Self-supervised spatio-temporal representation learning for videos by predicting motion and appearance statistics

• Main Authors: WANG, Jiangliu, JIAO, Jianbo, BAO, Linchao, HE, Shengfeng, LIU, Yunhui, LIU, Wei
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Representation learning; Video analytics; Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8439; https://ink.library.smu.edu.sg/context/sis_research/article/9442/viewcontent/Wang_Self_Supervised_Spatio_Temporal_Representation_Learning_for_Videos_by_Predicting_Motion_and_CVPR_2019_paper.pdf
• Institution: Singapore Management University

We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a frame-by-frame basis, which are not applicable to many video analytic tas...