Action recognition using interest points capturing differential motion information

Yadav, Gaurav; Shukla, Prakhar; Sethfi, Amit

doi:10.1109/icassp.2016.7472003

Cited by 14 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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

132

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

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

132

View full text Add to dashboard Cite

show abstract

“…This has been the approach adopted by [43]. There are also attempts to implement k ‐ mean clustering method directly on HOG or HOF [33, 78] while others simply used HOF on selected and tracked points from TOPs and concatenate them to form a descriptor [28]. Ding and Qu extracted SIFT features from the selected interest points and then used BoW to construct the visual word in order to build the vocabulary for the feature descriptors.…”

Section: Updated Reviewmentioning

confidence: 99%

“…Zhang et al [62], on the other hand, computed only the optical flow information based on the detected STIP. A slightly different approach has been proposed by Yadav et al [28]. Their interest points are based on curl optical flow points that are above some prefixed threshold which are then densely tracked within 15 frames so as to collect temporal information.…”

Section: Updated Reviewmentioning

confidence: 99%

“…Presently, the most popular approach that has shown reliable and consistent performance for classification of human action has been the SVM classifier. Due to the complexity of the problems, there have been also many works that employ different instantiations of SVM such as single‐class SVM [9, 10, 14, 16, 23, 28, 34, 36–39, 42, 45, 47, 53, 60, 63, 64, 66, 67], latent SVM [46], multiclass SVM [12, 13, 19, 26, 35, 44, 51, 57], multiclass Kernel SVM [38, 62]. Wu et al [50] applied a two‐stage classifier in their work.…”

Section: Updated Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Advances in human action recognition: an updated survey

Abu-Bakar

2019

IET image process

View full text Add to dashboard Cite

Research in human activity recognition (HAR) has seen tremendous growth and continuously receiving attention from both the Computer Vision and the Image Processing communities. Due to the existence of numerous publications in this field, undoubtedly, there have been a number of review papers on this subject that categorise these techniques. Many of the recent works have started to tackle more challenging problems and these proposed techniques are addressing more realistic real‐world scenarios. Conspicuously, an updated survey that covers these methods is timely due. To simplify the categorisation, this study takes a two‐layer hierarchical approach. At the top level, the categorisation is based on the basic process flow of HAR, i.e. input data‐type, features‐type, descriptor‐type, and classifier‐type. At the second layer, each of these components is further subcategorised based on the diversity of the proposed methods. Finally, a remark on the coming popularity of deep learning approach in this field is also given.

show abstract

“…Kovashka and Grauman (2010) Hierarchical Space time neighborhood features 94.53% Our Bag of Expression (BoE) 96.68% Wang et al (2011) Dense Trajectories 84.20% Yadav et al (2016) Motion Boundaries and Dense Trajectories 91.30% Mota et al (2013) Tenser Motion Descriptor 75.40% Liu et al (2009) Bag of visual words 71.20% Our Bag of Expression (BoE) 93.42% Duta et al (2017) HMG + iDT Descriptor 93.00% Bag of Words and Fusion Methods 92.30% Wang et al (2016) Dense Trajectories 91.70%…”

Section: Kthmentioning

confidence: 99%

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

Action recognition using interest points capturing differential motion information

Cited by 14 publications

References 18 publications

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

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

Advances in human action recognition: an updated survey

A Bag of Expression framework for improved human action recognition

Contact Info

Product

Resources

About