{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:30:49Z","timestamp":1772040649911,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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":[[2021,9,19]]},"DOI":"10.1109\/icip42928.2021.9506157","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T21:08:41Z","timestamp":1629752921000},"page":"1059-1063","source":"Crossref","is-referenced-by-count":11,"title":["Joint Learning on the Hierarchy Representation for Fine-Grained Human Action Recognition"],"prefix":"10.1109","author":[{"given":"Mei Chee","family":"Leong","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I2 R),A* STAR"}]},{"given":"Hui Li","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2 R),A* STAR"}]},{"given":"Haosong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2 R),A* STAR"}]},{"given":"Liyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2 R),A* STAR"}]},{"given":"Feng","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}]},{"given":"Joo Hwee","family":"Lim","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2 R),A* STAR"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app10020557"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00527"},{"key":"ref5","article-title":"Haa500: Human-centric atomic action dataset with curated videos","author":"chung","year":"2020"},{"key":"ref8","author":"wang","year":"2017","journal-title":"Temporal segment networks for action recognition in videos"},{"key":"ref7","article-title":"Finegym: A hierarchical video dataset for fine-grained action understanding","author":"dian shao","year":"2020","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref2","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv preprint arXiv 1705 06950"},{"key":"ref1","first-page":"961","article-title":"Activitynet: A large-scale video benchmark for human activity understanding","author":"heilbron","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref9","author":"zhou","year":"2018","journal-title":"Temporal relational reasoning in videos"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref21","year":"2020","journal-title":"Openmmlab’s next generation video understanding toolbox and benchmark"}],"event":{"name":"2021 IEEE International Conference on Image Processing (ICIP)","location":"Anchorage, AK, USA","start":{"date-parts":[[2021,9,19]]},"end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9506008\/9506009\/09506157.pdf?arnumber=9506157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T21:10:11Z","timestamp":1655154611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9506157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icip42928.2021.9506157","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}