{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T12:59:03Z","timestamp":1769518743905,"version":"3.49.0"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/wacv48630.2021.00089","type":"proceedings-article","created":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T20:34:13Z","timestamp":1623702853000},"page":"846-858","source":"Crossref","is-referenced-by-count":106,"title":["The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose"],"prefix":"10.1109","author":[{"given":"Yizhak","family":"Ben-Shabat","sequence":"first","affiliation":[{"name":"Australian National University"}]},{"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney"}]},{"given":"Fatemeh","family":"Saleh","sequence":"additional","affiliation":[{"name":"Australian National University"}]},{"given":"Dylan","family":"Campbell","sequence":"additional","affiliation":[{"name":"Australian National University"}]},{"given":"Cristian","family":"Rodriguez-Opazo","sequence":"additional","affiliation":[{"name":"Australian National University"}]},{"given":"Hongdong","family":"Li","sequence":"additional","affiliation":[{"name":"Australian National University"}]},{"given":"Stephen","family":"Gould","sequence":"additional","affiliation":[{"name":"Australian National University"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00409"},{"key":"ref72","author":"wu","year":"2019","journal-title":"Detectron2"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref70","first-page":"4724","article-title":"Convolutional pose machines","author":"wei","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref76","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref77","article-title":"Towards automatic learning of procedures from web instructional videos","author":"zhou","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref74","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":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref39","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proceedings of the European Conference on Computer Vision"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00463"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"ref30","article-title":"Pointrend: Image segmentation as rendering","author":"kirillov","year":"2019","journal-title":"arXiv preprint arXiv 1912 08193"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref35","article-title":"Ikea furniture assembly environment for long-horizon complex manipulation tasks","author":"lee","year":"2019","journal-title":"arXiv preprint arXiv 1911 12945"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref60","article-title":"Artist: Autoregressive trajectory inpainting and scoring for tracking","author":"saleh","year":"2020","journal-title":"arXiv preprint arXiv 2004 06774"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.09.002"},{"key":"ref63","first-page":"510","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","author":"sigurdsson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_13"},{"key":"ref64","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"ref65","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv preprint arXiv 1212 0402"},{"key":"ref66","first-page":"3539","article-title":"Multiple people tracking by lifted multicut and person re-identification","author":"tang","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref29","first-page":"5008","article-title":"Instance-cut: from edges to instances with multicut","author":"kirillov","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2017.8227441"},{"key":"ref69","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"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.100"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","first-page":"1440","article-title":"Fast r-cnn","author":"girshick","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00576"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"ref50","first-page":"1990","article-title":"Learning to segment object candidates","author":"pinheiro","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.533"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.41"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0851-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref56","first-page":"17","article-title":"Performance measures and a data set for multi-target, multi-camera tracking","author":"ristani","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref55","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref54","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"redmon","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00475"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102897"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00627"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"ref14","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"ref18","first-page":"961","article-title":"Activitynet: A large-scale video benchmark for human activity understanding","author":"fabian caba heilbron","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref7","first-page":"7291","article-title":"Realtime multi-person 2D pose estimation using part affinity fields","author":"cao","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref49","first-page":"75","article-title":"Learning to refine object segments","author":"pinheiro","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00215"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00289"},{"key":"ref48","first-page":"7753","article-title":"3D human pose estima tion in video with temporal convolutions and semi-supervised training","author":"pavllo","year":"2019","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00763"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.378"},{"key":"ref41","first-page":"816","article-title":"Spatio-temporal lstm with trust gates for 3d human action recognition","author":"liu","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref44","article-title":"Eliminating exposure bias and loss-evaluation mismatch in multiple object tracking","author":"maksai","year":"2018","journal-title":"arXiv preprint arXiv 1811 10984"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"}],"event":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Waikoloa, HI, USA","start":{"date-parts":[[2021,1,3]]},"end":{"date-parts":[[2021,1,8]]}},"container-title":["2021 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9423008\/9423028\/09423070.pdf?arnumber=9423070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,31]],"date-time":"2022-12-31T03:18:03Z","timestamp":1672456683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9423070\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/wacv48630.2021.00089","relation":{},"subject":[],"published":{"date-parts":[[2021,1]]}}}