Two-Stream Convolutional Networks for Action Recognition in Videos on ShortScience.org

papers.nips.cc
scholar.google.com

Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, Karen and Zisserman, Andrew
Neural Information Processing Systems Conference - 2014 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 1

[link] Summary by NIPS Conference Reviews 8 years ago

This paper proposes a model for solving discriminative tasks with video inputs. The
model consists of two convolutional nets. The input to one net is an appearance
frame. The input to the second net is a stack of densely computed optical flow
features. Each pathway is trained separately to classify its input. The
prediction for a video is obtained by taking a (weighted) average of the
predictions made by each net.

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private