Aggressive Action Estimation: A Comprehensive Review on Neural Network Based Human Segmentation and Action Recognition
Open Access
- 8 January 2019
- journal article
- review article
- Published by MECS Publisher in International Journal of Education and Management Engineering
- Vol. 9 (1) , 9-19
Abstract
Human action recognition has been a talked topic since machine vision was coined. With the advent of neural networks and deep learning methods, various architectures were suggested to address the problems within a context. Convolutional neural network has been the primary go-to architecture for image segmentation, flow estimation and action recognition in recent days. As the problem itself is an extended version of various subproblems, such as frame segmentation, spatial and temporal feature extraction, motion modeling and action classification as a whole, some methods reviewed in this paper addressed sub-problems and some tried to address a single architecture to the action recognition problem. While being a success, convolution neural networks have drawbacks in its pooling methods. CapsNet, on the other hand, uses squashing function to determine the activation. Also it addresses spatiotemporal information with the normalized vector maps while CNN-based methods extracts feature map for spatial and temporal information and later augment them in a fusion layer for combining two separate feature maps. Critical review of papers provided in this work can contribute significantly in addressing human action recognition problem as a whole.Keywords
This publication has 11 references indexed in Scilit:
- Brain Tumor Type Classification via Capsule Networks2018
- Action-Attending Graphic Neural NetworkIEEE Transactions on Image Processing, 2018
- Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching2017
- Lattice Long Short-Term Memory for Human Action Recognition2017
- View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data2017
- Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition2017
- Spatiotemporal Pyramid Network for Video Action Recognition2017
- Learning a Deep Model for Human Action Recognition from Novel ViewpointsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in VideoInternational Journal of Computer Vision, 2016
- Deep learning in vision-based static hand gesture recognitionNeural Computing and Applications, 2016