{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:07:58Z","timestamp":1750306078255,"version":"3.41.0"},"reference-count":75,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2017,6,28]],"date-time":"2017-06-28T00:00:00Z","timestamp":1498608000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Ministry of Science and Technology of the Republic of China","award":["104-2628-E-001-001-MY2, 105-2221-E-001-030-MY2, 105-2218-E-001-006 and 104-2221-E-002-050-MY3"],"award-info":[{"award-number":["104-2628-E-001-001-MY2, 105-2221-E-001-030-MY2, 105-2218-E-001-006 and 104-2221-E-002-050-MY3"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2017,8,31]]},"abstract":"<jats:p>\n            This article addresses the problem of recognizing\n            <jats:italic>partially observed<\/jats:italic>\n            human actions. Videos of actions acquired in the real world often contain corrupt frames caused by various factors. These frames may appear irregularly, and make the actions only partially observed. They change the appearance of actions and degrade the performance of pretrained recognition systems. In this article, we propose an approach to address the corrupt-frame problem without knowing their locations and durations in advance. The proposed approach includes two key components:\n            <jats:italic>outlier filtering<\/jats:italic>\n            and\n            <jats:italic>observation completion<\/jats:italic>\n            . The former identifies and filters out unobserved frames, and the latter fills up the filtered parts by retrieving coherent alternatives from training data.\n            <jats:italic>Hidden Conditional Random Fields<\/jats:italic>\n            (HCRFs) are then used to recognize the filtered and completed actions. Our approach has been evaluated on three datasets, which contain both fully observed actions and partially observed actions with either real or synthetic corrupt frames. The experimental results show that our approach performs favorably against the other state-of-the-art methods, especially when corrupt frames are present.\n          <\/jats:p>","DOI":"10.1145\/3089250","type":"journal-article","created":{"date-parts":[[2017,6,30]],"date-time":"2017-06-30T12:36:19Z","timestamp":1498826179000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Recognizing Human Actions with Outlier Frames by Observation Filtering and Completion"],"prefix":"10.1145","volume":"13","author":[{"given":"Shih-Yao","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan University, CA, USA"}]},{"given":"Yen-Yu","family":"Lin","sequence":"additional","affiliation":[{"name":"Academia Sinica, Taipei, Taiwan"}]},{"given":"Chu-Song","family":"Chen","sequence":"additional","affiliation":[{"name":"Academia Sinica, Taipei, Taiwan"}]},{"given":"Yi-Ping","family":"Hung","sequence":"additional","affiliation":[{"name":"Tainan National University of the Arts, Tainan City, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2017,6,28]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502433"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0490-7"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_46"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.343"},{"key":"e_1_2_1_5_1","volume-title":"Realtime multi-person 2D pose estimation using part affinity fields. arXiv Preprint arXiv:1611.08050","author":"Cao Zhe","year":"2016","unstructured":"Zhe Cao , Tomas Simon , Shih-En Wei , and Yaser Sheikh . 2016. Realtime multi-person 2D pose estimation using part affinity fields. arXiv Preprint arXiv:1611.08050 ( 2016 ). Zhe Cao, Tomas Simon, Shih-En Wei, and Yaser Sheikh. 2016. Realtime multi-person 2D pose estimation using part affinity fields. arXiv Preprint arXiv:1611.08050 (2016)."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.96"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.19"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.53"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206612"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995555"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2038089"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.04.022"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.510"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2006.01.012"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2350774"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.16"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390195"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208303"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"e_1_2_1_23_1","volume-title":"Proc. Int\u2019l. Joint Conf. Artificial Intelligence. 1351--1357","author":"Gowayyed Mohammad A.","year":"2013","unstructured":"Mohammad A. Gowayyed , Marwan Torki , Mohamed E. Hussein , and Motaz El-Saban . 2013 . Histogram of oriented displacements (HOD): Describing trajectories of human joints for action recognition . In Proc. Int\u2019l. Joint Conf. Artificial Intelligence. 1351--1357 . Mohammad A. Gowayyed, Marwan Torki, Mohamed E. Hussein, and Motaz El-Saban. 