{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:45:58Z","timestamp":1760237158986,"version":"build-2065373602"},"reference-count":23,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2020,3,16]],"date-time":"2020-03-16T00:00:00Z","timestamp":1584316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","award":["JYT19029"],"award-info":[{"award-number":["JYT19029"]}],"id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602320"],"award-info":[{"award-number":["61602320"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004314","name":"Shenyang Aerospace University","doi-asserted-by":"publisher","award":["18YB39"],"award-info":[{"award-number":["18YB39"]}],"id":[{"id":"10.13039\/501100004314","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Predicting the categories of actions in partially observed videos is a challenging task in the computer vision field. The temporal progress of an ongoing action is of great importance for action prediction, since actions can present different characteristics at different temporal stages. To this end, we propose a novel multi-task deep forest framework, which treats temporal progress analysis as a relevant task to action prediction and takes advantage of observation ratio labels of incomplete videos during training. The proposed multi-task deep forest is a cascade structure of random forests and multi-task random forests. Unlike the traditional single-task random forests, multi-task random forests are built upon incomplete training videos annotated with action labels as well as temporal progress labels. Meanwhile, incorporating both random forests and multi-task random forests can increase the diversity of classifiers and improve the discriminative power of the multi-task deep forest. Experiments on the UT-Interaction and the BIT-Interaction datasets demonstrate the effectiveness of the proposed multi-task deep forest.<\/jats:p>","DOI":"10.3390\/info11030158","type":"journal-article","created":{"date-parts":[[2020,3,17]],"date-time":"2020-03-17T09:27:41Z","timestamp":1584437261000},"page":"158","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Multi-Task Framework for Action Prediction"],"prefix":"10.3390","volume":"11","author":[{"given":"Tianyu","family":"Yu","sequence":"first","affiliation":[{"name":"School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China"}]},{"given":"Cuiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China"}]},{"given":"Zhuo","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China"}]},{"given":"Xiangbin","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China"}]}],"member":"1968","published-online":{"date-parts":[[2020,3,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S. (2011, January 7). Human activity prediction: Early recognition of ongoing activities from streaming videos. Proceedings of the IEEE International Conference on Computer Vision, Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"ref_2","unstructured":"Yu, C., Barrett, D., Barbu, A., Narayanaswamy, S., and Song, W. (2013, January 23\u201328). Recognize Human Activities from Partially Observed Videos. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, Portland, OR, USA."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Lan, T., Chen, T.C., and Savarese, S. (2014, January 6\u201312). A Hierarchical Representation for Future Action Prediction. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"ref_4","unstructured":"Yu, K., Kit, D., and Yun, F. (2014, January 6\u201312). A Discriminative Model with Multiple Temporal Scales for Action Prediction. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","article-title":"On Space-Time Interest Points","volume":"64","author":"Laptev","year":"2005","journal-title":"Int. J. Comput. Vis."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, H., and Schmid, C. (2014, January 11). Action Recognition with Improved Trajectories. Proceedings of the IEEE International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/s11263-016-0897-2","article-title":"A hierarchical video description for complex activity understanding","volume":"118","author":"Liu","year":"2016","journal-title":"Int. J. Comput. Vis."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhou, Z.H., and Feng, J. (2017, January 19\u201325). Deep Forest: Towards An Alternative to Deep Neural Networks. Proceedings of the International Joint Conferences on Artificial Intelligence, Melbourne, Australia.","DOI":"10.24963\/ijcai.2017\/497"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.neucom.2016.11.004","article-title":"Human activity prediction using temporally-weighted generalized time warping","volume":"225","author":"Wang","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_11","unstructured":"Feng, Z., and Torre, F.D.L. (2012, January 16\u201321). Generalized Time Warping for Multi-modal Alignment of Human Motion. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, Providence, RI, USA."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ma, S., Sigal, L., and Sclaroff, S. (2016, January 26). Learning Activity Progression in LSTMs for Activity Detection and Early Detection. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kong, Y., Tao, Z., and Yun, F. (2017, January 21\u201326). Deep Sequential Context Networks for Action Prediction. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.390"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P., and Cuzzolin, F. (2017, January 22\u201329). Online Real-time Multiple Spatiotemporal Action Localisation and Prediction. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"35795","DOI":"10.1109\/ACCESS.2019.2904857","article-title":"Early Action Prediction with Generative Adversarial Networks","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_16","unstructured":"Kong, Y., Tao, Z., and Fu, Y. (2020, March 10). Adversarial Action Prediction Networks. Available online: https:\/\/ieeexplore.ieee.org\/abstract\/document\/8543243."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Gang, W., Duan, L.Y., and Kot, A.C. (2018, January 12\u201318). SSNet: Scale Selection Network for Online 3D Action Prediction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00871"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Schydlo, P., Rakovic, M., Jamone, L., and Santos-Victor, J. (2018, January 17\u201319). Anticipation in Human-Robot Cooperation: A Recurrent Neural Network Approach for Multiple Action Sequences Prediction. Proceedings of the IEEE International Conference on Robotics and Automation, Guangzhou, China.","DOI":"10.1109\/ICRA.2018.8460924"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1613\/jair.2470","article-title":"Spectrum of Variable-Random Trees","volume":"32","author":"Liu","year":"2008","journal-title":"J. Artif. Intell. Res."},{"key":"ref_20","first-page":"1","article-title":"An Introduction to the Boot-Strap","volume":"57","author":"Efron","year":"1993","journal-title":"Chapman & Hall"},{"key":"ref_21","unstructured":"Ryoo, M.S., and Aggarwal, J.K. (2020, March 10). UT-Interaction Dataset, ICPR contest on Semantic Description of Human Activities (SDHA). Available online: http:\/\/cvrc.ece.utexas.edu\/SDHA2010\/Human_Interaction.html."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kong, Y., Jia, Y., and Fu, Y. (2012, January 7\u201313). Learning human interaction by interactive phrases. Proceedings of the European Conference on Computer Vision, Florence, Italy.","DOI":"10.1007\/978-3-642-33718-5_22"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1844","DOI":"10.1109\/TPAMI.2015.2491928","article-title":"Max-Margin Action Prediction Machine","volume":"38","author":"Kong","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/11\/3\/158\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:07:18Z","timestamp":1760173638000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/11\/3\/158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,16]]},"references-count":23,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,3]]}},"alternative-id":["info11030158"],"URL":"https:\/\/doi.org\/10.3390\/info11030158","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2020,3,16]]}}}