{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T09:05:25Z","timestamp":1794474325143,"version":"4.9.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>Predicting future actions from observed partial videos is very challenging as the missing future is uncertain and sometimes has multiple possibilities. To obtain a reliable future estimation, a novel encoder-decoder architecture is proposed for integrating the tasks of synthesizing future motions from observed videos and reconstructing observed motions from synthesized future motions in an unified framework, which can capture the bi-directional dynamics depicted in partial videos along the temporal (past-to-future) direction and reverse chronological (future-back-to-past) direction. We then employ a bi-directional long short-term memory (Bi-LSTM) architecture to exploit the learned bi-directional dynamics for predicting early actions. Our experiments on two benchmark action datasets show that learning bi-directional dynamics benefits the early action prediction and our system clearly outperforms the state-of-the-art methods.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/126","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"897-903","source":"Crossref","is-referenced-by-count":27,"title":["DBDNet: Learning Bi-directional Dynamics for Early Action Prediction"],"prefix":"10.24963","author":[{"given":"Guoliang","family":"Pang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xionghui","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Fang","family":"Hu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, China"},{"name":"Guangdong Province Key Laboratory of Information Security Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, China"},{"name":"Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:58Z","timestamp":1564300018000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/126"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/126","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}