{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:04Z","timestamp":1778048524064,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001537","name":"University of Auckland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00044","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"371-381","source":"Crossref","is-referenced-by-count":0,"title":["Overcoming Fine-Grained Visual Challenges in Animal Re-Identification via Semantic Feature Alignment"],"prefix":"10.1109","author":[{"given":"Yihao","family":"Wu","sequence":"first","affiliation":[{"name":"The University of Auckland,School of Computer Science,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhao","sequence":"additional","affiliation":[{"name":"The University of Auckland,School of Computer Science,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhuo","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Auckland,School of Computer Science,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Alajas","sequence":"additional","affiliation":[{"name":"The University of Auckland,School of Computer Science,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alistair S.","family":"Glen","sequence":"additional","affiliation":[{"name":"Bioeconomy Science Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Auckland,School of Computer Science,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gillian","family":"Dobbie","sequence":"additional","affiliation":[{"name":"The University of Auckland,School of Computer Science,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Wilson","sequence":"additional","affiliation":[{"name":"The University of Auckland,School of Computer Science,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun Sing","family":"Koh","sequence":"additional","affiliation":[{"name":"The University of Auckland,School of Computer Science,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27830"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2018.8634778"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00585"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/ruminants4020013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1795.2009.00328.x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCMI51676.2020.9311574"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094783"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01333"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1742"},{"key":"ref14","article-title":"On the computational complexity of self-attention","volume-title":"Proceedings of the 34th International Conference on Algorithmic Learning Theory","author":"Keles"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00035"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_17"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01200"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413569"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02366"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758249"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolind.2025.113227"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/ece3.70958"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1068\/p2896"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW50321.2020.9096932"},{"key":"ref33","article-title":"Attention bottlenecks for multimodal fusion","author":"Nagrani","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02071-1"},{"key":"ref35","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-030718-104938"},{"key":"ref37","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100289"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13133"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref41","article-title":"Clipood: Generalizing clip to out-of-distributions","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Shu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref43","article-title":"Visualizing data using t-SNE","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref44","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.14278"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055627"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.575"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32962"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535353"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111455"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29639"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/272"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref56","article-title":"Cross-video identity correlating for person re-identification pre-training","volume-title":"The Thirty-Eighth Annual Conference on Neural Information Processing Systems","author":"Zuo"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492135.pdf?arnumber=11492135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:09:06Z","timestamp":1778047746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492135\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00044","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}