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...
| Hlavní autoři: | , , |
|---|---|
| Médium: | Conference item |
| Vydáno: |
Institute of Electrical and Electronics Engineers
2016
|