{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T10:43:26Z","timestamp":1777632206065,"version":"3.51.4"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019M653564"],"award-info":[{"award-number":["2019M653564"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","award":["B10120210117-OF06"],"award-info":[{"award-number":["B10120210117-OF06"]}],"id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036007"],"award-info":[{"award-number":["62036007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376207"],"award-info":[{"award-number":["62376207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20514"],"award-info":[{"award-number":["U21A20514"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176195"],"award-info":[{"award-number":["62176195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005320","name":"Xidian University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005320","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1016\/j.patcog.2024.110452","type":"journal-article","created":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T13:42:36Z","timestamp":1711460556000},"page":"110452","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":18,"special_numbering":"C","title":["Zero-shot sketch-based image retrieval via adaptive relation-aware metric learning"],"prefix":"10.1016","volume":"152","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5392-393X","authenticated-orcid":false,"given":"Yuhao","family":"Dang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1443-0776","authenticated-orcid":false,"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[]},{"given":"Ling","family":"Shao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.patcog.2024.110452_b1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925954","article-title":"The sketchy database: learning to retrieve badly drawn bunnies","volume":"35","author":"Sangkloy","year":"2016","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.patcog.2024.110452_b2","first-page":"25739","article-title":"Deep model reassembly","volume":"35","author":"Yang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2024.110452_b3","doi-asserted-by":"crossref","unstructured":"Z. Lu, S. He, X. Zhu, L. Zhang, Y.-Z. Song, T. Xiang, Simpler is better: Few-shot semantic segmentation with classifier weight transformer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 8741\u20138750.","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"10.1016\/j.patcog.2024.110452_b4","doi-asserted-by":"crossref","first-page":"3311","DOI":"10.1109\/TIP.2023.3282070","article-title":"Prediction calibration for generalized few-shot semantic segmentation","volume":"32","author":"Lu","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"10.1016\/j.patcog.2024.110452_b5","doi-asserted-by":"crossref","first-page":"3794","DOI":"10.1109\/TCYB.2022.3164142","article-title":"A discriminative cross-aligned variational autoencoder for zero-shot learning","volume":"53","author":"Liu","year":"2023","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2024.110452_b6","doi-asserted-by":"crossref","unstructured":"Y. Liu, J. Li, X. Gao, A simple discriminative dual semantic auto-encoder for zero-shot classification, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 940\u2013941.","DOI":"10.1109\/CVPRW50498.2020.00478"},{"key":"10.1016\/j.patcog.2024.110452_b7","doi-asserted-by":"crossref","unstructured":"A. Dutta, Z. Akata, 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, pp. 5089\u20135098.","DOI":"10.1109\/CVPR.2019.00523"},{"key":"10.1016\/j.patcog.2024.110452_b8","doi-asserted-by":"crossref","unstructured":"Z. Zhang, Y. Zhang, R. Feng, T. Zhang, W. Fan, Zero-shot sketch-based image retrieval via graph convolution network, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2020, pp. 12943\u201312950.","DOI":"10.1609\/aaai.v34i07.6993"},{"key":"10.1016\/j.patcog.2024.110452_b9","doi-asserted-by":"crossref","unstructured":"K. Han, A. Vedaldi, A. Zisserman, Learning to discover novel visual categories via deep transfer clustering, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 8401\u20138409.","DOI":"10.1109\/ICCV.2019.00849"},{"issue":"11","key":"10.1016\/j.patcog.2024.110452_b10","doi-asserted-by":"crossref","first-page":"1624","DOI":"10.1109\/TVCG.2010.266","article-title":"Sketch-based image retrieval: Benchmark and bag-of-features descriptors","volume":"17","author":"Eitz","year":"2010","journal-title":"IEEE Trans. Visual. Comput. Graph."