{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:15Z","timestamp":1777888755479,"version":"3.51.4"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC2232860"],"award-info":[{"award-number":["OAC2232860"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01463","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15770-15780","source":"Crossref","is-referenced-by-count":0,"title":["Global and Local Entailment Learning for Natural World Imagery"],"prefix":"10.1109","author":[{"given":"Srikumar","family":"Sastry","sequence":"first","affiliation":[{"name":"Washington University in St. Louis"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aayush","family":"Dhakal","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Xing","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subash","family":"Khanal","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathan","family":"Jacobs","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_13"},{"key":"ref2","article-title":"Multi-relational poincar\u00e9 graph embeddings","volume":"32","author":"Balazevic","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref4","article-title":"Hyperbolic graph convolutional neural networks","volume":"32","author":"Chami","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.617"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01254"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3687123.3698297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01449"},{"key":"ref9","article-title":"Probabilistic language-image pre-training","author":"Chun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Wildsat: Learning satellite image representations from wildlife observations","author":"Daroya","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"7694","article-title":"Hyperbolic image-text representations","volume-title":"International Conference on Machine Learning","author":"Desai","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-1708"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.fss.2011.09.005"},{"key":"ref14","first-page":"1646","article-title":"Hyperbolic entailment cones for learning hierarchical embeddings","volume-title":"International conference on machine learning","author":"Ganea","year":"2018"},{"key":"ref15","article-title":"CLIBD: Bridging vision and genomics for biodiversity monitoring at scale","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Gong","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01225"},{"key":"ref17","first-page":"173","article-title":"Contrastive ground-level image and remote sensing pretraining improves representation learning for natural world imagery","volume-title":"European Conference on Computer Vision","author":"Andy","year":"2024"},{"key":"ref18","volume-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1313"},{"key":"ref21","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0529"},{"key":"ref23","volume-title":"Vlm4bio: A benchmark dataset to evaluate pretrained vision-language models for trait discovery from biological images","author":"Maruf","year":"2024"},{"key":"ref24","article-title":"Cross the gap: Exposing the intra-modal misalignment in clip via modality inversion","author":"Mistretta","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01844"},{"key":"ref26","article-title":"Poincar\u00e9 embeddings for learning hierarchical representations","volume":"30","author":"Nickel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"37793788","article-title":"Learning continuous hierarchies in the lorentz model of hyperbolic geometry","volume-title":"International conference on machine learning","author":"Nickel","year":"2018"},{"key":"ref28","article-title":"Compositional entailment learning for hyperbolic vision-language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Pal","year":"2025"},{"key":"ref29","first-page":"1","article-title":"Harnessing artificial intelligence to fill global shortfalls in biodiversity knowledge","author":"Laura","year":"2025","journal-title":"Nature Reviews Biodiversity"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02574"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2023.1224471"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00698"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00179"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2023.102095"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.45"},{"key":"ref38","article-title":"Poincar\u2019e glove: Hyperbolic word embeddings","author":"Tifrea","year":"2018","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref40","article-title":"Order-embeddings of images and language","author":"Vendrov","year":"2015","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0379"},{"key":"ref44","article-title":"Learning visual hierarchies with hyperbolic embeddings","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3241"},{"key":"ref46","article-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Shadow cones: A generalized framework for partial order embeddings","author":"Yu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444959.pdf?arnumber=11444959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:56Z","timestamp":1777611296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01463","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}