{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:55:59Z","timestamp":1757310959208,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161403","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T13:20:56Z","timestamp":1688476856000},"page":"8262-8268","source":"Crossref","is-referenced-by-count":7,"title":["ANSEL Photobot: A Robot Event Photographer with Semantic Intelligence"],"prefix":"10.1109","author":[{"given":"Dmitriy","family":"Rivkin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"Dudek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikhil","family":"Kakodkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Meger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Limoyo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Jenkin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francois","family":"Hogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341086"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1249268"},{"key":"ref34","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Picture composition for a robot photographer","year":"2003","author":"dixon","key":"ref15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"journal-title":"Lerop A learning-based modular robot photography framework","year":"2019","author":"kang","key":"ref14"},{"key":"ref36","article-title":"c the syntax and semantics of the proposed international algebraic language of the zurich acm-gamm conference","author":"jw","year":"0","journal-title":"Proceedings of the International Conference of Information Processing UNESCO Paris June"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985868"},{"key":"ref30","first-page":"13 988","article-title":"Clip-it! language-guided video summarization","author":"narasimhan","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907096"},{"journal-title":"Language Models are Unsupervised Multitask Learners","year":"2019","author":"radford","key":"ref33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21698"},{"key":"ref32","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Advances in neural information processing systems"},{"journal-title":"LaMDA Language Models for Dialog Applications","year":"2022","author":"thoppilan","key":"ref2"},{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907405"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1998.724672"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206454"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463196"},{"journal-title":"Summarizing Videos with Attention","year":"2018","author":"fajtl","key":"ref24"},{"key":"ref23","first-page":"407","author":"apostolidis","year":"2022","journal-title":"Summarizing videos using concentrated attention and considering the uniqueness and diversity of the video frames"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9500-x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540176"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2000.895271"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCBI.2018.00014"},{"key":"ref21","first-page":"pp-xxxx","article-title":"The paparazzi solution","author":"brisset","year":"0","journal-title":"MAV 2006 2nd US-European Competition and Workshop on Micro Air Vehicles"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3393914.3395816"},{"key":"ref27","first-page":"1","article-title":"Google clips smart camera isn't smart enough, but its aims are still worth considering","volume":"27","author":"bonnington","year":"2018","journal-title":"Slate [Online]"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.229"},{"journal-title":"Lm-nav Robotic navigation with large pre-trained models of language vision and action","year":"2022","author":"shah","key":"ref8"},{"journal-title":"Inner monologue Embodied reasoning through planning with language models","year":"2022","author":"huang","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531404"},{"journal-title":"Learning Transferable Visual Models From Natural Language Supervision","year":"2021","author":"radford","key":"ref4"},{"journal-title":"Palm Scaling language modeling with pathways","year":"2022","author":"chowdhery","key":"ref3"},{"key":"ref6","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"ahn","year":"2022","journal-title":"ArXiv Preprint"},{"journal-title":"Flamingo a visual language model for few-shot learning","year":"2022","author":"alayrac","key":"ref5"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161403.pdf?arnumber=10161403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T13:36:23Z","timestamp":1690205783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161403","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}