},{"key":"10.1016\/j.patcog.2024.110452_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108291","article-title":"Ae-net: Fine-grained sketch-based image retrieval via attention-enhanced network","volume":"122","author":"Chen","year":"2022","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.patcog.2024.110452_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108508","article-title":"A deformable cnn-based triplet model for fine-grained sketch-based image retrieval","volume":"125","author":"Zhang","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.110452_b13","doi-asserted-by":"crossref","unstructured":"A. Sain, A.K. Bhunia, Y. Yang, T. Xiang, Y.-Z. Song, Stylemeup: Towards style-agnostic sketch-based image retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8504\u20138513.","DOI":"10.1109\/CVPR46437.2021.00840"},{"key":"10.1016\/j.patcog.2024.110452_b14","doi-asserted-by":"crossref","unstructured":"W. Ge, Deep metric learning with hierarchical triplet loss, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 269\u2013285.","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"10.1016\/j.patcog.2024.110452_b15","unstructured":"K. Sohn, Improved deep metric learning with multi-class n-pair loss objective, Adv. Neural Inf. Process. Syst. 29."},{"key":"10.1016\/j.patcog.2024.110452_b16","doi-asserted-by":"crossref","unstructured":"P. Wu, S.C. Hoi, H. Xia, P. Zhao, D. Wang, C. Miao, Online multimodal deep similarity learning with application to image retrieval, in: Proceedings of the 21st ACM International Conference on Multimedia, 2013, pp. 153\u2013162.","DOI":"10.1145\/2502081.2502112"},{"key":"10.1016\/j.patcog.2024.110452_b17","article-title":"Zero-shot learning with attentive region embedding and enhanced semantics","author":"Liu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2024.110452_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108928","article-title":"Metric learning via perturbing hard-to-classify instances","volume":"132","author":"Guo","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.110452_b19","series-title":"European Conference on Computer Vision","first-page":"73","article-title":"Factorizing knowledge in neural networks","author":"Yang","year":"2022"},{"key":"10.1016\/j.patcog.2024.110452_b20","doi-asserted-by":"crossref","unstructured":"X. Yang, X. Wang, Diffusion model as representation learner, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 18938\u201318949.","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"10.1016\/j.patcog.2024.110452_b21","series-title":"In defense of the triplet loss for person re-identification","author":"Hermans","year":"2017"},{"key":"10.1016\/j.patcog.2024.110452_b22","doi-asserted-by":"crossref","unstructured":"F. Schroff, D. Kalenichenko, J. Philbin, Facenet: A unified embedding for face recognition and clustering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"10.1016\/j.patcog.2024.110452_b23","doi-asserted-by":"crossref","unstructured":"Y. Shen, L. Liu, F. Shen, L. Shao, Zero-shot sketch-image hashing, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3598\u20133607.","DOI":"10.1109\/CVPR.2018.00379"},{"key":"10.1016\/j.patcog.2024.110452_b24","doi-asserted-by":"crossref","unstructured":"T. Yu, Z. Lu, X. Jin, Z. Chen, X. Wang, Task residual for tuning vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 10899\u201310909.","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"10.1016\/j.patcog.2024.110452_b25","doi-asserted-by":"crossref","unstructured":"S. Dey, P. Riba, A. Dutta, J. Llados, Y.-Z. Song, Doodle to search: Practical zero-shot sketch-based image retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2179\u20132188.","DOI":"10.1109\/CVPR.2019.00228"},{"key":"10.1016\/j.patcog.2024.110452_b26","series-title":"2020 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Ocean: A dual learning approach for generalized zero-shot sketch-based image retrieval","author":"Zhu","year":"2020"},{"key":"10.1016\/j.patcog.2024.110452_b27","doi-asserted-by":"crossref","unstructured":"Q. Liu, L. Xie, H. Wang, A.L. Yuille, Semantic-aware knowledge preservation for zero-shot sketch-based image retrieval, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 3662\u20133671.","DOI":"10.1109\/ICCV.2019.00376"},{"key":"10.1016\/j.patcog.2024.110452_b28","first-page":"22479","article-title":"Variational interaction information maximization for cross-domain disentanglement","volume":"33","author":"Hwang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2024.110452_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108528","article-title":"An efficient framework for zero-shot sketch-based image retrieval","volume":"126","author":"Tursun","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.110452_b30","doi-asserted-by":"crossref","unstructured":"A. Sain, A.K. Bhunia, V. Potlapalli, P.N. Chowdhury, T. Xiang, Y.