{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:27Z","timestamp":1777865307199,"version":"3.51.4"},"reference-count":59,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01113","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11969-11979","source":"Crossref","is-referenced-by-count":0,"title":["Switch-a-View: View Selection Learned from Unlabeled In-the-Wild Videos"],"prefix":"10.1109","author":[{"given":"Sagnik","family":"Majumder","sequence":"first","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tushar","family":"Nagarajan","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziad","family":"Al-Halah","sequence":"additional","affiliation":[{"name":"University of Utah"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989164"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601198"},{"key":"ref3","article-title":"Video-mined task graphs for keystep recognition in instructional videos","volume":"36","author":"Ashutosh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01365"},{"key":"ref5","article-title":"Brandon Castellano","volume-title":"Pyscenedetect"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3183794"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00184"},{"key":"ref8","article-title":"Geometry-aware recurrent neural networks for active visual recognition","volume":"31","author":"Cheng","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Self-view grounding given a narrated 360 deg video","author":"Chou","year":"2017","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298981"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"ref12","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00151"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00026"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871033"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/354384.354537"},{"key":"ref17","article-title":"Diverse sequential subset selection for supervised video summarization","author":"Gong","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02557-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180851"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.153"},{"key":"ref23","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840991"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.284"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00687"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02702"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01395"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_31"},{"key":"ref36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.455"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw6326"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_16"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546119"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_19"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01583"},{"key":"ref46","article-title":"Charades-ego: A large-scale dataset of paired third and first person videos","author":"Gunnar","year":"2018","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Video skimming for quick browsing based on audio and image characterization","volume-title":"Technical Report CMU-CS-95\u2013186","author":"Smith","year":"1995"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref49","first-page":"154","article-title":"Pano2vid: Automatic cinematography for watching 360 videos","volume-title":"Asian Conference on Computer Vision","author":"Su","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.854388"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref52","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref55","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01228-1_1","article-title":"Snap angle prediction for 360\u00b0 panoramas","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Xiong","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1324287.1324293"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01424"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01033"}],"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\/11445328.pdf?arnumber=11445328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:38Z","timestamp":1777529678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445328\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01113","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}