{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:16:28Z","timestamp":1783527388159,"version":"3.55.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031723469","type":"print"},{"value":"9783031723476","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72347-6_4","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:02:55Z","timestamp":1726491775000},"page":"52-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Cross-Modal Attention Alignment Network with\u00a0Auxiliary Text Description for\u00a0Zero-Shot Sketch-Based Image Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4335-5290","authenticated-orcid":false,"given":"Hanwen","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2159-8203","authenticated-orcid":false,"given":"Ge","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1735-1788","authenticated-orcid":false,"given":"Kai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4962-4496","authenticated-orcid":false,"given":"Jiyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8936-4270","authenticated-orcid":false,"given":"Ming","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Domain-smoothing network for zero-shot sketch-based image retrieval. arXiv preprint arXiv:2106.11841 (2021)","DOI":"10.24963\/ijcai.2021\/158"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Tursun, O., et al.: An efficient framework for zero-shot sketch-based image retrieval. Pattern Recogn. 126, 108528 (2022)","DOI":"10.1016\/j.patcog.2022.108528"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Tian, J., et al.: 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. 36. no. 2 (2022)","DOI":"10.1609\/aaai.v36i2.20136"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Sain, A., et al.: Sketch3T: test-time training for zero-shot SBIR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00731"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Liu, Q., et al.: Semantic-aware knowledge preservation for zero-shot sketch-based image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00376"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Lin, F., et al.: Zero-shot everything sketch-based image retrieval, and in explainable style. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02236"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, S., et al.: Zero-shot sketch based image retrieval using graph transformer. In: 26th International Conference on Pattern Recognition (ICPR). IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956095"},{"key":"4_CR8","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 (2019)","DOI":"10.1109\/CVPR.2019.00523"},{"key":"4_CR9","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. Multimedia 23, 2833\u20132842 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Dey, S., et al.: Doodle to search: practical zero-shot sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00228"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Deng, C., et al.: Progressive cross-modal semantic network for zero-shot sketch-based image retrieval. IEEE Trans. Image Process. 29, 8892\u20138902 (2020)","DOI":"10.1109\/TIP.2020.3020383"},{"key":"4_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/978-3-030-01225-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"SK Yelamarthi","year":"2018","unstructured":"Yelamarthi, S.K., Reddy, S.K., Mishra, A., Mittal, A.: A zero-shot framework for sketch based image retrieval. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 316\u2013333. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_19"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Liu, L., et al.: Deep sketch hashing: fast free-hand sketch-based image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.247"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., et al.: I2MVFormer: large language model generated multi-view document supervision for zero-shot image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01456"},{"key":"4_CR15","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, 33, 1877\u20131901 (2020)"},{"key":"4_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"4_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Chen, C.-F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"4_CR19","unstructured":"Doersch, C., Gupta, A., Zisserman, A.: CrossTransformers: spatially-aware few-shot transfer. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21981\u201321993 (2020)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Mao, C., et al.: Doubly right object recognition: a why prompt for visual rationales. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00267"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Prompt, generate, then cache: cascade of foundation models makes strong few-shot learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"4_CR22","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR (2021)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Shen, Y., et al.: Zero-shot sketch-image hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00379"},{"key":"4_CR24","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 (2019)","DOI":"10.1109\/CVPR.2019.00077"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Sangkloy, P., et al.: The sketchy database: learning to retrieve badly drawn bunnies. ACM Trans. Graph. (TOG) 35(4), 1\u201312 (2016)","DOI":"10.1145\/2897824.2925954"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Eitz, M., et al.: An evaluation of descriptors for large-scale image retrieval from sketched feature lines. Comput. Graph. 34(5), 482\u2013498 (2010)","DOI":"10.1016\/j.cag.2010.07.002"},{"key":"4_CR28","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. arXiv preprint arXiv:2210.07183 (2022)"},{"key":"4_CR29","unstructured":"Yang, Y., et al.: CoVLR: coordinating cross-modal consistency and intra-modal structure for vision-language retrieval. arXiv e-prints (2023). arXiv-2304"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhang, C., Xu, Y.C., Yu, D., Zhan, D.C., Yang, J.: Rethinking label-wise cross-modal retrieval from a semantic sharing perspective. In: IJCAI, pp. 3300\u20133306 (2021)","DOI":"10.24963\/ijcai.2021\/454"},{"key":"4_CR31","unstructured":"Yang, Y., et al.: Learning adaptive embedding considering incremental class. IEEE Trans. Knowl. Data Eng. 35(3), 2736\u20132749 (2021)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72347-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:15:17Z","timestamp":1726492517000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72347-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723469","9783031723476"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72347-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}