-Z. Song, Sketch3t: Test-time training for zero-shot sbir, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7462\u20137471.","DOI":"10.1109\/CVPR52688.2022.00731"},{"issue":"12","key":"10.1016\/j.patcog.2024.110452_b31","doi-asserted-by":"crossref","first-page":"9181","DOI":"10.1109\/TPAMI.2021.3123315","article-title":"Transferable coupled network for zero-shot sketch-based image retrieval","volume":"44","author":"Wang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2024.110452_b32","doi-asserted-by":"crossref","first-page":"2833","DOI":"10.1109\/TMM.2020.3017918","article-title":"Styleguide: zero-shot sketch-based image retrieval using style-guided image generation","volume":"23","author":"Dutta","year":"2020","journal-title":"IEEE Trans. Multimed."},{"issue":"4","key":"10.1016\/j.patcog.2024.110452_b33","first-page":"1","article-title":"How do humans sketch objects?","volume":"31","author":"Eitz","year":"2012","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"10.1016\/j.patcog.2024.110452_b34","doi-asserted-by":"crossref","unstructured":"L. Liu, F. Shen, Y. Shen, X. Liu, L. Shao, Deep sketch hashing: Fast free-hand sketch-based image retrieval, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2862\u20132871.","DOI":"10.1109\/CVPR.2017.247"},{"key":"10.1016\/j.patcog.2024.110452_b35","doi-asserted-by":"crossref","unstructured":"S.K. Yelamarthi, S.K. Reddy, A. Mishra, A. Mittal, A zero-shot framework for sketch based image retrieval, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 300\u2013317.","DOI":"10.1007\/978-3-030-01225-0_19"},{"key":"10.1016\/j.patcog.2024.110452_b36","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"421","article-title":"Concurrent spatial and channel \u2018queeze & excitation\u2019 fully convolutional networks","author":"Roy","year":"2018"},{"key":"10.1016\/j.patcog.2024.110452_b37","doi-asserted-by":"crossref","unstructured":"E. Kodirov, T. Xiang, S. Gong, Semantic autoencoder for zero-shot learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 3174\u20133183.","DOI":"10.1109\/CVPR.2017.473"},{"key":"10.1016\/j.patcog.2024.110452_b38","series-title":"Domain-smoothing network for zero-shot sketch-based image retrieval","author":"Wang","year":"2021"},{"key":"10.1016\/j.patcog.2024.110452_b39","series-title":"Progressive domain-independent feature decomposition network for zero-shot sketch-based image retrieval","author":"Xu","year":"2020"},{"key":"10.1016\/j.patcog.2024.110452_b40","doi-asserted-by":"crossref","first-page":"8892","DOI":"10.1109\/TIP.2020.3020383","article-title":"Progressive cross-modal semantic network for zero-shot sketch-based image retrieval","volume":"29","author":"Deng","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2024.110452_b41","doi-asserted-by":"crossref","unstructured":"J. Tian, X. Xu, Z. Wang, F. Shen, X. Liu, Relationship-preserving knowledge distillation for zero-shot sketch based image retrieval, in: Proceedings of the 29th ACM International Conference on Multimedia, 2021, pp. 5473\u20135481.","DOI":"10.1145\/3474085.3475676"},{"key":"10.1016\/j.patcog.2024.110452_b42","doi-asserted-by":"crossref","unstructured":"W. Wang, Y. Shi, S. Chen, Q. Peng, F. Zheng, X. You, Norm-guided adaptive visual embedding for zero-shot sketch-based image retrieval, in: IJCAI, 2021, 1106\u20131112.","DOI":"10.24963\/ijcai.2021\/153"},{"issue":"11","key":"10.1016\/j.patcog.2024.110452_b43","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320324002036?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320324002036?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:52:35Z","timestamp":1777434755000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320324002036"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":43,"alternative-id":["S0031320324002036"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2024.110452","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2024,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Zero-shot sketch-based image retrieval via adaptive relation-aware metric learning","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2024.110452","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"110452"}}