2013. Histogram of oriented displacements (HOD): Describing trajectories of human joints for action recognition. In Proc. Int\u2019l. Joint Conf. Artificial Intelligence. 1351--1357."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0683-3"},{"key":"e_1_2_1_25_1","volume-title":"Proc. Euro. Conf. Signal Processing. 1--5.","author":"Iosifidis Alexandros","year":"2013","unstructured":"Alexandros Iosifidis , Anastasios Tefas , and Ioannis Pitas . 2013 . Dynamic action classification based on iterative data selection and feedforward neural networks . In Proc. Euro. Conf. Signal Processing. 1--5. Alexandros Iosifidis, Anastasios Tefas, and Ioannis Pitas. 2013. Dynamic action classification based on iterative data selection and feedforward neural networks. In Proc. Euro. Conf. Signal Processing. 1--5."},{"key":"e_1_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Yun Jiang and Ashutosh Saxena. 2014. Modeling high-dimensional humans for activity anticipation using Gaussian process latent CRFs. In Robotics: Science and Systems.  Yun Jiang and Ashutosh Saxena. 2014. Modeling high-dimensional humans for activity anticipation using Gaussian process latent CRFs. In Robotics: Science and Systems.","DOI":"10.15607\/RSS.2014.X.015"},{"key":"e_1_2_1_27_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E . Hinton . 2012 . Imagenet classification with deep convolutional neural networks. In Proc. Advances in Neural Information Processing Systems . 1097--1105. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Proc. Advances in Neural Information Processing Systems. 1097--1105."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1236471.1236475"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.2297321"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912001"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005597"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.08.016"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952630"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.335"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2399172"},{"key":"e_1_2_1_38_1","volume-title":"Where, what and how actions occur in videos? arXiv Preprint arXiv:1602.03346","author":"Liu Li","year":"2016","unstructured":"Li Liu , Yi Zhou , and Ling Shao . 2016b. DAP3D-Net : Where, what and how actions occur in videos? arXiv Preprint arXiv:1602.03346 ( 2016 ). Li Liu, Yi Zhou, and Ling Shao. 2016b. DAP3D-Net: Where, what and how actions occur in videos? arXiv Preprint arXiv:1602.03346 (2016)."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_28"},{"key":"e_1_2_1_40_1","volume-title":"Proc. Berkeley Symp. Mathematical Statistics and Probability","volume":"1","author":"MacQueen James","year":"1967","unstructured":"James MacQueen . 1967 . Some methods for classification and analysis of multivariate observations . In Proc. Berkeley Symp. Mathematical Statistics and Probability , Vol. 1 . 281--297. James MacQueen. 1967. Some methods for classification and analysis of multivariate observations. In Proc. Berkeley Symp. Mathematical Statistics and Probability, Vol. 1. 281--297."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"e_1_2_1_42_1","volume-title":"Proc. Int\u2019l. Conf. Machine Learning. 1033--1040","author":"Martens James","year":"2011","unstructured":"James Martens and Ilya Sutskever . 2011 . Learning recurrent neural networks with Hessian-free optimization . In Proc. Int\u2019l. Conf. Machine Learning. 1033--1040 . James Martens and Ilya Sutskever. 2011. Learning recurrent neural networks with Hessian-free optimization. In Proc. Int\u2019l. Conf. Machine Learning. 1033--1040."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771382"},{"key":"e_1_2_1_45_1","volume-title":"Proc. Advances in Neural Information Processing Systems. 1419--1427","author":"Peng Jian","year":"2009","unstructured":"Jian Peng , Liefeng Bo , and Jinbo Xu . 2009 . Conditional neural fields . In Proc. Advances in Neural Information Processing Systems. 1419--1427 . Jian Peng, Liefeng Bo, and Jinbo Xu. 2009. Conditional neural fields. In Proc. Advances in Neural Information Processing Systems. 1419--1427."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA.2013.6566433"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1124"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.342"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"e_1_2_1_50_1","doi-asserted-by":"crossref","unstructured":"M. S. Ryoo and J. K. Aggarwal. 2010. UT-Interaction Dataset ICPR contest on Semantic Description of Human Activities (SDHA). (2010).  M. S. Ryoo and J. K. Aggarwal. 2010. UT-Interaction Dataset ICPR contest on Semantic Description of Human Activities (SDHA). (2010).","DOI":"10.1007\/978-3-642-17711-8_28"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587730"},{"key":"e_1_2_1_52_1","volume-title":"Proc. Conf. Computer Vision and Pattern Recognition. 1784--1791","author":"Shen Wei","year":"2012","unstructured":"Wei Shen , Ke Deng , Xiang Bai , Tommer Leyvand , Baining Guo , and Zhuowen Tu . 