Bayesian Covariance Representation with Global Informative Prior for 3D Action Recognition

2021 ◽  
Vol 17 (4) ◽  
pp. 1-22
Author(s):  
Jianhai Zhang ◽  
Zhiyong Feng ◽  
Yong Su ◽  
Meng Xing
Keyword(s):  
Action Recognition ◽  
Temporal Order ◽  
State Of The Art ◽  
Feature Representation ◽  
Independent Action ◽  
Sufficient Statistics ◽  
Informative Prior ◽  
Global Action ◽  
High Order Statistics ◽  
Order Structures

For the merits of high-order statistics and Riemannian geometry, covariance matrix has become a generic feature representation for action recognition. An independent action can be represented by an empirical statistics over all of its pose samples. Two major problems of covariance include the following: (1) it is prone to be singular so that actions fail to be represented properly, and (2) it is short of global action/pose-aware information so that expressive and discriminative power is limited. In this article, we propose a novel Bayesian covariance representation by a prior regularization method to solve the preceding problems. Specifically, covariance is viewed as a parametric maximum likelihood estimate of Gaussian distribution over local poses from an independent action. Then, a Global Informative Prior (GIP) is generated over global poses with sufficient statistics to regularize covariance. In this way, (1) singularity is greatly relieved due to sufficient statistics, (2) global pose information of GIP makes Bayesian covariance theoretically equivalent to a saliency weighting covariance over global action poses so that discriminative characteristics of actions can be represented more clearly. Experimental results show that our Bayesian covariance with GIP efficiently improves the performance of action recognition. In some databases, it outperforms the state-of-the-art variant methods that are based on kernels, temporal-order structures, and saliency weighting attentions, among others.

scholarly journals Automatic Detection of Discrimination Actions from Social Images

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 325
Author(s):  
Zhihao Wu ◽  
Baopeng Zhang ◽  
Tianchen Zhou ◽  
Yan Li ◽  
Jianping Fan
Keyword(s):  
Action Recognition ◽  
State Of The Art ◽  
Automatic Detection ◽  
Experimental Results ◽  
Practical Approach ◽  
Detection And Identification ◽  
Art Methods ◽  
Image Set ◽  
Social Images ◽  
Relationship Identification

In this paper, we developed a practical approach for automatic detection of discrimination actions from social images. Firstly, an image set is established, in which various discrimination actions and relations are manually labeled. To the best of our knowledge, this is the first work to create a dataset for discrimination action recognition and relationship identification. Secondly, a practical approach is developed to achieve automatic detection and identification of discrimination actions and relationships from social images. Thirdly, the task of relationship identification is seamlessly integrated with the task of discrimination action recognition into one single network called the Co-operative Visual Translation Embedding++ network (CVTransE++). We also compared our proposed method with numerous state-of-the-art methods, and our experimental results demonstrated that our proposed methods can significantly outperform state-of-the-art approaches.

scholarly journals Disentangled Feature Learning Network for Vehicle Re-Identification

2020 ◽  
Author(s):  
Yan Bai ◽  
Yihang Lou ◽  
Yongxing Dai ◽  
Jun Liu ◽  
Ziqian Chen ◽  
...  
Keyword(s):  
State Of The Art ◽  
Feature Learning ◽  
Feature Representation ◽  
Public Security ◽  
The Public ◽  
Common Features ◽  
Learning Network ◽  
Single Feature ◽  
Art Performance

Vehicle Re-Identification (ReID) has attracted lots of research efforts due to its great significance to the public security. In vehicle ReID, we aim to learn features that are powerful in discriminating subtle differences between vehicles which are visually similar, and also robust against different orientations of the same vehicle. However, these two characteristics are hard to be encapsulated into a single feature representation simultaneously with unified supervision. Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the consistency of the metric scales. The experiments show the effectiveness of our method that achieves state-of-the-art performance on three challenging datasets.

scholarly journals Redundancy Removal Adversarial Active Learning Based on Norm Online Uncertainty Indicator

