The Complex Action Recognition via the Correlated Topic Model

Tu, Hong-bin; Xia, Limin; Wang, Zhengwu

doi:10.1155/2014/810185

Cited by 11 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method compared favourably with existing techniques, achieving higher classification accuracy for the KTH dataset and comparable accuracy for the Weizmann dataset. For Tu et al [65], it was reported that this is the 'average accuracy', but it is not clear if they used the leave-one-out cross validation. Shao et al [66] reported 95.37% accuracy for the KTH dataset and 100% for the Weizmann dataset.…”

Section: Experiments Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Fusing directional wavelet local binary pattern and moments for human action recognition

Al-Berry

Salem

Ebeid

et al. 2016

IET Computer Vision

View full text Add to dashboard Cite

Recently, transformation‐based methods have been widely used in many computer vision areas because of their powerful representation ability. One of the most widely used transforms is the wavelet transform that has proved to be very useful in many applications. In this study, a new method for human action representation and description is proposed. This method combines the advantages of local and global descriptions. The method works by fusing the Hu invariant moments as global descriptors with a new local descriptor that is based on three‐dimensional stationary wavelet transform and the concept of local binary patterns. The performance of the new method was examined in two different ways. The first one is by fusing the proposed directional global and local features in one feature vector, while the other is using the features of different directional bands separately to train multiple classifiers and then using a voting scheme to vote for the best match. The performance of the proposed method is verified using standard datasets, achieving high accuracy in comparison with state‐of‐the‐art methods. In addition, the proposed method is proved to be robust to the changes in lighting and scale variations, but it exhibits limitations towards dynamic backgrounds.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

“…[69] 88.81 92.2 Bregonzio (2012) [70] 94.33 96. 66 Tu et al (2014) [65] 90.6 89.20 Shao et al (2015) [66] 95.37 100 Fig. 11 Confusion matrices obtained for the KTH dataset using the voting scheme…”

Section: Discussionmentioning

confidence: 98%

Fusing directional wavelet local binary pattern and moments for human action recognition

Al-Berry

Salem

Ebeid

et al. 2016

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…in order to reduce the resolution size of the images and finally to have the most minimal execution 21 95, 6 SIFT-3D (Scale Invariant Feature Transform) 39 82, 6 HOG-3D (Histogram of Oriented Gradients 3D) 5 84, 3 OF+CTM (Optical Flow and Correlated Topic Model ) 40 89.20 HOG-NSP (Histogram of Oriented Gradients with Nine Symmetry Planes) 24 95, 9…”

Section: Human Action Recognitionmentioning

confidence: 99%

Spatial image polynomial decomposition with application to video classification

Moubtahij¹,

Augereau

Tairi

et al. 2015

J. Electron. Imaging

View full text Add to dashboard Cite

International audienceThis paper addresses the use of orthogonal polynomial basis transform in video classification due to its multiple advantages, especially for multiscale and multiresolution analysis similar to the wavelet transform. In our approach, we benefit from these advantages to reduce the resolution of the video by using a multiscale/multiresolution decomposition to define a new algorithm that decomposes a color image into geometry and texture component by projecting the image on a bivariate polynomial basis and considering the geometry component as the partial reconstruction and the texture component as the remaining part, and finally to model the features (like motion and texture) extracted from reduced image sequences by projecting them into a bivariate polynomial basis in order to construct a hybrid polynomial motion texture video descriptor. To evaluate our approach, we consider two visual recognition tasks, namely the classification of dynamic textures and recognition of human actions. The experimental section shows that the proposed approach achieves a perfect recognition rate in the Weizmann database and highest accuracy in the Dyntex++ database compared to existing methods

show abstract

“…These representations result in clear human modeling, although the complexity of joint/skeleton estimation requires good accuracy from tracking and prediction. Motion/flow-based representation is a global feature-based method using the motion or flow of an object, such as invariant motion history volume [ 22 ], local descriptors from optical-flow trajectories [ 23 ], KLT motion-based snippet trajectories [ 24 ], Divergence-Curl-Shear descriptors [ 25 ], hybrid features using contours and optical flow [ 26 ], motion history and optical-flow images [ 27 ], multilevel motion sets [ 28 ], projection of accumulated motion energy [ 29 ], pyramid of spatial-temporal motion descriptors [ 30 ], and motion and optical flow with Markov random fields for occlusion estimation [ 31 ]. These methods do not require accurate background subtractions but make use of acquired, inconstant features that need strategy and descriptors to manage.…”

Section: Introductionmentioning

confidence: 99%

Multiview Layer Fusion Model for Action Recognition Using RGBD Images

Chalearnnetkul

Suvonvorn

2018

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Vision-based action recognition encounters different challenges in practice, including recognition of the subject from any viewpoint, processing of data in real time, and offering privacy in a real-world setting. Even recognizing profile-based human actions, a subset of vision-based action recognition, is a considerable challenge in computer vision which forms the basis for an understanding of complex actions, activities, and behaviors, especially in healthcare applications and video surveillance systems. Accordingly, we introduce a novel method to construct a layer feature model for a profile-based solution that allows the fusion of features for multiview depth images. This model enables recognition from several viewpoints with low complexity at a real-time running speed of 63 fps for four profile-based actions: standing/walking, sitting, stooping, and lying. The experiment using the Northwestern-UCLA 3D dataset resulted in an average precision of 86.40%. With the i3DPost dataset, the experiment achieved an average precision of 93.00%. With the PSU multiview profile-based action dataset, a new dataset for multiple viewpoints which provides profile-based action RGBD images built by our group, we achieved an average precision of 99.31%.

show abstract

The Complex Action Recognition via the Correlated Topic Model

Cited by 11 publications

References 33 publications

Fusing directional wavelet local binary pattern and moments for human action recognition

Fusing directional wavelet local binary pattern and moments for human action recognition

Spatial image polynomial decomposition with application to video classification

Multiview Layer Fusion Model for Action Recognition Using RGBD Images

Contact Info

Product

Resources

About