2012 . Exemplar-based human action pose correction and tagging . In Proc. Conf. Computer Vision and Pattern Recognition. 1784--1791 . Wei Shen, Ke Deng, Xiang Bai, Tommer Leyvand, Baining Guo, and Zhuowen Tu. 2012. Exemplar-based human action pose correction and tagging. In Proc. Conf. Computer Vision and Pattern Recognition. 1784--1791."},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.772"},{"key":"e_1_2_1_54_1","volume-title":"Proc. Conf. Computer Vision and Pattern Recognition. 1815--1821","author":"Shu Guang","year":"2012","unstructured":"Guang Shu , Afshin Dehghan , Omar Oreifej , Emily Hand , and Mubarak Shah . 2012 . Part-based multiple-person tracking with partial occlusion handling . In Proc. Conf. Computer Vision and Pattern Recognition. 1815--1821 . Guang Shu, Afshin Dehghan, Omar Oreifej, Emily Hand, and Mubarak Shah. 2012. Part-based multiple-person tracking with partial occlusion handling. In Proc. Conf. Computer Vision and Pattern Recognition. 1815--1821."},{"key":"e_1_2_1_55_1","volume-title":"Proc. Advances in Neural Information Processing Systems. 568--576","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014 . Two-stream convolutional networks for action recognition in videos . In Proc. Advances in Neural Information Processing Systems. 568--576 . Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Proc. Advances in Neural Information Processing Systems. 568--576."},{"key":"e_1_2_1_56_1","volume-title":"Proc. Conf. Computer Vision and Pattern Recognition. 2120--2127","author":"Song Yale","year":"2012","unstructured":"Yale Song , Louis-Philippe Morency , and Randall Davis . 2012 . Multi-view latent variable discriminative models for action recognition . In Proc. Conf. Computer Vision and Pattern Recognition. 2120--2127 . Yale Song, Louis-Philippe Morency, and Randall Davis. 2012. Multi-view latent variable discriminative models for action recognition. In Proc. Conf. Computer Vision and Pattern Recognition. 2120--2127."},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.457"},{"key":"e_1_2_1_58_1","volume-title":"Proc. Int\u2019l. Conf. Robotics and Automation. 842--849","author":"Sung Jaeyong","year":"2012","unstructured":"Jaeyong Sung , Colin Ponce , Bart Selman , and Ashutosh Saxena . 2012 . Unstructured human activity detection from RGBD images . In Proc. Int\u2019l. Conf. Robotics and Automation. 842--849 . Jaeyong Sung, Colin Ponce, Bart Selman, and Ashutosh Saxena. 2012. Unstructured human activity detection from RGBD images. In Proc. Int\u2019l. Conf. Robotics and Automation. 842--849."},{"volume-title":"An Introduction to Conditional Random Fields for Relational Learning","author":"Sutton C.","key":"e_1_2_1_59_1","unstructured":"C. Sutton and A. McCallum . 2007. An Introduction to Conditional Random Fields for Relational Learning . MIT Press . C. Sutton and A. McCallum. 2007. An Introduction to Conditional Random Fields for Relational Learning. MIT Press."},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2385591"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354966"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.198"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383298"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459207"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.5555\/1927006.1927055"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.365"},{"key":"e_1_2_1_69_1","volume-title":"Learning deep feature representations with domain guided dropout for person re-identification. arXiv Preprint arXiv:1604.07528","author":"Xiao Tong","year":"2016","unstructured":"Tong Xiao , Hongsheng Li , Wanli Ouyang , and Xiaogang Wang . 2016. Learning deep feature representations with domain guided dropout for person re-identification. arXiv Preprint arXiv:1604.07528 ( 2016 ). Tong Xiao, Hongsheng Li, Wanli Ouyang, and Xiaogang Wang. 2016. Learning deep feature representations with domain guided dropout for person re-identification. arXiv Preprint arXiv:1604.07528 (2016)."},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396380"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2319594"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/2750780"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2009.05.015"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2128332"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648583"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3089250","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3089250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:30:07Z","timestamp":1750217407000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3089250"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,28]]},"references-count":75,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,8,31]]}},"alternative-id":["10.1145\/3089250"],"URL":"https:\/\/doi.org\/10.1145\/3089250","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2017,6,28]]},"assertion":[{"value":"2016-09-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}