{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:29:58Z","timestamp":1775190598945,"version":"3.50.1"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/iccvw.2019.00539","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T12:29:15Z","timestamp":1583497755000},"page":"4385-4395","source":"Crossref","is-referenced-by-count":55,"title":["Manipulation-Skill Assessment from Videos with Spatial Attention Network"],"prefix":"10.1109","author":[{"given":"Zhenqiang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minjie","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoichi","family":"Sato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"sharma","year":"2015","journal-title":"Action recognition using visual attention"},{"key":"ref38","first-page":"618","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","author":"ramprasaath","year":"2017","journal-title":"ICCV"},{"key":"ref33","first-page":"71","article-title":"Human motion assessment in real time using recurrent self-organization","author":"german","year":"0","journal-title":"IEEE Intl Symposium on Robot and Human Interactive Communication (Ro-Man)"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"4700","DOI":"10.1523\/JNEUROSCI.13-11-04700.1993","article-title":"A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information","volume":"13","author":"bruno","year":"1993","journal-title":"Journal of Neuroscience"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07521-1_15"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_36"},{"key":"ref36","author":"paszke","year":"2017","journal-title":"On Automatic Differentiation"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.16"},{"key":"ref34","author":"park","year":"2018","journal-title":"BAM Bottleneck Attention Module"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref29","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.239"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","first-page":"754","article-title":"Predicting gaze in egocentric video by learning task-dependent attention transition","author":"huang","year":"2018","journal-title":"ECCV"},{"key":"ref22","first-page":"523","article-title":"Estimation of skill levels in sports based on hierarchical spatiotemporal correspondences","author":"ilg","year":"0","journal-title":"Pattern Recognition Symposium"},{"key":"ref21","author":"huang","year":"2019","journal-title":"Mutual context network for jointly estimating egocentric gaze and actions"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36592-3_51"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00081"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref25","article-title":"Unified spatio-temporal attention networks for action recognition in videos","author":"li","year":"2018","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref50","author":"xu","year":"2018","journal-title":"Learning to score the figure skating sports videos"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.image.2017.11.005","article-title":"Hierarchical multi-scale attention networks for action recognition","volume":"61","author":"shiyang","year":"2018","journal-title":"Signal Processing Image Communication"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1007\/s11548-016-1468-2","article-title":"Automated video-based assessment of surgical skills for training and evaluation in medical schools","volume":"11","author":"aneeq","year":"2016","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/s11548-018-1704-z","article-title":"Video and accelerometer-based motion analysis for automated surgical skills assessment","volume":"13","author":"aneeq","year":"2018","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"ref57","first-page":"430","article-title":"Automated assessment of surgical skills using frequency analysis","author":"aneeq","year":"0","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2361121"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2072545.2072550"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350896"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00634"},{"key":"ref11","author":"doughty","year":"2019","journal-title":"The Pros and Cons Rank-aware Temporal Attention for Skill Determination in Long Videos"},{"key":"ref40","article-title":"Video based assessment of osats using sequential motion textures","author":"sharma","year":"2014","journal-title":"Georgia Institute of Technology"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.402"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref14","first-page":"3","article-title":"Jhu-isi gesture and skill assessment working set (jigsaws): A surgical activity dataset for human motion modeling","volume":"3","author":"gao","year":"0","journal-title":"MICCAI Workshop M2CAI"},{"key":"ref15","first-page":"34","article-title":"Attentional pooling for action recognition","author":"girdhar","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.273"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref3","first-page":"23","article-title":"Graph-based analysis of physical exercise actions","author":"\u00e7eliktutan","year":"0","journal-title":"Proceedings of the 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Healthcare"},{"key":"ref6","author":"chung","year":"2014","journal-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_5"},{"key":"ref8","first-page":"135","article-title":"Guide to the carnegie mellon university multimodal activity (cmu-mmac) database","author":"de la torre","year":"2008","journal-title":"Robotics Institute"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451364"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.11.016"},{"key":"ref48","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"ECCV"},{"key":"ref47","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref42","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2014.6867908"},{"key":"ref44","author":"soomro","year":"2012","journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild"},{"key":"ref43","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","volume":"1","author":"song","year":"2017","journal-title":"AAAI"}],"event":{"name":"2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW)","location":"Seoul, Korea (South)","start":{"date-parts":[[2019,10,27]]},"end":{"date-parts":[[2019,10,28]]}},"container-title":["2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/8982559\/9021948\/09022197.pdf?arnumber=9022197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T15:14:01Z","timestamp":1658157241000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/9022197\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":59,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/iccvw.2019.00539","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}