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jifeng Guo ◽  
Zhiqi Pang ◽  
Wenbo Sun ◽  
Shi Li ◽  
Yu Chen
Keyword(s):  
Active Learning ◽  
Feature Vector ◽  
State Of The Art ◽  
Representation Learning ◽  
The State ◽  
Feature Representation ◽  
Learning Ability ◽  
Redundancy Removal ◽  
Previous State ◽  
Uncertainty Score

Active learning aims to select the most valuable unlabelled samples for annotation. In this paper, we propose a redundancy removal adversarial active learning (RRAAL) method based on norm online uncertainty indicator, which selects samples based on their distribution, uncertainty, and redundancy. RRAAL includes a representation generator, state discriminator, and redundancy removal module (RRM). The purpose of the representation generator is to learn the feature representation of a sample, and the state discriminator predicts the state of the feature vector after concatenation. We added a sample discriminator to the representation generator to improve the representation learning ability of the generator and designed a norm online uncertainty indicator (Norm-OUI) to provide a more accurate uncertainty score for the state discriminator. In addition, we designed an RRM based on a greedy algorithm to reduce the number of redundant samples in the labelled pool. The experimental results on four datasets show that the state discriminator, Norm-OUI, and RRM can improve the performance of RRAAL, and RRAAL outperforms the previous state-of-the-art active learning methods.

scholarly journals A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation

2020 ◽  
Vol 8 ◽  
pp. 93-108 ◽  
Author(s):  
Jian Guan ◽  
Fei Huang ◽  
Zhihao Zhao ◽  
Xiaoyan Zhu ◽  
Minlie Huang
Keyword(s):  
Long Range ◽  
Temporal Order ◽  
State Of The Art ◽  
Knowledge Bases ◽  
Fine Tuning ◽  
Causal Relationships ◽  
Commonsense Knowledge ◽  
Language Generation ◽  
Story Generation ◽  
Global Coherence

Story generation, namely, generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2) still suffer from repetition, logic conflicts, and lack of long-range coherence in generated stories. We conjecture that this is because of the difficulty of associating relevant commonsense knowledge, understanding the causal relationships, and planning entities and events with proper temporal order. In this paper, we devise a knowledge-enhanced pretraining model for commonsense story generation. We propose to utilize commonsense knowledge from external knowledge bases to generate reasonable stories. To further capture the causal and temporal dependencies between the sentences in a reasonable story, we use multi-task learning, which combines a discriminative objective to distinguish true and fake stories during fine-tuning. Automatic and manual evaluation shows that our model can generate more reasonable stories than state-of-the-art baselines, particularly in terms of logic and global coherence.

scholarly journals Action recognition based on 2D skeletons extracted from RGB videos

2019 ◽  
Vol 277 ◽  
pp. 02034
Author(s):  
Sophie Aubry ◽  
Sohaib Laraba ◽  
Joëlle Tilmanne ◽  
Thierry Dutoit
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Action Recognition ◽  
State Of The Art ◽  
Video Stream ◽  
Motion Data ◽  
Rgb Images ◽  
Human Pose ◽  
2D Images ◽  
Made In

In this paper a methodology to recognize actions based on RGB videos is proposed which takes advantages of the recent breakthrough made in deep learning. Following the development of Convolutional Neural Networks (CNNs), research was conducted on the transformation of skeletal motion data into 2D images. In this work, a solution is proposed requiring only the use of RGB videos instead of RGB-D videos. This work is based on multiple works studying the conversion of RGB-D data into 2D images. From a video stream (RGB images), a two-dimension skeleton of 18 joints for each detected body is extracted with a DNN-based human pose estimator called OpenPose. The skeleton data are encoded into Red, Green and Blue channels of images. Different ways of encoding motion data into images were studied. We successfully use state-of-the-art deep neural networks designed for image classification to recognize actions. Based on a study of the related works, we chose to use image classification models: SqueezeNet, AlexNet, DenseNet, ResNet, Inception, VGG and retrained them to perform action recognition. For all the test the NTU RGB+D database is used. The highest accuracy is obtained with ResNet: 83.317% cross-subject and 88.780% cross-view which outperforms most of state-of-the-art results.

