Video Description Using Bidirectional Recurrent Neural Networks

Abstract

Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions. The combination of Convolutional and Recurrent Neural Networks in these models has proven to outperform the previous state of the art, obtaining more accurate video descriptions. In this… (More)
DOI: 10.1007/978-3-319-44781-0_1

Topics

4 Figures and Tables

Statistics

0204020162017
Citations per Year

Citation Velocity: 13

Averaging 13 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Slides referencing similar topics