{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:20Z","timestamp":1777865360699,"version":"3.51.4"},"reference-count":40,"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\/501100000780","name":"European Union","doi-asserted-by":"publisher","award":["B53C22003870006"],"award-info":[{"award-number":["B53C22003870006"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["ISF 624\/25,ISF 2903\/25"],"award-info":[{"award-number":["ISF 624\/25,ISF 2903\/25"]}],"id":[{"id":"10.13039\/501100003977","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\/iccv51701.2025.01018","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10940-10949","source":"Crossref","is-referenced-by-count":0,"title":["MonSTeR: A Unified Model for Motion, Scene, Text Retrieval"],"prefix":"10.1109","author":[{"given":"Luca","family":"Collorone","sequence":"first","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Gioia","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimiliano","family":"Pappa","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Leoni","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Ficarra","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Or","family":"Litany","sequence":"additional","affiliation":[{"name":"Technion, NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Indro","family":"Spinelli","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Galasso","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00199"},{"key":"ref2","first-page":"1026","article-title":"Weisfeiler and lehman go topological: Message passing simplicial networks","volume-title":"In Proceedings of the 38th International Conference on Machine Learning","author":"Bodnar"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00182"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_12"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_4"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_53"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_19"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref12","article-title":"Contrastive audio-visual masked autoencoder","author":"Gong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00186"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01639"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00886"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00200"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_25"},{"key":"ref24","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"39529","article-title":"Position: Topological deep learning is the new frontier for relational learning","volume-title":"In Proceedings of the 41st International Conference on Machine Learning","author":"Papamarkou"},{"key":"ref26","author":"Papillon","year":"2024","journal-title":"Architectures of topological deep learning: A survey of message-passing topological neural networks"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref28","first-page":"17782","article-title":"Geometric multimodal contrastive representation learning","volume-title":"In International Conference on Machine Learning","author":"Poklukar"},{"key":"ref29","author":"Radford","year":"2019","journal-title":"Language models are unsupervised multitask learners"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00571"},{"key":"ref31","author":"Sanh","year":"2020","journal-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref33","author":"Tevet","year":"2022","journal-title":"Human motion diffusion model"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1088"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00158"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00095"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"}],"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\/11445333.pdf?arnumber=11445333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:28Z","timestamp":1777529968000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01018","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}