Convolutional two-stream network fusion for video action recognition

Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take adv...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς: Feichtenhofer, C, Pinz, A, Zisserman, A
Μορφή: Conference item
Έκδοση: Institute of Electrical and Electronics Engineers 2016