{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:57:19Z","timestamp":1781161039501,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819200672","type":"print"},{"value":"9789819200689","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\/978-981-92-0068-9_34","type":"book-chapter","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:09:09Z","timestamp":1781158149000},"page":"507-518","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CLIP-Based Dual-Encoder Approach for\u00a0Sketch-to-Image Retrieval"],"prefix":"10.1007","author":[{"given":"Ky Quoc Binh","family":"Le","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thi-Ngoc-Hanh","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"34_CR1","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.cviu.2017.06.007","volume":"164","author":"T Bui","year":"2017","unstructured":"Bui, T., Ribeiro, L., Ponti, M., Collomosse, J.: Compact descriptors for sketch-based image retrieval using a triplet loss convolutional neural network. Comput. Vis. Image Underst. 164, 27\u201337 (2017). https:\/\/doi.org\/10.1016\/j.cviu.2017.06.007","journal-title":"Comput. Vis. Image Underst."},{"key":"34_CR2","doi-asserted-by":"publisher","unstructured":"Caron, M., Touvron, H., Misra, I., et\u00a0al.: Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9650\u20139660 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00953","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"34_CR3","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":"34_CR4","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"34_CR5","doi-asserted-by":"publisher","unstructured":"Dutta, A., Akata, Z.: Semantically tied paired cycle consistency for any-shot sketch-based image retrieval. Int. J. Comput. Vision , 2684\u20132703 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01350-x","DOI":"10.1007\/s11263-020-01350-x"},{"issue":"4","key":"34_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2185520.2185527","volume":"31","author":"M Eitz","year":"2012","unstructured":"Eitz, M., Hays, J., Alexa, M.: How do humans sketch objects? ACM Trans. Graph. 31(4), 1\u201310 (2012). https:\/\/doi.org\/10.1145\/2185520.2185527","journal-title":"ACM Trans. Graph."},{"key":"34_CR7","doi-asserted-by":"publisher","unstructured":"Feng, Z., Huang, S., Lai, J.: Attention-guided siamese network for clothes-changing person re-identification. In: Image and Graphics (Lecture Notes in Computer Science, vol. 12889), pp. 314\u2013325. Springer (2021). https:\/\/doi.org\/10.1007\/978-3-030-87358-5_25","DOI":"10.1007\/978-3-030-87358-5_25"},{"key":"34_CR8","unstructured":"Frome, A., Corrado, G.S., Shlens, J., et\u00a0al.: Devise: a deep visual-semantic embedding model. In: NeurIPS (2013)"},{"key":"34_CR9","doi-asserted-by":"publisher","unstructured":"Hou, Q., Zhang, L., Cheng, M.M., Feng, J.: Strip pooling: rethinking spatial pooling for scene parsing. In: CVPR, pp. 4003\u20134012 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00407","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"34_CR10","doi-asserted-by":"publisher","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 5967\u20135976 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"key":"34_CR11","unstructured":"Jetley, S., Lord, N.A., Lee, N., Torr, P.: Learn to pay attention. In: ICLR (2018)"},{"key":"34_CR12","unstructured":"Jia, C., Yang, Y., Xia, Y., et\u00a0al.: Scaling up visual and vision-language representation learning with contrastive learning. In: ICML (2021)"},{"key":"34_CR13","doi-asserted-by":"publisher","first-page":"5314","DOI":"10.1109\/TIP.2020.2971443","volume":"29","author":"W Jiang","year":"2020","unstructured":"Jiang, W., Wang, X., Jiang, S., et al.: Deep sketch hashing with center similarity. IEEE Trans. Image Process. 29, 5314\u20135327 (2020). https:\/\/doi.org\/10.1109\/TIP.2020.2971443","journal-title":"IEEE Trans. Image Process."},{"key":"34_CR14","doi-asserted-by":"publisher","unstructured":"Li, J., et\u00a0al.: Online sketching hashing. In: AAAI, pp. 7105\u20137112 (2018). https:\/\/doi.org\/10.1609\/aaai.v32i1.12090","DOI":"10.1609\/aaai.v32i1.12090"},{"key":"34_CR15","doi-asserted-by":"publisher","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 (CVPR), pp. 2298\u20132307 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.247","DOI":"10.1109\/CVPR.2017.247"},{"key":"34_CR16","unstructured":"Liu, Z., et\u00a0al.: A survey on visual prompt learning. arXiv preprint arXiv:2307XXXXXX (2023)"},{"key":"34_CR17","doi-asserted-by":"publisher","unstructured":"Qi, Y., Song, Y.Z., Zhang, H., et\u00a0al.: Sketch-based image