RNN Fisher Vectors for Action Recognition and Image Annotation

12/12/2015
by   Guy Lev, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/29/2018

Histogram of Oriented Depth Gradients for Action Recognition

In this paper, we report on experiments with the use of local measures f...
research
12/26/2017

Actionable Email Intent Modeling with Reparametrized RNNs

Emails in the workplace are often intentional calls to action for its re...
research
12/14/2017

Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition

Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. H...
research
12/25/2018

Coupled Recurrent Network (CRN)

Many semantic video analysis tasks can benefit from multiple, heterogeno...
research
09/07/2015

An end-to-end generative framework for video segmentation and recognition

We describe an end-to-end generative approach for the segmentation and r...
research
10/03/2020

A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition

In the last few years, compression of deep neural networks has become an...
research
02/04/2016

Comparative Evaluation of Action Recognition Methods via Riemannian Manifolds, Fisher Vectors and GMMs: Ideal and Challenging Conditions

We present a comparative evaluation of various techniques for action rec...

Please sign up or login with your details

Forgot password? Click here to reset