Action Anticipation with RBF KernelizedFeature Mapping RNN

11/18/2019
by   Yuge Shi, et al.
13

We introduce a novel Recurrent Neural Network-based algorithm for future video feature generation and action anticipation called feature mapping RNN. Our novel RNN architecture builds upon three effective principles of machine learning, namely parameter sharing, Radial Basis Function kernels and adversarial training. Using only some of the earliest frames of a video, the feature mapping RNN is able to generate future features with a fraction of the parameters needed in traditional RNN. By feeding these future features into a simple multi-layer perceptron facilitated with an RBF kernel layer, we are able to accurately predict the action in the video. In our experiments, we obtain 18 UT-Interaction datasets over prior state-of-the-art for action anticipation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/18/2019

Action Anticipation with RBF Kernelized Feature Mapping RNN

We introduce a novel Recurrent Neural Network-based algorithm for future...
research
04/28/2019

Hierarchical Recurrent Neural Network for Video Summarization

Exploiting the temporal dependency among video frames or subshots is ver...
research
12/26/2014

Polyphonic Music Generation by Modeling Temporal Dependencies Using a RNN-DBN

In this paper, we propose a generic technique to model temporal dependen...
research
06/02/2021

Framing RNN as a kernel method: A neural ODE approach

Building on the interpretation of a recurrent neural network (RNN) as a ...
research
02/27/2020

Hierarchical Memory Decoding for Video Captioning

Recent advances of video captioning often employ a recurrent neural netw...
research
03/18/2017

Recurrent Models for Situation Recognition

This work proposes Recurrent Neural Network (RNN) models to predict stru...
research
11/01/2017

Performance Evaluation of Channel Decoding With Deep Neural Networks

With the demand of high data rate and low latency in fifth generation (5...

Please sign up or login with your details

Forgot password? Click here to reset