retrieval via CNN and fusion. In: ACM Multimedia, pp. 69\u201373 (2016). https:\/\/doi.org\/10.1145\/2964284.2967308","DOI":"10.1145\/2964284.2967308"},{"key":"34_CR18","doi-asserted-by":"publisher","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: CNN image retrieval learns fine-grained details. In: CVPR, pp. 1955\u20131963 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.215","DOI":"10.1109\/CVPR.2016.215"},{"key":"34_CR19","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"34_CR20","doi-asserted-by":"publisher","unstructured":"Ramy, A., Barakat, N., Barakat, N.H.: Sketch to image using generative adversarial networks (GAN) (2022). https:\/\/doi.org\/10.13140\/RG.2.2.16797.38889","DOI":"10.13140\/RG.2.2.16797.38889"},{"key":"34_CR21","doi-asserted-by":"publisher","unstructured":"Sain, A., Bhunia, A.K., Chowdhury, P.N., Koley, S., Xiang, T., Song, Y.Z.: 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 (CVPR), pp. 2765\u20132775 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00271","DOI":"10.1109\/CVPR52729.2023.00271"},{"issue":"4","key":"34_CR22","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. 35(4), 1\u201312 (2016). https:\/\/doi.org\/10.1145\/2897824.2925954","journal-title":"ACM Trans. Graph."},{"key":"34_CR23","doi-asserted-by":"publisher","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815\u2013823 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"34_CR24","doi-asserted-by":"publisher","unstructured":"Seddati, O., Dupont, S., Mahmoudi, S., Dutoit, T.: Transformers and CNNs both beat humans on SBIR. arXiv preprint arXiv:2209.06629 (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.06629","DOI":"10.48550\/arXiv.2209.06629"},{"key":"34_CR25","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured latent representations with deep generative models. In: NeurIPS, pp. 3040\u20133048 (2015)"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Douze, M., et\u00a0al.: Training data-efficient image transformers. In: ICML (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"34_CR27","doi-asserted-by":"publisher","unstructured":"Wang, J., Zhou, F., Wen, S., Liu, X.: Learning fine-grained image similarity with deep ranking. In: CVPR, pp. 1386\u20131393 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.180","DOI":"10.1109\/CVPR.2014.180"},{"key":"34_CR28","doi-asserted-by":"publisher","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: ECCV, pp. 3\u201319 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"34_CR29","doi-asserted-by":"publisher","unstructured":"Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning \u2014 the good, the bad and the ugly. In: CVPR, pp. 3077\u20133086 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.330","DOI":"10.1109\/CVPR.2017.330"},{"key":"34_CR30","unstructured":"Xu, P., Hospedales, T.M.: Sketch-a-class: cross-modality feature learning. In: IJCAI, pp. 3163\u20133169 (2017)"},{"key":"34_CR31","doi-asserted-by":"publisher","unstructured":"Yang, Y., Hospedales, T.M.: A unified perspective on zero-shot image classification. In: CVPR (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7299154","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"34_CR32","doi-asserted-by":"publisher","unstructured":"Yu, Q., Yang, Y., Song, Y.Z., Xiang, T., Hospedales, T.: Sketch-a-net that beats humans. arXiv preprint arXiv:1501.07873 (2015). https:\/\/doi.org\/10.48550\/arXiv.1501.07873","DOI":"10.48550\/arXiv.1501.07873"},{"key":"34_CR33","doi-asserted-by":"publisher","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16816\u201316825 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01637","DOI":"10.1109\/CVPR52688.2022.01637"},{"key":"34_CR34","doi-asserted-by":"publisher","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV, pp. 2223\u20132232 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.244","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Communications in Computer and Information Science","Recent Challenges in Intelligent information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-0068-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:09:13Z","timestamp":1781158153000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-0068-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819200672","9789819200689"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-0068-9_34","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaohsiung","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 April 2026","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":"aciids2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}