RNN Fisher Vectors for Action Recognition and Image Annotation

Recurrent Neural Networks (RNNs) have had considerable success in classifying and predicting sequences. We demonstrate that RNNs can be effectively used in order to encode sequences and provide effective representations. The methodology we use is based on Fisher Vectors, where the RNNs are the gener...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2015-12
Main Authors: Lev, Guy, Sadeh, Gil, Klein, Benjamin, Wolf, Lior
Format: Article
Language:English
Subjects:
Back propagation
Image annotation
Image classification
Neural networks
Object recognition
Probabilistic models
Recurrent neural networks
Sequences
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recurrent Neural Networks (RNNs) have had considerable success in classifying and predicting sequences. We demonstrate that RNNs can be effectively used in order to encode sequences and provide effective representations. The methodology we use is based on Fisher Vectors, where the RNNs are the generative probabilistic models and the partial derivatives are computed using backpropagation. State of the art results are obtained in two central but distant tasks, which both rely on sequences: video action recognition and image annotation. We also show a surprising transfer learning result from the task of image annotation to the task of video action recognition.
ISSN:2331-8422