{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T17:05:31Z","timestamp":1773162331734,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Singapore Ministry of Education Academic Research Fund Tier 2 under Official Number","award":["T2EP20221-0023"],"award-info":[{"award-number":["T2EP20221-0023"]}]},{"name":"Sony Faculty Innovation Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3611174","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:26:58Z","timestamp":1758648418000},"page":"6192-6203","source":"Crossref","is-referenced-by-count":2,"title":["HOVER: Hyperbolic Video-Text Retrieval"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5067-2647","authenticated-orcid":false,"given":"Jun","family":"Wen","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore, Queenstown, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8850-040X","authenticated-orcid":false,"given":"Ruiqi","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Ji","sequence":"additional","affiliation":[{"name":"National University of Singapore, Queenstown, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-5282","authenticated-orcid":false,"given":"Menglin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yale University, New Haven, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Difei","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Queenstown, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7324-7034","authenticated-orcid":false,"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering,, University at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"National University of Singapore, Queenstown, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-023-00267-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref7","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021","journal-title":"arXiv:2109.04290"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275071"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3227973"},{"key":"ref10","article-title":"CLIP2TV: Align, match and distill for video-text retrieval","author":"Gao","year":"2021","journal-title":"arXiv:2111.05610"},{"key":"ref11","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021","journal-title":"arXiv:2106.11097"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref13","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language representation alignment","author":"Xue","year":"2022","journal-title":"arXiv:2209.06430"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref15","article-title":"Disentangled representation learning","author":"Wang","year":"2022","journal-title":"arXiv:2211.11695"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3136921"},{"key":"ref19","article-title":"Hyperbolic graph neural networks: A review of methods and applications","author":"Yang","year":"2022","journal-title":"arXiv:2202.13852"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00645"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.82.036106"},{"key":"ref22","first-page":"1","article-title":"Poincar\u00e9 embeddings for learning hierarchical representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Nickel"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25878-7_34"},{"key":"ref24","first-page":"4460","article-title":"Representation tradeoffs for hyperbolic embeddings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sala"},{"key":"ref25","first-page":"10011","article-title":"Generalization error bound for hyperbolic ordinal embedding","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Suzuki"},{"key":"ref26","first-page":"1243","article-title":"Generalization bounds for graph embedding using negative sampling: Linear vs hyperbolic","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Suzuki"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00441"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00661"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01644"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02666"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-1708"},{"key":"ref32","first-page":"7694","article-title":"Hyperbolic image-text representations","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Desai"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00122"},{"key":"ref34","first-page":"17939","article-title":"MOMA: Multi-object multi-actor activity parsing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Luo"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00379"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref39","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv:2212.03191"},{"key":"ref40","article-title":"VALOR: Vision-audio-language omni-perception pretraining model and dataset","author":"Liu","year":"2023","journal-title":"arXiv:2304.08345"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref42","first-page":"4868","article-title":"Hyperbolic graph convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chami"},{"key":"ref43","first-page":"8230","article-title":"Hyperbolic graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Liu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512118"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467422"},{"key":"ref46","first-page":"1","article-title":"Multi-relational Poincar\u00e9 graph embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Balazevic"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00010"},{"key":"ref48","first-page":"103","article-title":"Hyperbolic busemann learning with ideal prototypes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ghadimi Atigh"},{"key":"ref49","first-page":"1","article-title":"Hyperbolic neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ganea"},{"key":"ref50","article-title":"Hyperbolic neural networks++","author":"Shimizu","year":"2020","journal-title":"arXiv:2006.08210"},{"key":"ref51","article-title":"Fully hyperbolic neural networks","author":"Chen","year":"2021","journal-title":"arXiv:2105.14686"},{"key":"ref52","first-page":"1646","article-title":"Hyperbolic entailment cones for learning hierarchical embeddings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganea"},{"key":"ref53","first-page":"12316","article-title":"Modeling heterogeneous hierarchies with relation-specific hyperbolic cones","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bai"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00726"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00929"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_28"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","first-page":"3779","article-title":"Learning continuous hierarchies in the Lorentz model of hyperbolic geometry","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nickel"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11176922.pdf?arnumber=11176922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:19:30Z","timestamp":1759295970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11176922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3611174","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}