{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:18:57Z","timestamp":1771265937734,"version":"3.50.1"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"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":[[2018,7]]},"DOI":"10.1109\/icme.2018.8486486","type":"proceedings-article","created":{"date-parts":[[2018,10,11]],"date-time":"2018-10-11T18:34:18Z","timestamp":1539282858000},"page":"1-6","source":"Crossref","is-referenced-by-count":32,"title":["Skeleton-Indexed Deep Multi-Modal Feature Learning for High Performance Human Action Recognition"],"prefix":"10.1109","author":[{"given":"Sijie","family":"Song","sequence":"first","affiliation":[{"name":"Institute of Computer Science and Technology, Peking University, Beijing, China"}]},{"given":"Cuiling","family":"Lan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation, Beijing, China"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"given":"Jiaying","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Computer Science and Technology, Peking University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref10","author":"simonyan","year":"0","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref14","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref15","first-page":"816","article-title":"Spatio-temporal lstm with trust gates for 3D human action recognition","author":"liu","year":"2016","journal-title":"ECCV"},{"key":"ref16","first-page":"2923","article-title":"Chained multi-stream networks exploiting pose, motion, and appearance for action classification and detection","author":"mohammadreza","year":"2017","journal-title":"ICCV"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.48"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964328"},{"key":"ref3","first-page":"20","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref6","first-page":"744","article-title":"Multi-region two-stream r-cnn for action detection","author":"peng","year":"2016","journal-title":"ECCV"},{"key":"ref5","first-page":"1","article-title":"Multi-modality multi-task recurrent neural network for online action detection","author":"liu","year":"2018","journal-title":"IEEE Transactions on Circuit Systems and Video Technology"},{"key":"ref8","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"2017","journal-title":"inAAAI\/IAAI"},{"key":"ref7","first-page":"3218","article-title":"P-CNN: Pose-based cnn features for action recognition","author":"guilhem","year":"2015","journal-title":"ICCV"},{"key":"ref2","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref9","article-title":"Temporal perceptive network for skeleton-based action recognition","author":"hu","year":"2017","journal-title":"BMVC"}],"event":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","location":"San Diego, CA, USA","start":{"date-parts":[[2018,7,23]]},"end":{"date-parts":[[2018,7,27]]}},"container-title":["2018 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8472825\/8486434\/08486486.pdf?arnumber=8486486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T18:38:14Z","timestamp":1754332694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8486486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icme.2018.8486486","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}