{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:46:15Z","timestamp":1730231175153,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095638","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["One-Shot Action Detection via Attention Zooming In"],"prefix":"10.1109","author":[{"given":"He-Yen","family":"Hsieh","sequence":"first","affiliation":[{"name":"Institute of Information Science,Academia Sinica,Taiwan"}]},{"given":"Ding-Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Information Science,Academia Sinica,Taiwan"}]},{"given":"Cheng-Wei","family":"Chang","sequence":"additional","affiliation":[{"name":"Institute of Information Science,Academia Sinica,Taiwan"}]},{"given":"Tyng-Luh","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Science,Academia Sinica,Taiwan"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463643"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref23","article-title":"Multi-modal few-shot temporal action detection via vision-language meta-adaptation","volume":"abs 2211 14905","author":"nag","year":"2022","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref11","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00517"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6815"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLRE"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","article-title":"The THUMOS challenge on action recognition for videos “in the wild","volume":"155","author":"idrees","year":"2017","journal-title":"Comput Vis Image Underst"},{"key":"ref18","first-page":"961","article-title":"Activitynet: A large-scale video benchmark for human activity under-standing","author":"heilbron","year":"2015","journal-title":"CVPR"},{"key":"ref8","article-title":"Few-shot temporal action localization with query adaptive transformer","author":"nag","year":"2021","journal-title":"BMVC"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6763"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/610"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_30"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095638.pdf?arnumber=10095638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:56:46Z","timestamp":1699883806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095638","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}