Differential Recurrent Neural Networks for Action Recognition

Abstract

The long short-term memory (LSTM) neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from long input sequences. It has the potential to model any sequential time-series data, where the current hidden state has to be considered in the context of the past hidden states. This property makes LSTM an ideal choice to learn the complex dynamics of various actions. Unfortunately, the conventional LSTMs do not consider the impact of spatio-temporal dynamics corresponding to the given salient motion patterns, when they gate the information that ought to be memorized through time. To address this problem, we propose a differential gating scheme for the LSTM neural network, which emphasizes on the change in information gain caused by the salient motions between the successive frames. This change in information gain is quantified by Derivative of States (DoS), and thus the proposed LSTM model is termed as differential Recurrent Neural Network (dRNN). We demonstrate the effectiveness of the proposed model by automatically recognizing actions from the real-world 2D and 3D human action datasets. Our study is one of the first works towards demonstrating the potential of learning complex time-series representations via high-order derivatives of states.

References in corpus (1)

• DRAW: A Recurrent Neural Network For Image Generation

Cited by in corpus (10)

• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• Action Recognition with Joint Attention on Multi-Level Deep Features
• Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates
• Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
• Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection
• Large-scale Isolated Gesture Recognition Using Convolutional Neural Networks
• Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions
• Summarization of ICU Patient Motion from Multimodal Multiview Videos
• Discriminatively Learned Hierarchical Rank Pooling Networks
• Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks