Multi-Layered Deep Learning Features Fusion for Human Action Recognition
Source abstract
Abstract
Human Action Recognition (HAR) is an active research topic in machine learning for the last few decades. Visual surveillance, robotics, and pedestrian detection are the main applications for action recognition. Computer visio... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Human Pose and Action Recognition · Anomaly Detection Techniques and Applications · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (36)
Show source-provided references
1. A new hybrid deep learning model for human action recognition10.1016/j.jksuci.2019.09.004 ↗
2. An implementation of optimized framework for action classification using multilayers neural network on selected fused features
3. Intelligent human action recognition: A framework of optimal features selection based on euclidean distance and strong correlation
4. Traditional features based automated system for human activities recognition
5. A multilevel paradigm for deep convolutional neural network features selection with an application to human gait recognition
6. A resource conscious human action recognition framework using 26-layered deep convolutional neural network
7. Human action recognition using fusion of multiview and deep features: an application to video surveillance
8. Human action recognition: A framework of statistical weighted segmentation and rank correlation-based selection10.1007/s10044-019-00789-0 ↗
9. Improved strategy for human action recognition; Experiencing a cascaded design
10. 3D convolutional neural networks for human action recognition10.1109/TPAMI.2012.59 ↗
11. A survey of depth and inertial sensor fusion for human action recognition10.1007/s11042-015-3177-1 ↗
12. Highly refined human action recognition model to handle intraclass variability & interclass similarity10.1007/s11042-019-7392-z ↗
13. On space-time interest points10.1007/s11263-005-1838-7 ↗
14. The recognition of human movement using temporal templates10.1109/34.910878 ↗
15. A spatio-temporal descriptor based on 3d-gradients
16. An efficient dense and scale-invariant spatio-temporal interest point detector
17. A 3-dimensional sift descriptor and its application to action recognition
18. Dense trajectories and motion boundary descriptors for action recognition10.1007/s11263-012-0594-8 ↗
19. An implementation of optimized framework for action classification using multilayers neural network on selected fused features10.1007/s10044-018-0688-1 ↗
20. Action recognition using optimized deep autoencoder and CNN for surveillance data streams of non-stationary environments10.1016/j.future.2019.01.029 ↗
21. A sustainable deep learning framework for object recognition using multilayers deep features fusion and selection10.3390/su12125037 ↗
22. L. Wang, P. Koniusz and D. Q. Huynh, “Hallucinating bag-of-words and fisher vector IDT terms for CNN-based action recognition,” arXiv preprint arXiv: 1906.05910, 2019.
23. Region-sequence based six-stream CNN features for general and fine-grained human action recognition in videos10.1016/j.patcog.2017.11.026 ↗
24. A framework of human action recognition using length control features fusion and weighted entropy-variances based feature selection10.1016/j.imavis.2020.104090 ↗
25. Transferable two-stream convolutional neural network for human action recognition10.1016/j.jmsy.2020.04.007 ↗
26. A combined multiple action recognition and summarization for surveillance video sequences10.1007/s10489-020-01823-z ↗
27. Enhancing CNN with preprocessing stage in automatic emotion recognition10.1016/j.procs.2017.10.038 ↗
28. Deep residual learning for image recognition
29. Canonical correlation analysis for data fusion and group inferences10.1109/MSP.2010.936725 ↗
30. Multi-views action recognition on deep learning and K-SVD
31. Hexagonal volume local binary pattern (H-VLBP) with deep stacked autoencoder for human action recognition10.1016/j.cogsys.2019.03.001 ↗
32. Human action recognition with salient trajectories and multiple kernel learning10.1007/s11042-017-5209-5 ↗
33. On-line deep learning method for action recognition10.1007/s10044-014-0404-8 ↗
34. A novel 3D gradient LBP descriptor for action recognition
35. Hierarchical clustering multi-task learning for joint human action grouping and recognition10.1109/TPAMI.2016.2537337 ↗
36. On an algorithm for human action recognition10.1016/j.eswa.2018.08.014 ↗