Sequence to Sequence - Video to Text on ShortScience.org

dx.doi.org
sci-hub
scholar.google.com

Sequence to Sequence - Video to Text
Venugopalan, Subhashini and Rohrbach, Marcus and Donahue, Jeffrey and Mooney, Raymond J. and Darrell, Trevor and Saenko, Kate
International Conference on Computer Vision - 2015 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 1

[link] Summary by beahacker 8 years ago

It is a nice paper on video captioning. They exploit LSTM ability to learn long term dependencies to modeling the problem of translating video sequence to language sequence. The new thing in this paper is that they have two LSTM layers for modeling frames in videos and also words in sentences.

Your comment:

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

Anon Private