DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 2625 - 2632
• Main Authors: Sun, Lin, Jia, Kui, Chan, Tsung-Han, Fang, Yuqiang, Wang, Gang, Yan, Shuicheng
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Abstracts; action recognition; Computer vision; Convolution; deep learning; Feature extraction; Feature recognition; Invariants; Kernel; Learning; Pattern recognition; Recognition; Representations; Sampling; slow feature analysis; Three dimensional; Three-dimensional displays; Video sequences; Visualization

Most of the previous work on video action recognition use complex hand-designed local features, such as SIFT, HOG and SURF, but these approaches are implemented sophisticatedly and difficult to be extended to other sensor modalities. Recent studies discover that there are no universally best hand-en...