{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:25:49Z","timestamp":1730255149049,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956701","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1273-1279","source":"Crossref","is-referenced-by-count":1,"title":["Cosine Similarity based Few-Shot Video Classifier with Attention-based Aggregation"],"prefix":"10.1109","author":[{"given":"Biplob","family":"Debnath","sequence":"first","affiliation":[{"name":"NEC Laboratories America,Princeton,New Jersey,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Po","sequence":"additional","affiliation":[{"name":"NEC Laboratories America,Princeton,New Jersey,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farhan Asif","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"The University of New Mexico,Albuquerque,NM,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srimat","family":"Chakradhar","sequence":"additional","affiliation":[{"name":"NEC Laboratories America,Princeton,New Jersey,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref31","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref30","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"kolesnikov","year":"2021","journal-title":"ICLRE"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"ref36","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00610"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref12","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref17","first-page":"6202","article-title":"Slowfast networks for video recognition","author":"feichtenhofer","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_38"},{"key":"ref5","article-title":"Few-shot action recognition with prototype-centered attentive learning","author":"zhu","year":"2021","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_26"},{"key":"ref7","article-title":"A closer look at few-shot classification","author":"chen","year":"2018","journal-title":"ICLRE"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"kay","key":"ref2"},{"key":"ref9","article-title":"A closer look at few-shot video classifcation: A new baseline and benchmark","author":"zhenxi zhu","year":"2021","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"year":"2021","key":"ref1","article-title":"Video marketing statistics: The state of video marketing in 2021"},{"article-title":"A comprehensive study of deep video action recognition","year":"2020","author":"zhu","key":"ref20"},{"article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"soomro","key":"ref22"},{"article-title":"Towards good practices for very deep two-stream convnets","year":"2015","author":"wang","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"tran","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956701.pdf?arnumber=9956701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:06:23Z","timestamp":1671480383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956701","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}