Logo image
Redundancy and attention in convolutional LSTM for gesture recognition
Journal article   Peer reviewed

Redundancy and attention in convolutional LSTM for gesture recognition

G. Zhu, L. Zhang, L. Yang, L. Mei, S.A.A. Shah, M. Bennamoun and P. Shen
IEEE Transactions on Neural Networks and Learning Systems, Vol.31(4), pp.1323-1335
2020
url
Link to Published Version *Subscription may be requiredView

Abstract

Convolutional long short-term memory (ConvLSTM) networks have been widely used for action/gesture recognition, and different attention mechanisms have also been embedded into ConvLSTM networks. This paper explores the redundancy of spatial convolutions and the effects of the attention mechanism in ConvLSTM, based on our previous gesture recognition architectures that combine the 3-D convolutional neural network (CNN) and ConvLSTM. Depthwise separable, group, and shuffle convolutions are used to replace the convolutional structures in ConvLSTM for the redundancy analysis. In addition, four ConvLSTM variants are derived for attention analysis: 1) by removing the convolutional structures of the three gates in ConvLSTM; 2) by applying the attention mechanism on the ConvLSTM input; and 3) by reconstructing the input and 4) output gates with the modified channelwise attention mechanism. Evaluation results demonstrate that the spatial convolutions in the three gates scarcely contribute to the spatiotemporal feature fusion and that the attention mechanisms embedded into the input and output gates cannot improve the feature fusion. In other words, ConvLSTM mainly contributes to the temporal fusion along with the recurrent steps to learn long-term spatiotemporal features when taking spatial or spatiotemporal features as input. A new LSTM variant is derived on this basis in which the convolutional structures are embedded only into the input-to-state transition of LSTM. The code of the LSTM variants is publicly available. 1 1

Details

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#11 Sustainable Cities and Communities

Source: InCites

Metrics

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types
Domestic collaboration
International collaboration
Citation topics
4 Electrical Engineering, Electronics & Computer Science
4.116 Robotics
4.116.1097 Gesture Recognition
Web Of Science research areas
Computer Science, Artificial Intelligence
Computer Science, Hardware & Architecture
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
ESI research areas
Computer Science
Logo image