NELGJan 1, 2015

Sequence Modeling using Gated Recurrent Neural Networks

arXiv:1501.00299v116 citations
Originality Synthesis-oriented
AI Analysis

This addresses the problem of realistic motion generation for applications like animation or robotics, but it is incremental as it applies an existing method (GRUs) to a new domain (human motion data).

The paper tackled the problem of modeling human motion data by using Gated Recurrent Units in Recurrent Neural Networks to predict the next data point at each time-step, resulting in the ability to capture long-term dependencies and generate realistic motions.

In this paper, we have used Recurrent Neural Networks to capture and model human motion data and generate motions by prediction of the next immediate data point at each time-step. Our RNN is armed with recently proposed Gated Recurrent Units which has shown promising results in some sequence modeling problems such as Machine Translation and Speech Synthesis. We demonstrate that this model is able to capture long-term dependencies in data and generate realistic motions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes