Convolutional Two-Stream Network Fusion for Video Action Recognition

CVPR 2016 Christoph FeichtenhoferAxel PinzAndrew Zisserman

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 advantage of this spatio-temporal information... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.