Action Recognition Based on Multi-scale Oriented Neighborhood Features

Yang, Jiangfeng; Ma, Zheng; Xie, Mei

doi:10.14257/ijsip.2015.8.1.21

Cited by 9 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This combined approach retains the HOG precision rate to improve the detection rate. Yang et al [ 119 ] constructed a neighborhood by adding weights on the distance components. SONFs and MONFs are generated by concatenating multiple SONFs.…”

Section: Experimentation Setup and Analysismentioning

confidence: 99%

A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition

Johnson

Uthariaraj

2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Human action recognition is a trending topic in the field of computer vision and its allied fields. The goal of human action recognition is to identify any human action that takes place in an image or a video dataset. For instance, the actions include walking, running, jumping, throwing, and much more. Existing human action recognition techniques have their own set of limitations when it concerns model accuracy and flexibility. To overcome these limitations, deep learning technologies were implemented. In the deep learning approach, a model learns by itself to improve its recognition accuracy and avoids problems such as gradient eruption, overfitting, and underfitting. In this paper, we propose a novel parameter initialization technique using the Maxout activation function. Firstly, human action is detected and tracked from the video dataset to learn the spatial-temporal features. Secondly, the extracted feature descriptors are trained using the RBM-NN. Thirdly, the local features are encoded into global features using an integrated forward and backward propagation process via RBM-NN. Finally, an SVM classifier recognizes the human actions in the video dataset. The experimental analysis performed on various benchmark datasets showed an improved recognition rate when compared to other state-of-the-art learning models.

show abstract

Section: Experimentation Setup and Analysismentioning

confidence: 99%

A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition

Johnson

Uthariaraj

2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…It should be noted that BoE performance was optimized for KTH dataset as discussed in section 3.1. BoE outperforms MultiScale Neighborhood features (MONFs) based approach for UCF Sports and KTH dataset (Yang et al, 2015). MONFs was formed by concatenating Single scale neighborhood features (SONF).…”

Section: Comparison With State-of-the-artmentioning

confidence: 99%

“…Bag of Expression (BoE) 97.33% Peng and Schmid (2016) Multi Region two stream R-CNN 95.74% Abdulmunem et al (2016) Bag of Visual words 90.90% Wang et al (2013) Dense Trajectories and motion boundary descriptor 88.00% Yang et al (2015) Multi-scale oriented neighborhood features 91.80%…”

Section: Ourmentioning

confidence: 99%

“…Kovashka and Grauman (2010) Hierarchical Space time neighborhood features 87.27% Our Bag of Expression (BoE) 99.51% Abdulmunem et al (2016) Bag of Visual words 97.20% Wang et al (2013) Dense Trajectories and motion boundary descriptor 95.00% Gilbert et al (2011) Mined Hierarchical compound features 94.50% Yang et al (2015) Multi-scale oriented neighborhood features 96.50%…”

Section: Ucf Sportsmentioning

confidence: 99%

“…However, their approach is computationally expensive and its performance is limited by the available optical flow quality. Yang et al (2015) represented features using multi-scale oriented neighborhood features (MONFs), which are formed by concatenating Singlescale Oriented Neighborhood Features (SONF). They evaluated their approach on KTH and UCF Sports dataset and stated that the proposed method outperforms the local ST features based method for action recognition.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Bag of Expression framework for improved human action recognition

Nazir

Yousaf

Nebel

et al. 2018

Pattern Recognition Letters

View full text Add to dashboard Cite

The Bag of Words (BoW) approach has been widely used for human action recognition in recent state-of-the-art methods. In this paper, we introduce what we call a Bag of Expression (BoE) framework, based on the bag of words method, for recognizing human action in simple and realistic scenarios. The proposed approach includes space time neighborhood information in addition to visual words. The main focus is to enhance the existing strengths of the BoW approach like view independence, scale invariance and occlusion handling. BOE includes independent pairs of neighbors for building expressions, therefore it is tolerant to occlusion and capable of handling view independence up to some extent in realistic scenarios. Our main contribution includes learning a class specific visual words extraction approach for establishing a relationship between these extracted visual words in both space and time dimension. Finally, we have carried out a set of experiments to optimize different parameters and compare its performance with recent state-of-the-art-methods. Our approach outperforms existing Bag of Words based approaches, when evaluated using the same performance evaluation methods. We tested our approach on four publicly available datasets for human action recognition i.e. UCF-Sports, KTH, UCF11 and UCF50 and achieve significant results i.e. 97.3%, 99.5%, 96.7% and 93.42% respectively in terms of average accuracy.

show abstract

Human action recognition with salient trajectories and multiple kernel learning

Pan²,

Deng³

2017

Multimed Tools Appl

View full text Add to dashboard Cite

Action Recognition Based on Multi-scale Oriented Neighborhood Features

Cited by 9 publications

References 44 publications

A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition

A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition

A Bag of Expression framework for improved human action recognition

Human action recognition with salient trajectories and multiple kernel learning

Contact Info

Product

Resources

About