scholarly journals Multi-Term Attention Networks for Skeleton-Based Action Recognition

2020 ◽  
Vol 10 (15) ◽  
pp. 5326
Author(s):  
Xiaolei Diao ◽  
Xiaoqiang Li ◽  
Chen Huang
Keyword(s):  
Neural Network ◽  
Time Scales ◽  
Action Recognition ◽  
State Of The Art ◽  
Attention Networks ◽  
Weighted Fusion ◽  
Temporal Features ◽  
Benchmark Datasets ◽  
Spatio Temporal ◽  
Different Time Scales

The same action takes different time in different cases. This difference will affect the accuracy of action recognition to a certain extent. We propose an end-to-end deep neural network called “Multi-Term Attention Networks” (MTANs), which solves the above problem by extracting temporal features with different time scales. The network consists of a Multi-Term Attention Recurrent Neural Network (MTA-RNN) and a Spatio-Temporal Convolutional Neural Network (ST-CNN). In MTA-RNN, a method for fusing multi-term temporal features are proposed to extract the temporal dependence of different time scales, and the weighted fusion temporal feature is recalibrated by the attention mechanism. Ablation research proves that this network has powerful spatio-temporal dynamic modeling capabilities for actions with different time scales. We perform extensive experiments on four challenging benchmark datasets, including the NTU RGB+D dataset, UT-Kinect dataset, Northwestern-UCLA dataset, and UWA3DII dataset. Our method achieves better results than the state-of-the-art benchmarks, which demonstrates the effectiveness of MTANs.

scholarly journals Feature Fusion of Deep Spatial Features and Handcrafted Spatiotemporal Features for Human Action Recognition

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1599 ◽  
Author(s):  
Md Uddin ◽  
Young-Koo Lee
Keyword(s):  
Action Recognition ◽  
State Of The Art ◽  
Human Action Recognition ◽  
Human Action ◽  
Support Vector ◽  
Feature Descriptor ◽  
Weber’S Law ◽  
Weber's Law ◽  
Spatiotemporal Features ◽  
Spatial Features

Human action recognition plays a significant part in the research community due to its emerging applications. A variety of approaches have been proposed to resolve this problem, however, several issues still need to be addressed. In action recognition, effectively extracting and aggregating the spatial-temporal information plays a vital role to describe a video. In this research, we propose a novel approach to recognize human actions by considering both deep spatial features and handcrafted spatiotemporal features. Firstly, we extract the deep spatial features by employing a state-of-the-art deep convolutional network, namely Inception-Resnet-v2. Secondly, we introduce a novel handcrafted feature descriptor, namely Weber’s law based Volume Local Gradient Ternary Pattern (WVLGTP), which brings out the spatiotemporal features. It also considers the shape information by using gradient operation. Furthermore, Weber’s law based threshold value and the ternary pattern based on an adaptive local threshold is presented to effectively handle the noisy center pixel value. Besides, a multi-resolution approach for WVLGTP based on an averaging scheme is also presented. Afterward, both these extracted features are concatenated and feed to the Support Vector Machine to perform the classification. Lastly, the extensive experimental analysis shows that our proposed method outperforms state-of-the-art approaches in terms of accuracy.

scholarly journals Learning Soft Mask Based Feature Fusion with Channel and Spatial Attention for Robust Visual Object Tracking

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 4021 ◽  
Author(s):  
Mustansar Fiaz ◽  
Arif Mahmood ◽  
Soon Ki Jung
Keyword(s):  
Object Tracking ◽  
Spatial Attention ◽  
Feature Fusion ◽  
State Of The Art ◽  
Feature Representation ◽  
Visual Object ◽  
Target Feature ◽  
Visual Object Tracking ◽  
Low Level ◽  
Benchmark Datasets

