{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:14:45Z","timestamp":1776888885646,"version":"3.51.2"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561347","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"13049-13055","source":"Crossref","is-referenced-by-count":5,"title":["Attentional Learn-able Pooling for Human Activity Recognition"],"prefix":"10.1109","author":[{"given":"Bappaditya","family":"Debnath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mary","family":"O'Brien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swagat","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ardhendu","family":"Behera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.334"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.342"},{"key":"ref35","first-page":"428","article-title":"Efficient pose-based action recognition","author":"eweiwi","year":"2014","journal-title":"ACCV"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"AAAI"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","first-page":"971","article-title":"Action- vlad: Learning spatio-temporal aggregation for action classification","author":"girdhar","year":"2017","journal-title":"CVPR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref15","article-title":"Learnable pooling with context gating for video classification","author":"miech","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.01.010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.516"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537340"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.gaitpost.2014.01.008"},{"key":"ref28","first-page":"34","article-title":"Attentional pooling for action recognition","author":"girdhar","year":"2017","journal-title":"NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.225"},{"key":"ref6","article-title":"Action recognition using visual attention","author":"sharma","year":"2016","journal-title":"ICLR Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00056"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"ref8","article-title":"Human activity recognition with pose-driven attention to rgb","author":"baradel","year":"2018","journal-title":"BMVC"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2841649"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.456"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.207"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref20","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref47","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref21","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2018"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12328","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"yan","year":"2018","journal-title":"AAAI"},{"key":"ref24","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2627563"},{"key":"ref44","first-page":"601","article-title":"Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn","author":"li","year":"2017","journal-title":"ICME Workshops"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11212","article-title":"An end-to-end spatiotemporal attention model for human action recognition from skeleton data","author":"song","year":"2017","journal-title":"AAAI"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561347.pdf?arnumber=9561347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:47:05Z","timestamp":1673563625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561347\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561347","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}