Learning features for action recognition and identity with deep belief networks

Ali, Khawlah Hussein; Wang, Tianjiang

doi:10.1109/icalip.2014.7009771

Cited by 17 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future work, we shall continue investigating ways to deal with the 3D CNN model for action recognition. There are also other deep architectures, such as the deep belief networks [16], which achieve promising performance on action recognition tasks. It's also an interesting research direction.…”

Section: Discussionmentioning

confidence: 99%

Human Action Recognition based on Convolutional Neural Networks with a Convolutional Auto-Encoder

Geng¹,

Song²

2016

Advances in Computer Science Research

View full text Add to dashboard Cite

Human action recognition (HAR) research is hot in computer vision, but high precision recognition of human action in the complex background is still an open question. Most current methods build classifiers based on complex handcrafted features computed from the raw inputs, which are driven by tasks and uncertain. In this paper, type of deep model convolutional neural network (CNN) is proposed for HAR that can act directly on the raw inputs. In addition, an efficient pre-training strategy has been introduced to reduce the high computational cost of kernel training to enable improved real-world applications. The proposed approach has been tested on the KTH database and the achieved results compares favorably against state-of-the-art algorithms using hand-designed features.

show abstract

Section: Discussionmentioning

confidence: 99%

Human Action Recognition based on Convolutional Neural Networks with a Convolutional Auto-Encoder

Geng¹,

Song²

2016

Advances in Computer Science Research

View full text Add to dashboard Cite

show abstract

“…Method Database split Training time Processing speed s1 scenario Full database Yadav et al 30 IP + SVM 80%-20% ---98.20% Shi et al 31 DTD, DNN 9-16 ---95.6% Kovashka et al 32 BoW + SVM 8-8-9 ---94.53% Gilbert et al 33 HCF + SVM LOOCV ∼ 5.6 h 24 fps -94.5% Baccouche et al 34 CNN & RNN 16-9 ---94.39% Ali and Wang 35 DBN & SVM 50%-20%-30% ---94.3% Wang et al 36 DT + SVM 16-9 ---94.2% Liu et al 37 MMI + SVM LOOCV ---94.15% Sun et al 38 FT + SVM auto ---94.0% Veeriah et al 39 Differential 46 MT cells 16-9 --74.63% -Schuldt et al 22 FT + SVM 8-8-9 ---71.83% Table 1. Performance of various state-of-the-art digital approaches compared to our best experimental result.…”

Section: Performance Authorsmentioning

confidence: 99%

Human action recognition with a large-scale brain-inspired photonic computer

Antonik¹,

Marsal²,

Brunner³

et al. 2019

Nat Mach Intell

122

View full text Add to dashboard Cite

The recognition of human actions in video streams is a challenging task in computer vision, with cardinal applications in e.g. brain-computer interface and surveillance. Deep learning has shown remarkable results recently, but can be found hard to use in practice, as its training requires large datasets and special purpose, energy-consuming hardware. In this work, we propose a scalable photonic neuro-inspired architecture based on the reservoir computing paradigm, capable of recognising video-based human actions with state-of-the-art accuracy. Our experimental optical setup comprises off-the-shelf components, and implements a large parallel recurrent neural network that is easy to train and can be scaled up to hundreds of thousands of nodes. This work paves the way towards simply reconfigurable and energy-efficient photonic information processing systems for real-time video processing.

show abstract

“…To evaluate our proposed method, we compared the obtained classification results with several methods of the state-of-the-art using deep learning methods and using the same datasets. Considering the KTH, our method with an average accuracy equal to 94.83% outperforms Ali and Wang method [10] (94.3%), Geng and Song method [12] (92.49%), Baccouche et al method [22] (91.04%) and Ji et al method [14] (90.2%). For UIUC dataset, with an average accuracy equal 96%, we obtained also better results compared to Chalamala and Kumar method [23] (80%).…”

Section: Comparison With Existing Deep Learning Methodsmentioning

confidence: 84%

“…In the second part, we present works that employ deep learning technique. Ali and Wang [10] have proposed a human action modeling method based upon a two-dimensional wavelet and watermark embedding. The authors made use of DBN and the Discrete Cosine Transform technique for data learning and feature extraction.…”

Section: Related Workmentioning

confidence: 99%

Human Action Recognition in Video Sequences Using Deep Belief Networks

Abdellaoui¹,

Douik²

2020

View full text Add to dashboard Cite

For the last several decades, Human Activity Recognition (HAR) has been an intriguing topic in the domain of artificial intelligence research, since it has applications in many areas, such as image and signal processing. Generally, every recognition system can be either an end-to-end system or including two phases: feature extraction and classification. In order to create an optimal HAR system that offers a better quality of classification prediction, in this paper we propose a new approach within two-phase recognition system paradigm. Probabilistic generative models, known as Deep Belief Networks (DBNs), are introduced. These DBNs comprise a series of Restricted Boltzmann Machines (RBMs) and are responsible for data reconstruction, feature construction and classification. We tested our approach on the KTH and UIUC human action datasets. The results obtained are very promising, with the recognition accuracy outperforming the recent state-of-the-art.

show abstract

Learning features for action recognition and identity with deep belief networks

Cited by 17 publications

References 20 publications

Human Action Recognition based on Convolutional Neural Networks with a Convolutional Auto-Encoder

Human Action Recognition based on Convolutional Neural Networks with a Convolutional Auto-Encoder

Human action recognition with a large-scale brain-inspired photonic computer

Human Action Recognition in Video Sequences Using Deep Belief Networks

Contact Info

Product

Resources

About