Multi‐cue combination network for action‐based video classification
Open Access
- 11 July 2019
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 13 (6) , 542-548
Abstract
Action‐based video classification (or video‐based action recognition) is an active research area in computer vision. However, all currently utilised action‐based video classification approaches take spatial and temporal components into consideration while acoustic features ( e.g. sound and speech) are neglected. In this study, the authors propose a novel approach to combine multiple cues ( i.e. both visual and acoustic information) for action‐based video classification. Additionally, they introduce dense connections into their three‐stream network to address the gradient vanishing problem. Experimental results in the Kinetics Human Action Video data set and the Kinetics‐Sounds data set shows that their approach can effectively improve the accuracy in action‐based video classification.Keywords
Funding Information
- National Natural Science Foundation of China (61602407)
This publication has 31 references indexed in Scilit:
- Spatiotemporal Multiplier Networks for Video Action Recognition2017
- Exploring hybrid spatio-temporal convolutional networks for human action recognitionMultimedia Tools and Applications, 2017
- Learning correlations for human action recognition in videosMultimedia Tools and Applications, 2017
- Identity Mappings in Deep Residual Networks2016
- Rethinking the Inception Architecture for Computer Vision2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Long-term recurrent convolutional networks for visual recognition and description2015
- Hand tracking and gesture recognition system for human-computer interaction using low-cost hardwareMultimedia Tools and Applications, 2013
- Intelligent video surveillance system: 3-tier context-aware surveillance system with metadataMultimedia Tools and Applications, 2010
- Event detection and recognition for semantic annotation of videoMultimedia Tools and Applications, 2010