paradigm in clip for zero-shot sketch-based image retrieval. Multimed. Tools Appl. 1\u201318 (2023)","DOI":"10.1007\/s11042-023-17675-x"},{"key":"1_CR57","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.imavis.2019.06.010","volume":"89","author":"X Zhang","year":"2019","unstructured":"Zhang, X., Li, X., Liu, Y., Feng, F.: A survey on freehand sketch recognition and retrieval. Image Vis. Comput. 89, 67\u201387 (2019)","journal-title":"Image Vis. Comput."},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, Y., Feng, R., Zhang, T., Fan, W.: Zero-shot sketch-based image retrieval via graph convolution network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12943\u201312950 (2020)","DOI":"10.1609\/aaai.v34i07.6993"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"1_CR60","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vis. 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, R., Chen, L., Zhang, L.: Sketch-based image retrieval on a large scale database. In: Proceedings of the 20th ACM International Conference on Multimedia, pp. 973\u2013976 (2012)","DOI":"10.1145\/2393347.2396360"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, J., Xu, X., Shen, F., Lee, R.K.W., Wang, Z., Shen, H.T.: Ocean: a dual learning approach for generalized zero-shot sketch-based image retrieval. In: 2020 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2020)","DOI":"10.1109\/ICME46284.2020.9102940"}],"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\/978-3-031-72691-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:03:08Z","timestamp":1730570588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72691-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726903","9783031726910"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72691-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 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"}}]}}