We propose to improve the visual object tracking by introducing a soft mask based low-level feature fusion technique. The proposed technique is further strengthened by integrating channel and spatial attention mechanisms. The proposed approach is integrated within a Siamese framework to demonstrate its effectiveness for visual object tracking. The proposed soft mask is used to give more importance to the target regions as compared to the other regions to enable effective target feature representation and to increase discriminative power. The low-level feature fusion improves the tracker robustness against distractors. The channel attention is used to identify more discriminative channels for better target representation. The spatial attention complements the soft mask based approach to better localize the target objects in challenging tracking scenarios. We evaluated our proposed approach over five publicly available benchmark datasets and performed extensive comparisons with 39 state-of-the-art tracking algorithms. The proposed tracker demonstrates excellent performance compared to the existing state-of-the-art trackers.

scholarly journals A Hybrid Network for Large-Scale Action Recognition from RGB and Depth Modalities

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3305 ◽  
Author(s):  
Huogen Wang ◽  
Zhanjie Song ◽  
Wanqing Li ◽  
Pichao Wang
Keyword(s):  
Neural Network ◽  
Action Recognition ◽  
Canonical Correlation ◽  
Large Scale ◽  
State Of The Art ◽  
Hybrid Network ◽  
Support Vector ◽  
Multiple Modalities ◽  
Large Margin ◽  
Percentage Points

The paper presents a novel hybrid network for large-scale action recognition from multiple modalities. The network is built upon the proposed weighted dynamic images. It effectively leverages the strengths of the emerging Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) based approaches to specifically address the challenges that occur in large-scale action recognition and are not fully dealt with by the state-of-the-art methods. Specifically, the proposed hybrid network consists of a CNN based component and an RNN based component. Features extracted by the two components are fused through canonical correlation analysis and then fed to a linear Support Vector Machine (SVM) for classification. The proposed network achieved state-of-the-art results on the ChaLearn LAP IsoGD, NTU RGB+D and Multi-modal & Multi-view & Interactive ( M 2 I ) datasets and outperformed existing methods by a large margin (over 10 percentage points in some cases).

Feature Extraction and Representation for Distributed Multi-View Human Action Recognition

2013 ◽  
Vol 3 (2) ◽  
pp. 145-154 ◽  
Author(s):  
Jiajia Luo ◽  
Wei Wang ◽  
Hairong Qi
Keyword(s):  
Action Recognition ◽  
Approximation Error ◽  
Human Action Recognition ◽  
Human Action ◽  
Base Station ◽  
Feature Representation ◽  
Superior Performance ◽  
Feature Descriptor ◽  
Testing Stage ◽  
New Feature

Multi-view human action recognition has gained a lot of attention in recent years for its superior performance as compared to single view recognition. In this paper, we propose a new framework for the real-time realization of human action recognition in distributed camera networks (DCNs). We first present a new feature descriptor (Mltp-hist) that is tolerant to illumination change, robust in homogeneous region and computationally efficient. Taking advantage of the proposed Mltp-hist, the noninformative 3-D patches generated from the background can be further removed automatically that effectively highlights the foreground patches. Next, a new feature representation method based on sparse coding is presented to generate the histogram representation of local videos to be transmitted to the base station for classification. Due to the sparse representation of extracted features, the approximation error is reduced. Finally, at the base station, a probability model is produced to fuse the information from various views and a class label is assigned accordingly. Compared to the existing algorithms, the proposed framework has three advantages while having less requirements on memory and bandwidth consumption: 1) no preprocessing is required; 2) communication among cameras is unnecessary; and 3) positions and orientations of cameras do not need to be fixed. We further evaluate the proposed framework on the most popular multi-view action dataset IXMAS. Experimental results indicate that our proposed framework repeatedly achieves state-of-the-art results when various numbers of views are tested. In addition, our approach is tolerant to the various combination of views and benefit from introducing more views at the testing stage. Especially, our results are still satisfactory even when large misalignment exists between the training and testing samples.

Sign in / Sign up

Export Citation Format

Share Document